What If AI Understood Images Like We Do? This Model Might

Authors: (1) Hyeongjun Kwon, Yonsei University; (2) Jinhyun Jang, Yonsei University; (3) Jin Kim, Yonsei University; (4) Kwonyoung Kim, Yonsei University; (5) Kwanghoon Sohn, Yonsei University and Korea Institute of Science and Technology (KIST). Table of Links Abstract and 1 Introduction 2. Related Work 3. Hyperbolic Geometry 4. Method 4.1. Overview 4.2. Probabilistic hierarchy tree 4.3. Visual hierarchy decomposition 4.4. Learning hierarchy in hyperbolic space 4.5. Visual hierarchy encoding 5. Experiments and 5.1. Image classification 5.2. Object detection and Instance segmentation 5.3. Semantic segmentation 5.4. Visualization 6. Ablation studies and discussion 7. Conclusion and References A. Network Architecture B. Theoretical Baseline C. Additional Results D. Additional visualization 7. Conclusion In this paper, we have presented a novel Visual Hierarchy Mapper (Hi-Mapper) that investigates the hierarchical organization of visual scenes. We have achieved the goal by newly defining tree-like structure with probability distribution and learning the hierarchical relations in hyperbolic space. We have incorporated the hierarchical interpretation into the contrastive loss and efficiently identified the visual hierarchy in a data-efficient manner. Through an effective hierarchy decomposition and encoding procedures, the identified hierarchy has been successfully deployed to the global visual representation, enhancing the structured understanding of an entire scene. Hi-Mapper has consistently improved the performance of the existing DNNs when integrated with them, and also has demonstrated the effectiveness on various dense predictions. Acknowledgement. This research was supported by the Yonsei Signature Research Cluster Program of 2022 (2022- 22-0002). References [1] Aleksandr Ermolov, Leyla Mirvakhabova, Valentin Khrulkov, Nicu Sebe, and Ivan Oseledets. Hyperbolic vision transformers: Combining improvements in metric learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7409–7419, 2022. 1, 3 [2] Sungyeon Kim, Boseung Jeong, and Suha Kwak. Hier: Metric learning beyond class labels via hierarchical regularization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 19903–19912, 2023. 1, 3 [3] Georgia Gkioxari, Ross Girshick, Piotr Dollar, and Kaiming ´ He. Detecting and recognizing human-object interactions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8359–8367, 2018. 1 [4] Jinhyun Jang, Jungin Park, Jin Kim, Hyeongjun Kwon, and Kwanghoon Sohn. Knowing where to focus: Eventaware transformer for video grounding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13846–13856, 2023. 1 [5] Zhi Hou, Baosheng Yu, Yu Qiao, Xiaojiang Peng, and Dacheng Tao. Affordance transfer learning for human-object interaction detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 495–504, 2021. 1 [6] Hyeongjun Kwon, Taeyong Song, Somi Jeong, Jin Kim, Jinhyun Jang, and Kwanghoon Sohn. Probabilistic prompt learning for dense prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6768–6777, 2023. 1, 3 [7] Jin Kim, Jiyoung Lee, Jungin Park, Dongbo Min, and Kwanghoon Sohn. Pin the memory: Learning to generalize semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4350–4360, 2022. 1 [8] Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020. 1 [9] Prajit Ramachandran, Niki Parmar, Ashish Vaswani, Irwan Bello, Anselm Levskaya, and Jon Shlens. Stand-alone selfattention in vision models. Advances in neural information processing systems, 32, 2019. 1 [10] Hengshuang Zhao, Jiaya Jia, and Vladlen Koltun. Exploring self-attention for image recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10076–10085, 2020. 7 [11] Jianyuan Guo, Kai Han, Han Wu, Yehui Tang, Xinghao Chen, Yunhe Wang, and Chang Xu. Cmt: Convolutional neural networks meet vision transformers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12175–12185, 2022. [12] Haiping Wu, Bin Xiao, Noel Codella, Mengchen Liu, Xiyang Dai, Lu Yuan, and Lei Zhang. Cvt: Introducing convolutions to vision transformers. In Proceedings of the IEEE/CVF international conference on computer vision, pages 22–31, 2021. 