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.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning
Continual self-supervised learning (CSSL) learns a series of tasks sequentially on the unlabeled data. Two main challenges of continual learning are catastrophic forgetting and task confusion. While CSSL problem has been…
class-incremental learningClass Incremental LearningContinual LearningContinual Self-Supervised Learning+2Label-Occurrence-Balanced Mixup for Long-tailed Recognition
Mixup is a popular data augmentation method, with many variants subsequently proposed. These methods mainly create new examples via convex combination of random data pairs and their corresponding one-hot labels. However,…
Data AugmentationDBN-Mix: Training Dual Branch Network Using Bilateral Mixup Augmentation for Long-Tailed Visual Recognition
There is growing interest in the challenging visual perception task of learning from long-tailed class distributions. The extreme class imbalance in the training dataset biases the model to prefer recognizing majority cl…
Data AugmentationDiversityRepresentation LearningAdapting Robot's Explanation for Failures Based on Observed Human Behavior in Human-Robot Collaboration
This work aims to interpret human behavior to anticipate potential user confusion when a robot provides explanations for failure, allowing the robot to adapt its explanations for more natural and efficient collaboration.…
Gaze Estimationbatchboost: regularization for stabilizing training with resistance to underfitting & overfitting
Overfitting & underfitting and stable training are an important challenges in machine learning. Current approaches for these issues are mixup, SamplePairing and BC learning. In our work, we state the hypothesis that mixi…
Image ClassificationSemi-Supervised Image Classification