Semantic-aware SAM for Point-Prompted Instance Segmentation
This work addresses the challenge of precise category-specific segmentation for researchers and practitioners using point annotations to reduce labeling costs, representing an incremental improvement over existing SAM-based methods.
The paper tackles the problem of semantic ambiguity in SAM's class-agnostic segmentation for point-prompted instance segmentation by introducing SAPNet, which integrates MIL and SAM to select representative masks and uses strategies like Point Distance Guidance, achieving promising results on Pascal VOC and COCO datasets.
Single-point annotation in visual tasks, with the goal of minimizing labelling costs, is becoming increasingly prominent in research. Recently, visual foundation models, such as Segment Anything (SAM), have gained widespread usage due to their robust zero-shot capabilities and exceptional annotation performance. However, SAM's class-agnostic output and high confidence in local segmentation introduce 'semantic ambiguity', posing a challenge for precise category-specific segmentation. In this paper, we introduce a cost-effective category-specific segmenter using SAM. To tackle this challenge, we have devised a Semantic-Aware Instance Segmentation Network (SAPNet) that integrates Multiple Instance Learning (MIL) with matching capability and SAM with point prompts. SAPNet strategically selects the most representative mask proposals generated by SAM to supervise segmentation, with a specific focus on object category information. Moreover, we introduce the Point Distance Guidance and Box Mining Strategy to mitigate inherent challenges: 'group' and 'local' issues in weakly supervised segmentation. These strategies serve to further enhance the overall segmentation performance. The experimental results on Pascal VOC and COCO demonstrate the promising performance of our proposed SAPNet, emphasizing its semantic matching capabilities and its potential to advance point-prompted instance segmentation. The code will be made publicly available.