1, 6 [13] Xiaoyi Dong, Jianmin Bao, Dongdong Chen, Weiming Zhang, Nenghai Yu, Lu Yuan, Dong Chen, and Baining Guo. Cswin transformer: A general vision transformer backbone with cross-shaped windows. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12124–12134, 2022. 1 [14] Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, and Ling Shao. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In Proceedings of the IEEE/CVF international conference on computer vision, pages 568–578, 2021. [15] Yanghao Li, Chao-Yuan Wu, Haoqi Fan, Karttikeya Mangalam, Bo Xiong, Jitendra Malik, and Christoph Feichtenhofer. Mvitv2: Improved multiscale vision transformers for classification and detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4804–4814, 2022. 1 [16] Chun-Fu Richard Chen, Quanfu Fan, and Rameswar Panda. Crossvit: Cross-attention multi-scale vision transformer for image classification. In Proceedings of the IEEE/CVF international conference on computer vision, pages 357–366, 2021. 1, 2, 6 [17] Pengzhen Ren, Changlin Li, Guangrun Wang, Yun Xiao, Qing Du, Xiaodan Liang, and Xiaojun Chang. Beyond fixation: Dynamic window visual transformer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11987–11997, 2022. 1 [18] Shitao Tang, Jiahui Zhang, Siyu Zhu, and Ping Tan. Quadtree attention for vision transformers. arXiv preprint arXiv:2201.02767, 2022. 2, 4 [19] Mingyu Ding, Yikang Shen, Lijie Fan, Zhenfang Chen, Zitian Chen, Ping Luo, Joshua B Tenenbaum, and Chuang Gan. Visual dependency transformers: Dependency tree emerges from reversed attention. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14528–14539, 2023. 2, 6, 7 [20] Tsung-Wei Ke, Sangwoo Mo, and X Yu Stella. Learning hierarchical image segmentation for recognition and by recognition. In The Twelfth International Conference on Learning Representations, 2023. 2, 4 [21] N. Linial, E. London, and Y. Rabinovich. The geometry of graphs and some of its algorithmic applications. In Proceedings 35th Annual Symposium on Foundations of Computer Science, pages 577–591, 1994. doi: 10.1109/ SFCS.1994.365733. 2 [22] Hongbin Pei, Bingzhe Wei, Kevin Chang, Chunxu Zhang, and Bo Yang. Curvature regularization to prevent distortion in graph embedding. Advances in Neural Information Processing Systems, 33:20779–20790, 2020. [23] Maximillian Nickel and Douwe Kiela. Poincare embeddings ´ for learning hierarchical representations. Advances in neural information processing systems, 30, 2017. [24] Maximillian Nickel and Douwe Kiela. Learning continuous hierarchies in the lorentz model of hyperbolic geometry. In International conference on machine learning, pages 3779– 3788. PMLR, 2018. 3 [25] Zhi Gao, Yuwei Wu, Yunde Jia, and Mehrtash Harandi. Curvature generation in curved spaces for few-shot learning. In Proceedings of the IEEE/CVF international conference on computer vision, pages 8691–8700, 2021. 3 [26] Alexandru Tifrea, Gary Becigneul, and Octavian-Eugen ´ Ganea. Poincar\’e glove: Hyperbolic word embeddings. arXiv preprint arXiv:1810.06546, 2018. 3 [27] Yudong Zhu, Di Zhou, Jinghui Xiao, Xin Jiang, Xiao Chen, and Qun Liu. Hypertext: Endowing fasttext with hyperbolic geometry. arXiv preprint arXiv:2010.16143, 2020. 3 [28] Ines Chami, Zhitao Ying, Christopher Re, and Jure Leskovec. ´ Hyperbolic graph convolutional neural networks. Advances in neural information processing systems, 32, 2019. [29] Karan Desai, Maximilian Nickel, Tanmay Rajpurohit, Justin Johnson, and Shanmukha Ramakrishna Vedantam. Hyperbolic image-text representations. In International Conference on Machine Learning, pages 7694–7731. PMLR, 2023. 2, 3, 5 [30] Luke Vilnis and Andrew McCallum. Word representations via gaussian embedding. In International Conference on Learning Representations, 2015. 