HyperTransformer: Conclusion and References

This paper is available on arxiv under CC 4.0 license. Authors: (1) Andrey Zhmoginov, Google Research & {azhmogin,sandler,mxv}@google.com; (2) Mark Sandler, Google Research & {azhmogin,sandler,mxv}@google.com; (3) Max Vladymyrov, Google Research & {azhmogin,sandler,mxv}@google.com. Table of Links Abstract and Introduction Problem Setup and Related Work HyperTransformer Experiments Conclusion and References A Example of a Self-Attention Mechanism For Supervised Learning B Model Parameters C Additional Supervised Experiments D Dependence On Parameters and Ablation Studies E Attention Maps of Learned Transformer Models F Visualization of The Generated CNN Weights G Additional Tables and Figures 5 CONCLUSIONS In this work, we proposed a HyperTransformer (HT), a novel transformer-based model that generates all weights of a CNN model directly from a few-shot support set. This approach allows us to use a high-capacity model for encoding task-dependent variations in the weights of a smaller model. We demonstrate that generating the last logits layer alone, the transformer-based weight generator beats or matches performance of multiple traditional learning methods on several few shot benchmarks. More importantly, we showed that HT can be straightforwardly extended to handle unlabeled samples that might be present in the support set and our experiments demonstrate a considerable fewshot performance improvement in the presence of unlabeled data. Finally, we explore the impact of the transformer-encoded model diversity in CNN models of different sizes. We use HT to generate some or all convolutional kernels and biases and show that for sufficiently small models, adjusting all model parameters further improves their few-shot learning performance. REFERENCES Kelsey R. Allen, Evan Shelhamer, Hanul Shin, and Joshua B. Tenenbaum. Infinite mixture prototypes for few-shot learning. In Kamalika Chaudhuri and Ruslan Salakhutdinov (eds.), Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pp. 232–241. PMLR, 2019. Antreas Antoniou, Harrison Edwards, and Amos J. Storkey. How to train your MAML. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net, 2019. Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. End-to-end object detection with transformers. In Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (eds.), Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part I, volume 12346 of Lecture Notes in Computer Science, pp. 213–229. Springer, 2020. Hanting Chen, Yunhe Wang, Tianyu Guo, Chang Xu, Yiping Deng, Zhenhua Liu, Siwei Ma, Chunjing Xu, Chao Xu, and Wen Gao. Pre-trained image processing transformer. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19-25, 2021, pp. 12299–12310. Computer Vision Foundation / IEEE, 2021. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. An image is worth 16x16 words: Transformers for image recognition at scale. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021, 2021. Nanyi Fei, Zhiwu Lu, Tao Xiang, and Songfang Huang. MELR: meta-learning via modeling episode-level relationships for few-shot learning. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021. Chelsea Finn, Pieter Abbeel, and Sergey Levine. Model-agnostic meta-learning for fast adaptation of deep networks. In Doina Precup and Yee Whye Teh (eds.), Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pp. 1126–1135. PMLR, 06–11 Aug 2017. Spyros Gidaris and Nikos Komodakis. Dynamic few-shot visual learning without forgetting. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp. 4367–4375. IEEE Computer Society, 2018. doi: 10.1109/CVPR. 2018.00459. David Ha, Andrew M. Dai, and Quoc V. Le. HyperNetworks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings, 2017. Fusheng Hao, Fengxiang He, Jun Cheng, Lei Wang, Jianzhong Cao, and Dacheng Tao. Collect and select: Semantic alignment metric learning for few-shot learning. In 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp. 8459–8468. IEEE, 2019. doi: 10.1109/ICCV.2019.00855. Muhammad Abdullah Jamal and Guo-Jun Qi. Task agnostic meta-learning for few-shot learning. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 11719–11727. Computer Vision Foundation / IEEE, 2019. doi: 10.1109/CVPR.2019.01199. Gregory Koch, Richard Zemel, Ruslan Salakhutdinov, et al. Siamese neural networks for one-shot image recognition. In ICML deep learning workshop, volume 2. Lille, 2015. Aoxue Li, Tiange Luo, Tao Xiang, Weiran Huang, and Liwei Wang. Few-shot learning with global class representations. In 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp. 9714–9723. IEEE, 2019a. doi: 10.1109/ICCV.2019.00981. Huai-Yu Li, Weiming Dong, Xing Mei, Chongyang Ma, Feiyue Huang, and Bao-Gang Hu. Lgmnet: Learning to generate matching networks for few-shot learning. In Kamalika Chaudhuri and Ruslan Salakhutdinov (eds.), Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pp. 3825–3834. PMLR, 2019b. Lu Liu, William L. Hamilton, Guodong Long, Jing Jiang, and Hugo Larochelle. A universal representation transformer layer for few-shot image classification. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021. Chongyang Ma. LGM-Net. https://github.com/likesiwell/LGM-Net, 2019 Rabeeh Karimi Mahabadi, Sebastian Ruder, Mostafa Dehghani, and James Henderson. Parameterefficient multi-task fine-tuning for transformers via shared hypernetworks. In Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli (eds.), Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, pp. 565–576. Association for Computational Linguistics, 2021. doi: 10.18653/v1/2021. acl-long.47. Alex Nichol, Joshua Achiam, and John Schulman. On first-order meta-learning algorithms. CoRR, abs/1803.02999, 2018. Boris N. Oreshkin, Pau Rodr´ıguez Lopez, and Alexandre Lacoste. TADAM: task dependent adaptiv´ metric for improved few-shot learning. In Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicolo Cesa-Bianchi, and Roman Garnett (eds.), ` Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montreal, Canada ´ , pp. 719–729, 2018. Zhimao Peng, Zechao Li, Junge Zhang, Yan Li, Guo-Jun Qi, and Jinhui Tang. Few-shot image recognition with knowledge transfer. In 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp. 441–449. IEEE, 2019. doi: 10.1109/ICCV.2019.00053. Siyuan Qiao, Chenxi Liu, Wei Shen, and Alan L. Yuille. Few-shot image recognition by predicting parameters from activations. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp. 7229–7238. Computer Vision Foundation / IEEE Computer Society, 2018. doi: 10.1109/CVPR.2018.00755. Neale Ratzlaff and Fuxin Li. Hypergan: A generative model for diverse, performant neural networks. In Kamalika Chaudhuri and Ruslan Salakhutdinov (eds.), Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pp. 5361–5369. PMLR, 2019. Neale Ratzlaff and Fuxin Li. Hypergan: A generative model for diverse, performant neural networks. In Kamalika Chaudhuri and Ruslan Salakhutdinov (eds.), Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pp. 5361–5369. PMLR, 2019. Sachin Ravi and Hugo Larochelle. Optimization as a model for few-shot learning. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net, 2017. Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, and Raia Hadsell. Meta-learning with latent embedding optimization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019, 2019. Jake Snell, Kevin Swersky, and Richard S. Zemel. Prototypical networks for few-shot learning. In Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (eds.), Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pp. 4077–4087, 2017. Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip H. S. Torr, and Timothy M. Hospedales. Learning to compare: Relation network for few-shot learning. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp. 1199–1208. IEEE Computer Society, 2018. doi: 10.1109/CVPR.2018.00131. Yi Tay, Zhe Zhao, Dara Bahri, Donald Metzler, and Da-Cheng Juan. Hypergrid transformers:Towards A single model for multiple tasks. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021. Yonglong Tian, Yue Wang, Dilip Krishnan, Joshua B. Tenenbaum, and Phillip Isola. Rethinking fewshot image classification: A good embedding is all you need? In Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (eds.), Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XIV, volume 12359 of Lecture Notes in Computer Science, pp. 266–282. Springer, 2020. doi: 10.1007/978-3-030-58568-6\ 16. Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herve J ´ egou. Training data-efficient image transformers & distillation through attention. In Ma- ´ rina Meila and Tong Zhang (eds.), Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, volume 139 of Proceedings of Machine Learning Research, pp. 10347–10357. PMLR, 2021. