Active Learning Strategies for Weakly-supervised Object Detection
This work addresses the problem of reducing annotation costs for object detection in computer vision, offering a data-efficient solution that is incremental but with strong specific gains.
The paper tackles the performance gap between weakly-supervised and fully-supervised object detectors by fine-tuning a base detector with a few fully-annotated samples selected using a novel active learning strategy called 'box-in-box' (BiB). Results show BiB reaches 97% of fully-supervised Fast RCNN performance with only 10% of fully-annotated images on VOC07 and reduces the performance gap by over 70% on COCO using 1% of the training set.
Object detectors trained with weak annotations are affordable alternatives to fully-supervised counterparts. However, there is still a significant performance gap between them. We propose to narrow this gap by fine-tuning a base pre-trained weakly-supervised detector with a few fully-annotated samples automatically selected from the training set using ``box-in-box'' (BiB), a novel active learning strategy designed specifically to address the well-documented failure modes of weakly-supervised detectors. Experiments on the VOC07 and COCO benchmarks show that BiB outperforms other active learning techniques and significantly improves the base weakly-supervised detector's performance with only a few fully-annotated images per class. BiB reaches 97% of the performance of fully-supervised Fast RCNN with only 10% of fully-annotated images on VOC07. On COCO, using on average 10 fully-annotated images per class, or equivalently 1% of the training set, BiB also reduces the performance gap (in AP) between the weakly-supervised detector and the fully-supervised Fast RCNN by over 70%, showing a good trade-off between performance and data efficiency. Our code is publicly available at https://github.com/huyvvo/BiB.