2 [31] Ben Athiwaratkun and Andrew Gordon Wilson. Multimodal word distributions. arXiv preprint arXiv:1704.08424, 2017. 3 [32] Ben Athiwaratkun and Andrew Gordon Wilson. Hierarchical density order embeddings. In International Conference on Learning Representations, 2018. [33] Gengcong Yang, Jingyi Zhang, Yong Zhang, Baoyuan Wu, and Yujiu Yang. Probabilistic modeling of semantic ambiguity for scene graph generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12527–12536, 2021. 2 [34] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. 2, 6, 12 [35] Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herve Jegou. Training ´ data-efficient image transformers & distillation through attention. In International conference on machine learning, pages 10347–10357. PMLR, 2021. 2, 6, 7, 12 [36] Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009. 2, 6, 7, 8, 12, 14 [37] Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollar, and C Lawrence ´ Zitnick. Microsoft coco: Common objects in context. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pages 740–755. Springer, 2014. 6, 7 [38] Bolei Zhou, Hang Zhao, Xavier Puig, Sanja Fidler, Adela Barriuso, and Antonio Torralba. Scene parsing through ade20k dataset. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 633–641, 2017. 2, 7 [39] Pedro F Felzenszwalb, Ross B Girshick, David McAllester, and Deva Ramanan. Object detection with discriminatively trained part-based models. IEEE transactions on pattern analysis and machine intelligence, 32(9):1627–1645, 2009. 2 [40] Feng Han and Song-Chun Zhu. Bottom-up/top-down image parsing with attribute grammar. IEEE transactions on pattern analysis and machine intelligence, 31(1):59–73, 2008. [41] Erik B Sudderth, Antonio Torralba, William T Freeman, and Alan S Willsky. Learning hierarchical models of scenes, objects, and parts. In Tenth IEEE International Conference on Computer Vision (ICCV’05) Volume 1, volume 2, pages 1331–1338. IEEE, 2005. [42] Zhuowen Tu, Xiangrong Chen, Alan L Yuille, and Song-Chun Zhu. Image parsing: Unifying segmentation, detection, and recognition. International Journal of computer vision, 63: 113–140, 2005. 2 [43] Tianfu Wu and Song-Chun Zhu. A numerical study of the bottom-up and top-down inference processes in and-or graphs. International journal of computer vision, 93:226–252, 2011. 2 [44] Wenguan Wang, Zhijie Zhang, Siyuan Qi, Jianbing Shen, Yanwei Pang, and Ling Shao. Learning compositional neural information fusion for human parsing. In Proceedings of the IEEE/CVF international conference on computer vision, pages 5703–5713, 2019. 2 [45] Wenguan Wang, Hailong Zhu, Jifeng Dai, Yanwei Pang, Jianbing Shen, and Ling Shao. Hierarchical human parsing with typed part-relation reasoning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8929–8939, 2020. 2 [46] Sandro Braun, Patrick Esser, and Bjorn Ommer. Unsupervised part discovery by unsupervised disentanglement. In Pattern Recognition: 42nd DAGM German Conference, DAGM GCPR 2020, Tubingen, Germany, September 28–October 1, 2020, Proceedings 42, pages 345–359. Springer, 2021. 2 [47] Subhabrata Choudhury, Iro Laina, Christian Rupprecht, and Andrea Vedaldi. Unsupervised part discovery from contrastive reconstruction. Advances in Neural Information Processing Systems, 34:28104–28118, 2021. [48] Wei-Chih Hung, Varun Jampani, Sifei Liu, Pavlo Molchanov, Ming-Hsuan Yang, and Jan Kautz. Scops: Self-supervised co-part segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 869–878, 2019. 2 [49] Tsung-Wei Ke, Sangwoo Mo, and Stella X. Yu. Learning hierarchical image segmentation for recognition and by recognition. In The Twelfth International Conference on Learning Representations, 2024. 2 [50] Sanghyuk Chun, Seong Joon Oh, Rafael Sampaio De Rezende, Yannis Kalantidis, and Diane Larlus. Probabilistic embeddings for cross-modal retrieval. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8415–8424, 2021. 