paper-with-me

홈 › Papers

Learning Muti-expert Distribution Calibration for Long-tailed Video Classification

2022-05-22 · Yufan Hu, Junyu Gao, Changsheng Xu

Most existing state-of-the-art video classification methods assume that the training data obey a uniform distribution. However, video data in the real world typically exhibit an imbalanced long-tailed class distribution, resulting in a model bias towards head class and relatively low performance on tail class. While the current long-tailed classification methods usually focus on image classification, adapting it to video data is not a trivial extension. We propose an end-to-end multi-expert distribution calibration method to address these challenges based on two-level distribution information. The method jointly considers the distribution of samples in each class (intra-class distribution) and the overall distribution of diverse data (inter-class distribution) to solve the issue of imbalanced data under long-tailed distribution. By modeling the two-level distribution information, the model can jointly consider the head classes and the tail classes and significantly transfer the knowledge from the head classes to improve the performance of the tail classes. Extensive experiments verify that our method achieves state-of-the-art performance on the long-tailed video classification task.

📄 PDF Abstract BibTeX arXiv:2205.10788

Code (0)

등록된 구현이 없습니다.

Tasks

Classificationimage-classificationImage ClassificationVideo Classification

Similar Papers 제목 키워드 기반

Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution

2023-04-13 · CVPR 2023 1 · Jiahao Chen, Bing Su

How to estimate the uncertainty of a given model is a crucial problem. Current calibration techniques treat different classes equally and thus implicitly assume that the distribution of training data is balanced, but ign…

Domain Adaptation

AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization

2026-06-03 · Wanqi Yang, Yuexiao Ma, Alexander Conzelmann, Xiawu Zheng 외 arxiv

Mixture-of-Experts (MoE) architectures scale model capacity through sparse expert activation, but their deployment remains memory-bound because all expert weights must reside in memory. Mixed-precision quantization can s…

Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition

2021-07-20 · Yifan Zhang, Bryan Hooi, Lanqing Hong, Jiashi Feng

Existing long-tailed recognition methods, aiming to train class-balanced models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution. However, practical test class …

Image ClassificationLong-tail LearningTest Agnostic Long-Tailed Learning

Rethink Long-tailed Recognition with Vision Transformers

2023-02-28 · Zhengzhuo Xu, Shuo Yang, Xingjun Wang, Chun Yuan

In the real world, data tends to follow long-tailed distributions w.r.t. class or attribution, motivating the challenging Long-Tailed Recognition (LTR) problem. In this paper, we revisit recent LTR methods with promising…

Label-Aware Distribution Calibration for Long-tailed Classification

2021-11-09 · Chaozheng Wang, Shuzheng Gao, Cuiyun Gao, Pengyun Wang 외

Real-world data usually present long-tailed distributions. Training on imbalanced data tends to render neural networks perform well on head classes while much worse on tail classes. The severe sparseness of training inst…

Classification