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (eds.), Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pp. 5998–6008, 2017. Oriol Vinyals, Charles Blundell, Tim Lillicrap, Koray Kavukcuoglu, and Daan Wierstra. Matching networks for one shot learning. In Daniel D. Lee, Masashi Sugiyama, Ulrike von Luxburg, Isabelle Guyon, and Roman Garnett (eds.), Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain, pp. 3630–3638, 2016. Ziyang Wu, Yuwei Li, Lihua Guo, and Kui Jia. PARN: position-aware relation networks for few-shot learning. In 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp. 6658–6666. IEEE, 2019. doi: 10.1109/ICCV. 2019.00676. Fuzhi Yang, Huan Yang, Jianlong Fu, Hongtao Lu, and Baining Guo. Learning texture transformer network for image super-resolution. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020, pp. 5790–5799. Computer Vision Foundation / IEEE, 2020. doi: 10.1109/CVPR42600.2020.00583. Han-Jia Ye, Hexiang Hu, De-Chuan Zhan, and Fei Sha. Few-shot learning via embedding adaptation with set-to-set functions. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020, pp. 8805–8814. IEEE, 2020. doi: 10.1109/CVPR42600.2020.00883. Linwei Ye, Mrigank Rochan, Zhi Liu, and Yang Wang. Cross-modal self-attention network for referring image segmentation. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 10502–10511. Computer Vision Foundation / IEEE, 2019. doi: 10.1109/CVPR.2019.01075. Qinyuan Ye and Xiang Ren. Learning to generate task-specific adapters from task description. In Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli (eds.), Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 2: Short Papers), Virtual Event, August 1-6, 2021, pp. 646–653. Association for Computational Linguistics, 2021. doi: 10.18653/v1/2021.acl-short.82. Dominic Zhao, Johannes von Oswald, Seijin Kobayashi, Joao Sacramento, and Benjamin F Grewe. ˜ Meta-learning via hypernetworks. 2020. Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. Deformable DETR: deformable transformers for end-to-end object detection. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021. This paper is available on arxiv under CC 4.0 license. Authors: (1) Andrey Zhmoginov, Google Research & {azhmogin,sandler,mxv}@google.com; (2) Mark Sandler, Google Research & {azhmogin,sandler,mxv}@google.com; (3) Max Vladymyrov, Google Research & {azhmogin,sandler,mxv}@google.com. This paper is available on arxiv under CC 4.0 license. Authors: (1) Andrey Zhmoginov, Google Research & {azhmogin,sandler,mxv}@google.com; (2) Mark Sandler, Google Research & {azhmogin,sandler,mxv}@google.com; (3) Max Vladymyrov, Google Research & {azhmogin,sandler,mxv}@google.com. Table of Links Abstract and Introduction Problem Setup and Related Work HyperTransformer Experiments Conclusion and References A Example of a Self-Attention Mechanism For Supervised Learning B Model Parameters C Additional Supervised Experiments D Dependence On Parameters and Ablation Studies E Attention Maps of Learned Transformer Models F Visualization of The Generated CNN Weights G Additional Tables and Figures Abstract and Introduction Abstract and Introduction Problem Setup and Related Work Problem Setup and Related Work HyperTransformer HyperTransformer Experiments Experiments Conclusion and References Conclusion and References A Example of a Self-Attention Mechanism For Supervised Learning A Example of a Self-Attention Mechanism For Supervised Learning B Model Parameters B Model Parameters C Additional Supervised Experiments C Additional Supervised Experiments D Dependence On Parameters and Ablation Studies D Dependence On Parameters and Ablation Studies E Attention Maps of Learned Transformer Models E Attention Maps of Learned Transformer Models F Visualization of The Generated CNN Weights F Visualization of The Generated CNN Weights G Additional Tables and Figures G Additional Tables and Figures 5 CONCLUSIONS In this work, we proposed a HyperTransformer (HT), a novel transformer-based model that generates all weights of a CNN model directly from a few-shot support set. This approach allows us to use a high-capacity model for encoding task-dependent variations in the weights of a smaller model. We demonstrate that generating the last logits layer alone, the transformer-based weight generator beats or matches performance of multiple traditional learning methods on several few shot benchmarks. More importantly, we showed that HT can be straightforwardly extended to handle unlabeled samples that might be present in the support set and our experiments demonstrate a considerable fewshot performance improvement in the presence of unlabeled data. Finally, we explore the impact of the transformer-encoded model diversity in CNN models of different sizes. We use HT to generate some or all convolutional kernels and biases and show that for sufficiently small models, adjusting all model parameters further improves their few-shot learning performance. REFERENCES Kelsey R. Allen, Evan Shelhamer, Hanul Shin, and Joshua B. Tenenbaum. Infinite mixture prototypes for few-shot learning. In Kamalika Chaudhuri and Ruslan Salakhutdinov (eds.), Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pp. 232–241. PMLR, 2019. Antreas Antoniou, Harrison Edwards, and Amos J. Storkey. How to train your MAML. