C-WSL: Count-guided Weakly Supervised Localization
This addresses the challenge of reducing annotation effort for object localization in computer vision, offering a more efficient alternative to full bounding-box annotations.
The paper tackles the problem of weakly supervised localization (WSL) by introducing count-guided supervision using per-class object counts, resulting in large improvements in WSL performance and significantly outperforming state-of-the-art methods on VOC2007 and VOC2012 datasets.
We introduce count-guided weakly supervised localization (C-WSL), an approach that uses per-class object count as a new form of supervision to improve weakly supervised localization (WSL). C-WSL uses a simple count-based region selection algorithm to select high-quality regions, each of which covers a single object instance during training, and improves existing WSL methods by training with the selected regions. To demonstrate the effectiveness of C-WSL, we integrate it into two WSL architectures and conduct extensive experiments on VOC2007 and VOC2012. Experimental results show that C-WSL leads to large improvements in WSL and that the proposed approach significantly outperforms the state-of-the-art methods. The results of annotation experiments on VOC2007 suggest that a modest extra time is needed to obtain per-class object counts compared to labeling only object categories in an image. Furthermore, we reduce the annotation time by more than $2\times$ and $38\times$ compared to center-click and bounding-box annotations.