3, 5 [51] Yichun Shi and Anil K Jain. Probabilistic face embeddings. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 6902–6911, 2019. 3 [52] Jungin Park, Jiyoung Lee, Ig-Jae Kim, and Kwanghoon Sohn. Probabilistic representations for video contrastive learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14711–14721, 2022. 3 [53] Maximillian Nickel and Douwe Kiela. Poincare embeddings ´ for learning hierarchical representations. Advances in neural information processing systems, 30, 2017. 3 [54] Mina Ghadimi Atigh, Julian Schoep, Erman Acar, Nanne Van Noord, and Pascal Mettes. Hyperbolic image segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4453–4462, 2022. 3 [55] Zhenzhen Weng, Mehmet Giray Ogut, Shai Limonchik, and Serena Yeung. Unsupervised discovery of the long-tail in instance segmentation using hierarchical self-supervision. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2603–2612, 2021. 3 [56] Valentin Khrulkov, Leyla Mirvakhabova, Evgeniya Ustinova, Ivan Oseledets, and Victor Lempitsky. Hyperbolic image embeddings. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6418–6428, 2020. 3 [57] Durk P Kingma, Tim Salimans, and Max Welling. Variational dropout and the local reparameterization trick. Advances in neural information processing systems, 28, 2015. 4 [58] Aaron van den Oord, Yazhe Li, and Oriol Vinyals. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748, 2018. 5 [59] Mingxing Tan and Quoc Le. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR, 2019. 6, 12 [60] Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision, pages 10012–10022, 2021. 6, 7, 12 [61] Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, and Ling Shao. Pvt v2: Improved baselines with pyramid vision transformer. Computational Visual Media, 8(3):415–424, 2022. 6, 7 [62] Mingyu Ding, Bin Xiao, Noel Codella, Ping Luo, Jingdong Wang, and Lu Yuan. Davit: Dual attention vision transformers. In European Conference on Computer Vision, pages 74–92. Springer, 2022. 6 [63] Pengchuan Zhang, Xiyang Dai, Jianwei Yang, Bin Xiao, Lu Yuan, Lei Zhang, and Jianfeng Gao. Multi-scale vision longformer: A new vision transformer for highresolution image encoding. In Proceedings of the IEEE/CVF international conference on computer vision, pages 2998– 3008, 2021. [64] Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollar. Focal loss for dense object detection. ´ In Proceedings of the IEEE international conference on computer vision, pages 2980–2988, 2017. 6 [65] Elad Hoffer, Tal Ben-Nun, Itay Hubara, Niv Giladi, Torsten Hoefler, and Daniel Soudry. Augment your batch: Improving generalization through instance repetition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8129–8138, 2020. 6 [66] Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101, 2017. 6 [67] Kaiming He, Georgia Gkioxari, Piotr Dollar, and Ross Girshick. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961– 2969, 2017. 7, 12 [68] Yanghao Li, Hanzi Mao, Ross Girshick, and Kaiming He. Exploring plain vision transformer backbones for object detection. In European Conference on Computer Vision, pages 280–296. Springer, 2022. 7 [69] Alexander Kirillov, Ross Girshick, Kaiming He, and Piotr Dollar. Panoptic feature pyramid networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6399–6408, 2019. 7 [70] Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, and Jian Sun. Unified perceptual parsing for scene understanding. In Proceedings of the European conference on computer vision (ECCV), pages 418–434, 2018. 