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net, 2019. Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. End-to-end object detection with transformers. In Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (eds.), Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part I, volume 12346 of Lecture Notes in Computer Science, pp. 213–229. Springer, 2020. Hanting Chen, Yunhe Wang, Tianyu Guo, Chang Xu, Yiping Deng, Zhenhua Liu, Siwei Ma, Chunjing Xu, Chao Xu, and Wen Gao. Pre-trained image processing transformer. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19-25, 2021, pp. 12299–12310. Computer Vision Foundation / IEEE, 2021. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. An image is worth 16x16 words: Transformers for image recognition at scale. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021, 2021. Nanyi Fei, Zhiwu Lu, Tao Xiang, and Songfang Huang. MELR: meta-learning via modeling episode-level relationships for few-shot learning. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021. Chelsea Finn, Pieter Abbeel, and Sergey Levine. Model-agnostic meta-learning for fast adaptation of deep networks. In Doina Precup and Yee Whye Teh (eds.), Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pp. 1126–1135. PMLR, 06–11 Aug 2017. Spyros Gidaris and Nikos Komodakis. Dynamic few-shot visual learning without forgetting. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp. 4367–4375. IEEE Computer Society, 2018. doi: 10.1109/CVPR. 2018.00459. David Ha, Andrew M. Dai, and Quoc V. Le. HyperNetworks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings, 2017. Fusheng Hao, Fengxiang He, Jun Cheng, Lei Wang, Jianzhong Cao, and Dacheng Tao. Collect and select: Semantic alignment metric learning for few-shot learning. In 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp. 8459–8468. IEEE, 2019. doi: 10.1109/ICCV.2019.00855. Muhammad Abdullah Jamal and Guo-Jun Qi. Task agnostic meta-learning for few-shot learning. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 11719–11727. Computer Vision Foundation / IEEE, 2019. doi: 10.1109/CVPR.2019.01199. Gregory Koch, Richard Zemel, Ruslan Salakhutdinov, et al. Siamese neural networks for one-shot image recognition. In ICML deep learning workshop, volume 2. Lille, 2015. Aoxue Li, Tiange Luo, Tao Xiang, Weiran Huang, and Liwei Wang. Few-shot learning with global class representations. In 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp. 9714–9723. IEEE, 2019a. doi: 10.1109/ICCV.2019.00981. Huai-Yu Li, Weiming Dong, Xing Mei, Chongyang Ma, Feiyue Huang, and Bao-Gang Hu. Lgmnet: Learning to generate matching networks for few-shot learning. In Kamalika Chaudhuri and Ruslan Salakhutdinov (eds.), Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pp. 3825–3834. PMLR, 2019b. Lu Liu, William L. Hamilton, Guodong Long, Jing Jiang, and Hugo Larochelle. A universal representation transformer layer for few-shot image classification. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021. Chongyang Ma. LGM-Net. https://github.com/likesiwell/LGM-Net, 2019 Rabeeh Karimi Mahabadi, Sebastian Ruder, Mostafa Dehghani, and James Henderson. Parameterefficient multi-task fine-tuning for transformers via shared hypernetworks. In Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli (eds.), Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, pp. 565–576. Association for Computational Linguistics, 2021. doi: 10.18653/v1/2021. acl-long.47. Alex Nichol, Joshua Achiam, and John Schulman. On first-order meta-learning algorithms. CoRR, abs/1803.02999, 2018. Boris N. Oreshkin, Pau Rodr´ıguez Lopez, and Alexandre Lacoste. TADAM: task dependent adaptiv´ metric for improved few-shot learning. In Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicolo Cesa-Bianchi, and Roman Garnett (eds.), ` Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montreal, Canada ´ , pp. 719–729, 2018. Zhimao Peng, Zechao Li, Junge Zhang, Yan Li, Guo-Jun Qi, and Jinhui Tang. Few-shot image recognition with knowledge transfer. In 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp. 441–449. IEEE, 2019. doi: 10.1109/ICCV.2019.00053. Siyuan Qiao, Chenxi Liu, Wei Shen, and Alan L. Yuille. Few-shot image recognition by predicting parameters from activations. