Table of Links Abstract and 1 Introduction Abstract and 1 Introduction Related work
2.1. Generative Data Augmentation
2.2. Active Learning and Data Analysis


Preliminary


Our method
4.1. Estimation of Contribution in the Ideal Scenario
4.2. Batched Streaming Generative Active Learning


Experiments and 5.1. Offline Setting
5.2. Online Setting


Conclusion, Broader Impact, and References Related work
2.1. Generative Data Augmentation
2.2. Active Learning and Data Analysis Related work 2.1. Generative Data Augmentation 2.1. Generative Data Augmentation 2.2. Active Learning and Data Analysis 2.2. Active Learning and Data Analysis Preliminary Preliminary Preliminary Our method
4.1. Estimation of Contribution in the Ideal Scenario
4.2. Batched Streaming Generative Active Learning Our method 4.1. Estimation of Contribution in the Ideal Scenario 4.1. Estimation of Contribution in the Ideal Scenario 4.2. Batched Streaming Generative Active Learning 4.2. Batched Streaming Generative Active Learning Experiments and 5.1. Offline Setting
5.2. Online Setting Experiments and 5.1. Offline Setting Experiments and 5.1. Offline Setting 5.2. Online Setting 5.2. Online Setting Conclusion, Broader Impact, and References Conclusion, Broader Impact, and References Conclusion, Broader Impact, and References A. Implementation Details A. Implementation Details B. More ablations B. More ablations C. Discussion C. Discussion D. Visualization D. Visualization 5.2. Online Setting 5.2.1. MAIN RESULTS To validate the effectiveness of our method in handling longtailed segmentation tasks, we perform experiments on the LVIS (Gupta et al., 2019) dataset. A strong baseline —— XPaste (Zhao et al., 2023), is compared with our method. We further examine the impact of the usage (or non-usage) of CLIP (Radford et al., 2021), as mentioned in their paper, for filtering generated data. Given that X-Paste does not open source the generated data used, we have re-implemented the data generation pipeline and generated thousands of images 5.2.2. ABLATION Contribution estimation. We are interested in whether the three algorithms proposed in Section 4.2 are effective. Therefore, we conduct comparative experiments here, and the specific results are presented in Table 4. Random batch-level dropout. Our algorithm is essentially to accept or reject the generated data on a batch-by-batch basis. Therefore, when the contribution evaluation of the data is completely invalid, our algorithm degenerates into a random batch-level dropout. To verify that it is not this random dropout that brings performance improvement, we conduct a random batch-level Dropout experiment with the same acceptance rate. Table 6 shows that although random dropout will also bring a slight improvement, compared with our method, there is still a very obvious gap, which shows that the improvement brought by our method is not entirely due to random dropout. Random batch-level dropout. Authors:
(1) Muzhi Zhu, with equal contribution from Zhejiang University, China;
(2) Chengxiang Fan, with equal contribution from Zhejiang University, China;
(3) Hao Chen, Zhejiang University, China (haochen.cad@zju.edu.cn);
(4) Yang Liu, Zhejiang University, China;
(5) Weian Mao, Zhejiang University, China and The University of Adelaide, Australia;
(6) Xiaogang Xu, Zhejiang University, China;
(7) Chunhua Shen, Zhejiang University, China (chunhuashen@zju.edu.cn). Authors: Authors: (1) Muzhi Zhu, with equal contribution from Zhejiang University, China; (2) Chengxiang Fan, with equal contribution from Zhejiang University, China; (3) Hao Chen, Zhejiang University, China (haochen.cad@zju.edu.cn); (4) Yang Liu, Zhejiang University, China; (5) Weian Mao, Zhejiang University, China and The University of Adelaide, Australia; (6) Xiaogang Xu, Zhejiang University, China; (7) Chunhua Shen, Zhejiang University, China (chunhuashen@zju.edu.cn). This paper is available on arxiv under CC BY-NC-ND 4.0 Deed (Attribution-Noncommercial-Noderivs 4.0 International) license. This paper is available on arxiv under CC BY-NC-ND 4.0 Deed (Attribution-Noncommercial-Noderivs 4.0 International) license. available on arxiv available on arxiv [1] In CenterNet2, there is only one stage for mask loss. In addition, there are some other losses, which are not listed for simplicity.

Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.

Ablation of BSGAL: Contribution Estimation and Random Dropout Analysis

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

3D Mapping Initialization: Using RGB-D Images and Camera Parameters

Enhancing Long-Tailed Segmentation with Gradient Cache and BSGAL

BSGAL: Batched Streaming Active Learning for Generated Data

BSGAL: Gradient-Based Screening for Long-Tailed Perception Tasks

Offline Generative Active Learning: Feasibility and Limitations

It Is Okay If You Don't Know What You Like. We Do (feat. Deep Recommendation Algorithms)

3D Mapping Initialization: Using RGB-D Images and Camera Parameters

Enhancing Long-Tailed Segmentation with Gradient Cache and BSGAL

BSGAL: Batched Streaming Active Learning for Generated Data

BSGAL: Gradient-Based Screening for Long-Tailed Perception Tasks

Offline Generative Active Learning: Feasibility and Limitations

It Is Okay If You Don't Know What You Like. We Do (feat. Deep Recommendation Algorithms)

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps