Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognition
Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognition
Long-tailed image recognition is a computer vision problem considering a real-world class distribution rather than an artificial uniform. Existing methods typically detour the problem by i) adjusting a loss function, ii) decoupling classifier learning, or iii) proposing a new multi-head architecture called experts. In this paper, we tackle the problem from a different perspective to augment a training dataset to enhance the sample diversity of minority classes. Specifically, our method, namely Confusion-Pairing Mixup (CP-Mix), estimates the confusion distribution of the model and handles the data deficiency problem by augmenting samples from confusion pairs in real-time. In this way, CP-Mix trains the model to mitigate its weakness and distinguish a pair of classes it frequently misclassifies. In addition, CP-Mix utilizes a novel mixup formulation to handle the bias in decision boundaries that originated from the imbalanced dataset. Extensive experiments demonstrate that CP-Mix outperforms existing methods for long-tailed image recognition and successfully relieves the confusion of the classifier.
Youngseok Yoon、Haewon Jeong、Jungwoo Lee、Yao Qin、Sangwoo Hong、Hyungjun Joo
计算技术、计算机技术
Youngseok Yoon,Haewon Jeong,Jungwoo Lee,Yao Qin,Sangwoo Hong,Hyungjun Joo.Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognition[EB/OL].(2024-11-12)[2025-05-22].https://arxiv.org/abs/2411.07621.点此复制
评论