计算机科学
加权
稳健性(进化)
人工智能
模式识别(心理学)
跳跃式监视
样品(材料)
特征(语言学)
数据挖掘
机器学习
放射科
哲学
基因
医学
生物化学
化学
色谱法
语言学
作者
Jia-Wei Ma,Min Liang,Lei Chen,Shu Tian,Song-Lu Chen,Lei Chen,Xu-Cheng Yin
标识
DOI:10.1109/tmm.2023.3340065
摘要
Label assignment (LA) is one of the essential phases in the object detection paradigm and aims to classify samples as foreground or background. Current LA strategies generally discriminate samples by explicit thresholds and then calculate weighted losses based on their significances. However, existing methods mostly neglect to consider the importance of samples comprehensively due to the uneven distribution of objects and the limitations of detector structures. In this paper, we propose a hierarchical equalization loss (HEL) by reconsidering the underlying factors affecting sample weights. First, we mitigate sample imbalance at three progressive levels. (1) Task level. We propose task-reconciled weights (TRW) to overcome the effects caused by inter-task inconsistencies (i.e., the inherent differences of classification and localization). (2) Instance level. We propose instance-aware normalization (IAN) for reconstructing the distribution of sample weights within an instance to suppress environmental noise. (3) Pyramid level. We propose hierarchical modulation (HM) to alleviate the unbalanced distribution of multi-scale objects on feature pyramids. Then, we stack the above three mechanisms and formulate the effective weighted loss. Moreover, we propose a staggered candidate bag construction (SCBC) mechanism to further improve the robustness of our method. Without adding any extra overhead, HEL can improve the performance of representative detectors by an impressive margin. Equipped with HEL, a single “ResNet-50+FPN+Head” detector can achieve a performance of 41.9 AP on COCO under 1× schedule, outperforming other existing LA methods. Extensive experiments conducted on multiple backbones and datasets demonstrate the effectiveness of our method.
科研通智能强力驱动
Strongly Powered by AbleSci AI