Attentive Feature Augmentation for Long-Tailed Visual Recognition

Deep neural networks have achieved a great success on many visual recognition tasks.However, training data with a long-tailed distribution dramatically degenerates the performance of recognition models.In order to relieve this imbalance problem, an effective Long-Tailed Visual Recognition (LTVR) framework is proposed based on learned balance and robust features under long-tailed distribution circumstance.In this framework, a plug-and-play Attentive Feature Augmentation (AFA) module is designed to mine class-related and variationrelated features of original samples via attention mechanism.Then, those features are aggregated to synthesize fake features to cope with the imbalance of the original dataset.Moreover, a Lay-Back Learning Schedule (LBLS) is developed to ensure a good initialization of feature embedding.Extensive experiments are conducted with a two-stage training method to verify the effectiveness of the proposed framework on both feature learning and classifier rebalancing in the long-tailed image recognition task.Experimental results show that, when trained with imbalanced datasets, the proposed framework achieves superior performance over the state-of-the-art methods.