Contrast R-CNN for Continual Learning in Object Detection
This addresses continual learning for object detection, a domain-specific problem that is less explored compared to image classification, with incremental improvements over existing methods.
The paper tackles the problem of continual learning in object detection, where existing methods using knowledge distillation hinder learning new knowledge, and proposes Contrast R-CNN to balance retaining old knowledge and learning new knowledge, achieving effectiveness demonstrated on the PASCAL VOC dataset.
The continual learning problem has been widely studied in image classification, while rare work has been explored in object detection. Some recent works apply knowledge distillation to constrain the model to retain old knowledge, but this rigid constraint is detrimental for learning new knowledge. In our paper, we propose a new scheme for continual learning of object detection, namely Contrast R-CNN, an approach strikes a balance between retaining the old knowledge and learning the new knowledge. Furthermore, we design a Proposal Contrast to eliminate the ambiguity between old and new instance to make the continual learning more robust. Extensive evaluation on the PASCAL VOC dataset demonstrates the effectiveness of our approach.