.png){kind=icon}
返回
Adaptive Discriminative Regularization for Visual Classification
.png){kind=icon}
PRE
AI
DOI：10.1007/s11263-024-02080-0.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
How to improve discriminative feature learning is central in classification. Existing works address this problem by explicitly increasing inter-class separability and intra-class compactness by constructing positive and negative pairs for contrastive learning or posing tighter class separating margins. These methods do not exploit the similarity between different classes as they adhere to independent identical distributions assumption in data. In this paper, we embrace the real-world data distribution setting in that some classes share semantic overlaps due to their similar appearances or concepts. Regarding this hypothesis, we propose a novel regularization to improve discriminative learning. We first calibrate the estimated highest likelihood of one sample based on its semantically neighboring classes, then encourage the overall likelihood predictions to be deterministic by imposing an adaptive exponential penalty. As the gradient of the proposed method is roughly proportional to the uncertainty of the predicted likelihoods, we name it adaptive discriminative regularization (ADR), trained along with a standard cross entropy loss in classification. Extensive experiments demonstrate that it can yield consistent and non-trivial performance improvements in a variety of visual classification tasks (over 10 benchmarks). Furthermore, we find it is robust to long-tailed and noisy label data distribution. Its flexible design enables its compatibility with mainstream classification architectures and losses.
Keyword:
Image classification
Regularization
Loss function
Cross entropy
期刊
IF:
9.3
论文数:
4.0K
被引数:
2.8W
机构
引用论文
.png){kind=icon}
分享收藏
I3CL: Intra- and Inter-Instance Collaborative Learning for Arbitrary-Shaped Scene Text Detection
OAAI
OAAI分享收藏分享收藏
查看更多内容