7, 12 This paper is available on arxiv under CC BY 4.0 DEED license. Authors: (1) Hyeongjun Kwon, Yonsei University; (2) Jinhyun Jang, Yonsei University; (3) Jin Kim, Yonsei University; (4) Kwonyoung Kim, Yonsei University; (5) Kwanghoon Sohn, Yonsei University and Korea Institute of Science and Technology (KIST). Authors: Authors: (1) Hyeongjun Kwon, Yonsei University; (2) Jinhyun Jang, Yonsei University; (3) Jin Kim, Yonsei University; (4) Kwonyoung Kim, Yonsei University; (5) Kwanghoon Sohn, Yonsei University and Korea Institute of Science and Technology (KIST). Table of Links Abstract and 1 Introduction Abstract and 1 Introduction 2. Related Work 2. Related Work 3. Hyperbolic Geometry 3. Hyperbolic Geometry 4. Method 4.1. Overview 4.1. Overview 4.2. Probabilistic hierarchy tree 4.2. Probabilistic hierarchy tree 4.3. Visual hierarchy decomposition 4.3. Visual hierarchy decomposition 4.4. Learning hierarchy in hyperbolic space 4.4. Learning hierarchy in hyperbolic space 4.5. Visual hierarchy encoding 4.5. Visual hierarchy encoding 5. Experiments and 5.1. Image classification 5. Experiments and 5.1. Image classification 5.2. Object detection and Instance segmentation 5.2. Object detection and Instance segmentation 5.3. Semantic segmentation 5.3. Semantic segmentation 5.4. Visualization 5.4. Visualization 6. Ablation studies and discussion 6. Ablation studies and discussion 7. Conclusion and References 7. Conclusion and References A. Network Architecture A. Network Architecture B. Theoretical Baseline B. Theoretical Baseline C. Additional Results C. Additional Results D. Additional visualization D. Additional visualization 7. Conclusion In this paper, we have presented a novel Visual Hierarchy Mapper (Hi-Mapper) that investigates the hierarchical organization of visual scenes. We have achieved the goal by newly defining tree-like structure with probability distribution and learning the hierarchical relations in hyperbolic space. We have incorporated the hierarchical interpretation into the contrastive loss and efficiently identified the visual hierarchy in a data-efficient manner. Through an effective hierarchy decomposition and encoding procedures, the identified hierarchy has been successfully deployed to the global visual representation, enhancing the structured understanding of an entire scene. Hi-Mapper has consistently improved the performance of the existing DNNs when integrated with them, and also has demonstrated the effectiveness on various dense predictions. Acknowledgement . This research was supported by the Yonsei Signature Research Cluster Program of 2022 (2022- 22-0002). Acknowledgement References [1] Aleksandr Ermolov, Leyla Mirvakhabova, Valentin Khrulkov, Nicu Sebe, and Ivan Oseledets. Hyperbolic vision transformers: Combining improvements in metric learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7409–7419, 2022. 1, 3 [2] Sungyeon Kim, Boseung Jeong, and Suha Kwak. Hier: Metric learning beyond class labels via hierarchical regularization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 19903–19912, 2023. 1, 3 [3] Georgia Gkioxari, Ross Girshick, Piotr Dollar, and Kaiming ´ He. Detecting and recognizing human-object interactions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8359–8367, 2018. 1 [4] Jinhyun Jang, Jungin Park, Jin Kim, Hyeongjun Kwon, and Kwanghoon Sohn. Knowing where to focus: Eventaware transformer for video grounding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13846–13856, 2023. 1 [5] Zhi Hou, Baosheng Yu, Yu Qiao, Xiaojiang Peng, and Dacheng Tao. Affordance transfer learning for human-object interaction detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 495–504, 2021. 1 [6] Hyeongjun Kwon, Taeyong Song, Somi Jeong, Jin Kim, Jinhyun Jang, and Kwanghoon Sohn. Probabilistic prompt learning for dense prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6768–6777, 2023. 1, 3 [7] Jin Kim, Jiyoung Lee, Jungin Park, Dongbo Min, and Kwanghoon Sohn. Pin the memory: Learning to generalize semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4350–4360, 2022. 1 [8] Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020. 1 [9] Prajit Ramachandran, Niki Parmar, Ashish Vaswani, Irwan Bello, Anselm Levskaya, and Jon Shlens. Stand-alone selfattention in vision models. Advances in neural information processing systems, 32, 2019. 