REVIEW 2 cited by
DOEI: Dual Optimization of Embedding Information for Attention-Enhanced Class Activation Maps
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Weakly supervised semantic segmentation (WSSS) typically utilizes limited semantic annotations to obtain initial Class Activation Maps (CAMs). However, due to the inadequate coupling between class activation responses and semantic information in high-dimensional space, the CAM is prone to object co-occurrence or under-activation, resulting in inferior recognition accuracy. To tackle this issue, we propose DOEI, Dual Optimization of Embedding Information, a novel approach that reconstructs embedding representations through semantic-aware attention weight matrices to optimize the expression capability of embedding information. Specifically, DOEI amplifies tokens with high confidence and suppresses those with low confidence during the class-to-patch interaction. This alignment of activation responses with semantic information strengthens the propagation and decoupling of target features, enabling the generated embeddings to more accurately represent target features in high-level semantic space. In addition, we propose a hybrid-feature alignment module in DOEI that combines RGB values, embedding-guided features, and self-attention weights to increase the reliability of candidate tokens. Comprehensive experiments show that DOEI is an effective plug-and-play module that empowers state-of-the-art visual transformer-based WSSS models to significantly improve the quality of CAMs and segmentation performance on popular benchmarks, including PASCAL VOC (+3.6%, +1.5%, +1.2% mIoU) and MS COCO (+1.2%, +1.6% mIoU). Code will be available at https://github.com/AIGeeksGroup/DOEI.
Forward citations
Cited by 2 Pith papers
-
SSS: Semi-Supervised SAM-2 with Efficient Prompting for Medical Imaging Segmentation
SSS applies SAM-2 with a Discriminative Feature Enhancement mechanism and a physical-constraint sliding-window prompt generator, reporting Dice scores of 53.15 on BHSD and 89.34 to 91.21 on ACDC.
-
Semantic segmentation with reward
RSS applies GRPO-style reinforcement learning with mIoU rewards to semantic segmentation and claims to beat weakly supervised methods, but the comparison is unfair and the results are unreproducible.
Discussion (0). Sign in to comment.