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp. 7229–7238. Computer Vision Foundation / IEEE Computer Society, 2018. doi: 10.1109/CVPR.2018.00755. Neale Ratzlaff and Fuxin Li. Hypergan: A generative model for diverse, performant neural networks. In Kamalika Chaudhuri and Ruslan Salakhutdinov (eds.), Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pp. 5361–5369. PMLR, 2019. Neale Ratzlaff and Fuxin Li. Hypergan: A generative model for diverse, performant neural networks. In Kamalika Chaudhuri and Ruslan Salakhutdinov (eds.), Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, volume 97 of Proceedings of Machine Learning Research, pp. 5361–5369. PMLR, 2019. Sachin Ravi and Hugo Larochelle. Optimization as a model for few-shot learning. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net, 2017. Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, and Raia Hadsell. Meta-learning with latent embedding optimization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019, 2019. Jake Snell, Kevin Swersky, and Richard S. Zemel. Prototypical networks for few-shot learning. In Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (eds.), Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pp. 4077–4087, 2017. Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip H. S. Torr, and Timothy M. Hospedales. Learning to compare: Relation network for few-shot learning. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp. 1199–1208. IEEE Computer Society, 2018. doi: 10.1109/CVPR.2018.00131. Yi Tay, Zhe Zhao, Dara Bahri, Donald Metzler, and Da-Cheng Juan. Hypergrid transformers:Towards A single model for multiple tasks. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021. Yonglong Tian, Yue Wang, Dilip Krishnan, Joshua B. Tenenbaum, and Phillip Isola. Rethinking fewshot image classification: A good embedding is all you need? In Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (eds.), Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XIV, volume 12359 of Lecture Notes in Computer Science, pp. 266–282. Springer, 2020. doi: 10.1007/978-3-030-58568-6\ 16. Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herve J ´ egou. Training data-efficient image transformers & distillation through attention. In Ma- ´ rina Meila and Tong Zhang (eds.), Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, volume 139 of Proceedings of Machine Learning Research, pp. 10347–10357. PMLR, 2021. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (eds.), Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pp. 5998–6008, 2017. Oriol Vinyals, Charles Blundell, Tim Lillicrap, Koray Kavukcuoglu, and Daan Wierstra. Matching networks for one shot learning. In Daniel D. Lee, Masashi Sugiyama, Ulrike von Luxburg, Isabelle Guyon, and Roman Garnett (eds.), Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain, pp. 3630–3638, 2016. Ziyang Wu, Yuwei Li, Lihua Guo, and Kui Jia. PARN: position-aware relation networks for few-shot learning. In 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp. 6658–6666. IEEE, 2019. doi: 10.1109/ICCV. 2019.00676. Fuzhi Yang, Huan Yang, Jianlong Fu, Hongtao Lu, and Baining Guo. Learning texture transformer network for image super-resolution. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020, pp. 5790–5799. Computer Vision Foundation / IEEE, 2020. doi: 10.1109/CVPR42600.2020.00583. Han-Jia Ye, Hexiang Hu, De-Chuan Zhan, and Fei Sha. Few-shot learning via embedding adaptation with set-to-set functions. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020, pp. 8805–8814. IEEE, 2020. doi: 10.1109/CVPR42600.2020.00883. Linwei Ye, Mrigank Rochan, Zhi Liu, and Yang Wang. Cross-modal self-attention network for referring image segmentation. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 10502–10511. Computer Vision Foundation / IEEE, 2019. doi: 10.1109/CVPR.2019.01075. Qinyuan Ye and Xiang Ren. Learning to generate task-specific adapters from task description. In Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli (eds.), Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 2: Short Papers), Virtual Event, August 1-6, 2021, pp. 646–653. Association for Computational Linguistics, 2021. doi: 10.18653/v1/2021.acl-short.82. Dominic Zhao, Johannes von Oswald, Seijin Kobayashi, Joao Sacramento, and Benjamin F Grewe. ˜ Meta-learning via hypernetworks. 2020. Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. Deformable DETR: deformable transformers for end-to-end object detection. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021.