1 [10] Hengshuang Zhao, Jiaya Jia, and Vladlen Koltun. Exploring self-attention for image recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10076–10085, 2020. 7 [11] Jianyuan Guo, Kai Han, Han Wu, Yehui Tang, Xinghao Chen, Yunhe Wang, and Chang Xu. Cmt: Convolutional neural networks meet vision transformers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12175–12185, 2022. [12] Haiping Wu, Bin Xiao, Noel Codella, Mengchen Liu, Xiyang Dai, Lu Yuan, and Lei Zhang. Cvt: Introducing convolutions to vision transformers. In Proceedings of the IEEE/CVF international conference on computer vision, pages 22–31, 2021. 1, 6 [13] Xiaoyi Dong, Jianmin Bao, Dongdong Chen, Weiming Zhang, Nenghai Yu, Lu Yuan, Dong Chen, and Baining Guo. Cswin transformer: A general vision transformer backbone with cross-shaped windows. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12124–12134, 2022. 1 [14] Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, and Ling Shao. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In Proceedings of the IEEE/CVF international conference on computer vision, pages 568–578, 2021. [15] Yanghao Li, Chao-Yuan Wu, Haoqi Fan, Karttikeya Mangalam, Bo Xiong, Jitendra Malik, and Christoph Feichtenhofer. Mvitv2: Improved multiscale vision transformers for classification and detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4804–4814, 2022. 1 [16] Chun-Fu Richard Chen, Quanfu Fan, and Rameswar Panda. Crossvit: Cross-attention multi-scale vision transformer for image classification. In Proceedings of the IEEE/CVF international conference on computer vision, pages 357–366, 2021. 1, 2, 6 [17] Pengzhen Ren, Changlin Li, Guangrun Wang, Yun Xiao, Qing Du, Xiaodan Liang, and Xiaojun Chang. Beyond fixation: Dynamic window visual transformer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11987–11997, 2022. 1 [18] Shitao Tang, Jiahui Zhang, Siyu Zhu, and Ping Tan. Quadtree attention for vision transformers. arXiv preprint arXiv:2201.02767, 2022. 2, 4 [19] Mingyu Ding, Yikang Shen, Lijie Fan, Zhenfang Chen, Zitian Chen, Ping Luo, Joshua B Tenenbaum, and Chuang Gan. Visual dependency transformers: Dependency tree emerges from reversed attention. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14528–14539, 2023. 2, 6, 7 [20] Tsung-Wei Ke, Sangwoo Mo, and X Yu Stella. Learning hierarchical image segmentation for recognition and by recognition. In The Twelfth International Conference on Learning Representations, 2023. 2, 4 [21] N. Linial, E. London, and Y. Rabinovich. The geometry of graphs and some of its algorithmic applications. In Proceedings 35th Annual Symposium on Foundations of Computer Science, pages 577–591, 1994. doi: 10.1109/ SFCS.1994.365733. 2 [22] Hongbin Pei, Bingzhe Wei, Kevin Chang, Chunxu Zhang, and Bo Yang. Curvature regularization to prevent distortion in graph embedding. Advances in Neural Information Processing Systems, 33:20779–20790, 2020. [23] Maximillian Nickel and Douwe Kiela. Poincare embeddings ´ for learning hierarchical representations. Advances in neural information processing systems, 30, 2017. [24] Maximillian Nickel and Douwe Kiela. Learning continuous hierarchies in the lorentz model of hyperbolic geometry. In International conference on machine learning, pages 3779– 3788. PMLR, 2018. 3 [25] Zhi Gao, Yuwei Wu, Yunde Jia, and Mehrtash Harandi. Curvature generation in curved spaces for few-shot learning. In Proceedings of the IEEE/CVF international conference on computer vision, pages 8691–8700, 2021. 3 [26] Alexandru Tifrea, Gary Becigneul, and Octavian-Eugen ´ Ganea. Poincar\’e glove: Hyperbolic word embeddings. arXiv preprint arXiv:1810.06546, 2018. 3 [27] Yudong Zhu, Di Zhou, Jinghui Xiao, Xin Jiang, Xiao Chen, and Qun Liu. Hypertext: Endowing fasttext with hyperbolic geometry. arXiv preprint arXiv:2010.16143, 2020. 