Generalized Few-Shot Object Detection without Forgetting
This addresses a crucial limitation in realistic object detection applications where test samples may contain any instances, requiring models to detect all classes without forgetting.
The paper tackles the problem of few-shot object detection where models must learn new classes without forgetting previously learned ones, and introduces Retentive R-CNN, which significantly outperforms state-of-the-art methods by maintaining competitive performance on few-shot classes without degrading base class performance.
Recently few-shot object detection is widely adopted to deal with data-limited situations. While most previous works merely focus on the performance on few-shot categories, we claim that detecting all classes is crucial as test samples may contain any instances in realistic applications, which requires the few-shot detector to learn new concepts without forgetting. Through analysis on transfer learning based methods, some neglected but beneficial properties are utilized to design a simple yet effective few-shot detector, Retentive R-CNN. It consists of Bias-Balanced RPN to debias the pretrained RPN and Re-detector to find few-shot class objects without forgetting previous knowledge. Extensive experiments on few-shot detection benchmarks show that Retentive R-CNN significantly outperforms state-of-the-art methods on overall performance among all settings as it can achieve competitive results on few-shot classes and does not degrade the base class performance at all. Our approach has demonstrated that the long desired never-forgetting learner is available in object detection.