Feature Space Augmentation for Long-Tailed Data
Real-world data often follow a long-tailed distribution as the frequency of each class is typically different. For example, a dataset can have a large number of under-represented classes and a few classes with more than sufficient data. However, a model to represent the dataset is usually expected to have reasonably homogeneous performances across classes. Introducing class-balanced loss and advanced methods on data re-sampling and augmentation are among the best practices to alleviate the data imbalance problem. However, the other part of the problem about the under-represented classes will have to rely on additional knowledge to recover the missing information. In this work, we present a novel approach to address the long-tailed problem by augmenting the under-represented classes in the feature space with the features learned from the classes with ample samples. In particular, we decompose the features of each class into a class-generic component and a class-specific component using class activation maps. Novel samples of under-represented classes are then generated on the fly during training stages by fusing the class-specific features from the under-represented classes with the class-generic features from confusing classes. Our results on different datasets such as iNaturalist, ImageNet-LT, Places-LT and a long-tailed version of CIFAR have shown the state of the art performances.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ClassificationLong-tail LearningSimilar Papers 제목 키워드 기반
FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation
Recent methods for long-tailed instance segmentation still struggle on rare object classes with few training data. We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addre…
Instance SegmentationSegmentationSemantic SegmentationTransfer LearningBreadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed Recognition
The problem of long-tailed recognition, where the number of examples per class is highly unbalanced, is considered. While training with class-balanced sampling has been shown effective for this problem, it is known to ov…
Decision Boundary-aware Generation for Long-tailed Learning
Long-tailed data bias decision boundaries toward head classes and degrade tail class accuracy. Diffusion-based generative augmentation address this problem by generating additional data, while head-to-tail transfer furth…
Representation LearningSupervised Contrastive Learning on Blended Images for Long-tailed Recognition
Real-world data often have a long-tailed distribution, where the number of samples per class is not equal over training classes. The imbalanced data form a biased feature space, which deteriorates the performance of the …
Contrastive LearningData AugmentationLong-tail LearningSAFA: Sample-Adaptive Feature Augmentation for Long-Tailed Image Classification
Imbalanced datasets with long-tailed distribution widely exist in practice, posing great challenges for deep networks on how to handle the biased predictions between head (majority, frequent) classes and tail (minority, …
image-classificationImage ClassificationLong-tail Learning