WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition
This work reduces labeling costs for computer vision tasks by improving weakly-supervised recognition, though it is incremental as it builds on existing foundation models.
The paper tackles weakly-supervised object detection and segmentation by leveraging the Segment Anything Model (SAM) to address limitations like pseudo ground truth incompleteness and noise, achieving average improvements of 7.4% and 8.5% over previous state-of-the-art methods.
Weakly supervised visual recognition using inexact supervision is a critical yet challenging learning problem. It significantly reduces human labeling costs and traditionally relies on multi-instance learning and pseudo-labeling. This paper introduces WeakSAM and solves the weakly-supervised object detection (WSOD) and segmentation by utilizing the pre-learned world knowledge contained in a vision foundation model, i.e., the Segment Anything Model (SAM). WeakSAM addresses two critical limitations in traditional WSOD retraining, i.e., pseudo ground truth (PGT) incompleteness and noisy PGT instances, through adaptive PGT generation and Region of Interest (RoI) drop regularization. It also addresses the SAM's problems of requiring prompts and category unawareness for automatic object detection and segmentation. Our results indicate that WeakSAM significantly surpasses previous state-of-the-art methods in WSOD and WSIS benchmarks with large margins, i.e. average improvements of 7.4% and 8.5%, respectively. The code is available at \url{https://github.com/hustvl/WeakSAM}.