3 [28] Ines Chami, Zhitao Ying, Christopher Re, and Jure Leskovec. ´ Hyperbolic graph convolutional neural networks. Advances in neural information processing systems, 32, 2019. [29] Karan Desai, Maximilian Nickel, Tanmay Rajpurohit, Justin Johnson, and Shanmukha Ramakrishna Vedantam. Hyperbolic image-text representations. In International Conference on Machine Learning, pages 7694–7731. PMLR, 2023. 2, 3, 5 [30] Luke Vilnis and Andrew McCallum. Word representations via gaussian embedding. In International Conference on Learning Representations, 2015. 2 [31] Ben Athiwaratkun and Andrew Gordon Wilson. Multimodal word distributions. arXiv preprint arXiv:1704.08424, 2017. 3 [32] Ben Athiwaratkun and Andrew Gordon Wilson. Hierarchical density order embeddings. In International Conference on Learning Representations, 2018. [33] Gengcong Yang, Jingyi Zhang, Yong Zhang, Baoyuan Wu, and Yujiu Yang. Probabilistic modeling of semantic ambiguity for scene graph generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12527–12536, 2021. 2 [34] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. 2, 6, 12 [35] Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herve Jegou. Training ´ data-efficient image transformers & distillation through attention. In International conference on machine learning, pages 10347–10357. PMLR, 2021. 2, 6, 7, 12 [36] Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009. 2, 6, 7, 8, 12, 14 [37] Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollar, and C Lawrence ´ Zitnick. Microsoft coco: Common objects in context. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pages 740–755. Springer, 2014. 6, 7 [38] Bolei Zhou, Hang Zhao, Xavier Puig, Sanja Fidler, Adela Barriuso, and Antonio Torralba. Scene parsing through ade20k dataset. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 633–641, 2017. 2, 7 [39] Pedro F Felzenszwalb, Ross B Girshick, David McAllester, and Deva Ramanan. Object detection with discriminatively trained part-based models. IEEE transactions on pattern analysis and machine intelligence, 32(9):1627–1645, 2009. 2 [40] Feng Han and Song-Chun Zhu. Bottom-up/top-down image parsing with attribute grammar. IEEE transactions on pattern analysis and machine intelligence, 31(1):59–73, 2008. [41] Erik B Sudderth, Antonio Torralba, William T Freeman, and Alan S Willsky. Learning hierarchical models of scenes, objects, and parts. In Tenth IEEE International Conference on Computer Vision (ICCV’05) Volume 1, volume 2, pages 1331–1338. IEEE, 2005. [42] Zhuowen Tu, Xiangrong Chen, Alan L Yuille, and Song-Chun Zhu. Image parsing: Unifying segmentation, detection, and recognition. International Journal of computer vision, 63: 113–140, 2005. 2 [43] Tianfu Wu and Song-Chun Zhu. A numerical study of the bottom-up and top-down inference processes in and-or graphs. International journal of computer vision, 93:226–252, 2011. 2 [44] Wenguan Wang, Zhijie Zhang, Siyuan Qi, Jianbing Shen, Yanwei Pang, and Ling Shao. Learning compositional neural information fusion for human parsing. In Proceedings of the IEEE/CVF international conference on computer vision, pages 5703–5713, 2019. 2 [45] Wenguan Wang, Hailong Zhu, Jifeng Dai, Yanwei Pang, Jianbing Shen, and Ling Shao. Hierarchical human parsing with typed part-relation reasoning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8929–8939, 2020. 2 [46] Sandro Braun, Patrick Esser, and Bjorn Ommer. Unsupervised part discovery by unsupervised disentanglement. In Pattern Recognition: 42nd DAGM German Conference, DAGM GCPR 2020, Tubingen, Germany, September 28–October 1, 2020, Proceedings 42, pages 345–359. Springer, 2021. 2 [47] Subhabrata Choudhury, Iro Laina, Christian Rupprecht, and Andrea Vedaldi. Unsupervised part discovery from contrastive reconstruction. Advances in Neural Information Processing Systems, 34:28104–28118, 2021. [48] Wei-Chih Hung, Varun Jampani, Sifei Liu, Pavlo Molchanov, Ming-Hsuan Yang, and Jan Kautz. Scops: Self-supervised co-part segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 869–878, 2019. 