Research map / Detection and segmentation / Weakly supervised detection and segmentation
Self-supervised co-salient object detection via feature correspondences at multiple scales
Souradeep Chakraborty, Dimitris Samaras
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add region-level feature correspondence refinement (stage 2) (ablation) | SCoSPARC · CoCA | F-measure max: 0.567 -> 0.601 | Improved |
| add dense CRF post-processing (ablation) | SCoSPARC · CoCA | F-measure max: 0.601 -> 0.614 | Improved |
| add confidence-based adaptive thresholding instead of fixed 0.5 (ablation) | SCoSPARC stage 1 · Cosal2015 / CoSOD3k / CoCA | MAE and F-measure: Cosal2015 MAE 0.072 -> 0.069 but F 0.853 -> 0.840; CoCA F 0.564 -> 0.567 | Mixed |
| add saliency loss to co-occurrence loss (ablation) | SCoSPARC stage 1 · CoCA vs Cosal2015/CoSOD3k | F-measure max: CoCA 0.565 -> 0.564; CoSOD3k 0.801 -> 0.810 | Mixed |
| use patch size 16 instead of 8 in ViT-B (ablation) | SCoSPARC stage 1 · CoCA | F-measure max: 0.567 -> 0.511 | Hurt |
| use ViT-Small instead of ViT-Base (ablation) | SCoSPARC stage 1 · CoCA | F-measure max: 0.567 -> 0.560 | Hurt |
| use convolutional VGG-16 backbone instead of DINO ViT (ablation) | SCoSPARC stage 1 · CoCA | F-measure max: 0.567 -> 0.356 | Hurt |
| train on COCO9213 plus DUTS-Class instead of one dataset (ablation) | SCoSPARC stage 1 · CoCA | F-measure max: 0.532 -> 0.567 (vs COCO9213 only) | Improved |
| self-supervised training without labels versus supervised GCoNet+ with 50% labels | SCoSPARC · CoCA | F-measure max: 0.534 (GCoNet+ 50%) -> 0.614 | Improved |
| drop the dense CRF for speed (ablation) | SCoSPARC · inference speed | FPS: 4.1 -> 20.5 FPS | Improved |
Closest papers by meaning
- Re-thinking Co-Salient Object Detection (TPAMI 2021 · similarity 0.94)
- Taking a Deeper Look at Co-Salient Object Detection (CVPR 2020 · similarity 0.93)
- CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection (NeurIPS 2020 · similarity 0.91)
- Co-Salient Object Detection with Co-Representation Purification (TPAMI 2023 · similarity 0.90)
- CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection (CVPR 2024 · similarity 0.89)
- Visual Consensus Prompting for Co-Salient Object Detection (CVPR 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
