LTRL: Boosting Long-tail Recognition via Reflective Learning
This addresses the problem of imbalanced data distributions in real-world scenarios for computer vision applications, with incremental improvements over existing methods.
The paper tackles long-tail recognition by proposing a reflective learning paradigm that integrates reviewing past predictions, summarizing feature relations, and correcting gradient conflicts, achieving state-of-the-art performance on popular benchmarks.
In real-world scenarios, where knowledge distributions exhibit long-tail. Humans manage to master knowledge uniformly across imbalanced distributions, a feat attributed to their diligent practices of reviewing, summarizing, and correcting errors. Motivated by this learning process, we propose a novel learning paradigm, called reflecting learning, in handling long-tail recognition. Our method integrates three processes for reviewing past predictions during training, summarizing and leveraging the feature relation across classes, and correcting gradient conflict for loss functions. These designs are lightweight enough to plug and play with existing long-tail learning methods, achieving state-of-the-art performance in popular long-tail visual benchmarks. The experimental results highlight the great potential of reflecting learning in dealing with long-tail recognition.