Sparse Generation: Making Pseudo Labels Sparse for Point Weakly Supervised Object Detection on Low Data Volume
This work addresses the challenge of improving object detection accuracy with limited labeled data, which is incremental as it builds on existing pseudo label methods.
The paper tackles the problem of generating high-quality pseudo labels for point weakly supervised object detection in low-data and dense object scenarios by proposing Sparse Generation, which makes pseudo labels sparse through three processing stages and perspective-based matching, achieving significant advantages over SOTA methods on four datasets including MS COCO-val.
Existing pseudo label generation methods for point weakly supervised object detection are inadequate in low data volume and dense object detection tasks. We consider the generation of weakly supervised pseudo labels as the model's sparse output, and propose Sparse Generation as a solution to make pseudo labels sparse. The method employs three processing stages (Mapping, Mask, Regression), constructs dense tensors through the relationship between data and detector model, optimizes three of its parameters, and obtains a sparse tensor, thereby indirectly obtaining higher quality pseudo labels, and addresses the model's density problem on low data volume. Additionally, we propose perspective-based matching, which provides more rational pseudo boxes for prediction missed on instances. In comparison to the SOTA method, on four datasets (MS COCO-val, RSOD, SIMD, Bullet-Hole), the experimental results demonstrated a significant advantage.