The paper introduces the concept of information density to explain category bias in visual object detection. It finds a strong negative correlation between a category’s information density and its detection accuracy, showing that instance count alone does not account for bias. By incorporating information density into three advanced loss functions, the authors demonstrate reduced model bias and improved overall performance on Pascal VOC, COCO‑LT, and LVIS datasets.
By Ziwei Zhao, Yanxi Lu, Yuwei Hu, Shiyang Su, Mingxuan Wang, Chenyue Zhou, Jiayi Chen, Hehan Li, Xiaoshuai Hao, Andi Zhang, Yanbiao Ma
Balancing performance trade-offs on long-tailed data distributions remains a long-standing challenge in visual recognition. Existing methods mainly improve tail classes through re-balancing, represent...
arXiv:2609.37331v1 Announce Type: new
Abstract: Balancing performance trade-offs on long-tailed data distributions remains a long-standing challenge in visual recognition. Existing methods mainly imp...
By Shenghan Chen, Yiming Liu, Zhipeng Deng, Haolin Wang, Jiale Zhou, Zhijian Wu, Xiankai Lu, Yafei Ou, Yefeng Zheng
arXiv:2510. 06596v2 Announce Type: replace-cross Abstract: The performance of machine learning models depends heavily on training data.
By Ayush Zenith, Arnold Zumbrun, Neel Raut, Jing Lin
arXiv:2609.14654v1 Announce Type: new
Abstract: Convolutional neural networks (CNNs) are typically evaluated using held-out classification accuracy, an approach that presupposes predictions are based...
By Abhilekha Dalal, Michael Okonoda, Eder Martinez, Lior Shamir
arXiv:2605. 07821v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models.
By Boyang Dai, Chaoqi Chen, Yizhou Yu