2 [49] Tsung-Wei Ke, Sangwoo Mo, and Stella X. Yu. Learning hierarchical image segmentation for recognition and by recognition. In The Twelfth International Conference on Learning Representations, 2024. 2 [50] Sanghyuk Chun, Seong Joon Oh, Rafael Sampaio De Rezende, Yannis Kalantidis, and Diane Larlus. Probabilistic embeddings for cross-modal retrieval. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8415–8424, 2021. 3, 5 [51] Yichun Shi and Anil K Jain. Probabilistic face embeddings. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 6902–6911, 2019. 3 [52] Jungin Park, Jiyoung Lee, Ig-Jae Kim, and Kwanghoon Sohn. Probabilistic representations for video contrastive learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14711–14721, 2022. 3 [53] Maximillian Nickel and Douwe Kiela. Poincare embeddings ´ for learning hierarchical representations. Advances in neural information processing systems, 30, 2017. 3 [54] Mina Ghadimi Atigh, Julian Schoep, Erman Acar, Nanne Van Noord, and Pascal Mettes. Hyperbolic image segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4453–4462, 2022. 3 [55] Zhenzhen Weng, Mehmet Giray Ogut, Shai Limonchik, and Serena Yeung. Unsupervised discovery of the long-tail in instance segmentation using hierarchical self-supervision. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2603–2612, 2021. 3 [56] Valentin Khrulkov, Leyla Mirvakhabova, Evgeniya Ustinova, Ivan Oseledets, and Victor Lempitsky. Hyperbolic image embeddings. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6418–6428, 2020. 3 [57] Durk P Kingma, Tim Salimans, and Max Welling. Variational dropout and the local reparameterization trick. Advances in neural information processing systems, 28, 2015. 4 [58] Aaron van den Oord, Yazhe Li, and Oriol Vinyals. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748, 2018. 5 [59] Mingxing Tan and Quoc Le. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR, 2019. 6, 12 [60] Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision, pages 10012–10022, 2021. 6, 7, 12 [61] Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, and Ling Shao. Pvt v2: Improved baselines with pyramid vision transformer. Computational Visual Media, 8(3):415–424, 2022. 6, 7 [62] Mingyu Ding, Bin Xiao, Noel Codella, Ping Luo, Jingdong Wang, and Lu Yuan. Davit: Dual attention vision transformers. In European Conference on Computer Vision, pages 74–92. Springer, 2022. 6 [63] Pengchuan Zhang, Xiyang Dai, Jianwei Yang, Bin Xiao, Lu Yuan, Lei Zhang, and Jianfeng Gao. Multi-scale vision longformer: A new vision transformer for highresolution image encoding. In Proceedings of the IEEE/CVF international conference on computer vision, pages 2998– 3008, 2021. [64] Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollar. Focal loss for dense object detection. ´ In Proceedings of the IEEE international conference on computer vision, pages 2980–2988, 2017. 6 [65] Elad Hoffer, Tal Ben-Nun, Itay Hubara, Niv Giladi, Torsten Hoefler, and Daniel Soudry. Augment your batch: Improving generalization through instance repetition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8129–8138, 2020. 6 [66] Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101, 2017. 6 [67] Kaiming He, Georgia Gkioxari, Piotr Dollar, and Ross Girshick. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961– 2969, 2017. 7, 12 [68] Yanghao Li, Hanzi Mao, Ross Girshick, and Kaiming He. Exploring plain vision transformer backbones for object detection. In European Conference on Computer Vision, pages 280–296. Springer, 2022. 7 [69] Alexander Kirillov, Ross Girshick, Kaiming He, and Piotr Dollar. Panoptic feature pyramid networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6399–6408, 2019. 7 [70] Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, and Jian Sun. Unified perceptual parsing for scene understanding. In Proceedings of the European conference on computer vision (ECCV), pages 418–434, 2018. 7, 12 This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv