Research map / Detection and segmentation / Open-set and few-shot detection
Generalizable Co-Salient Object Detection via Mixed Content-Style Modulation
Guanting Guo, Shenglong Hu, Kaihua Zhang, Guangcan Liu, Min Xia
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 SCM (ablation) | CoMCS baseline · CoCA | S-measure: 0.662 -> 0.724 | Improved |
| add SCM (ablation) | CoMCS baseline · CoCA | max F-measure: 0.492 -> 0.608 | Improved |
| add SCM, MCM and MSM on top of SCM (ablation) | CoMCS · CoCA | S-measure: 0.724 -> 0.747 | Improved |
| add MSM style modulation (ablation) | SCM+MCM · CoCA | MAE: marginal 0.2% MAE change | No clear effect |
| add MCM and MSM to SCM-only (ablation) | CoMCS · Unseen-domain dataset | S-measure: 0.786 -> 0.856 | Improved |
| use CoMCS instead of MCCL | MCCL · Unseen-domain dataset | S-measure: 0.834 -> 0.856 | Improved |
| use CoMCS instead of GCoNet+ | GCoNet+ · Unseen-domain dataset | max F-measure: 0.803 -> 0.830 | Improved |
| use CoMCS instead of IPPO | IPPO · CoCA | S-measure: 0.747 vs 0.747 | No clear effect |
| use CoMCS instead of GCoNet+ | GCoNet+ · CoCA | MAE: 0.081 -> 0.084 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- GCoNet+ — GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector (TPAMI 2023) · better on 5 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Re-thinking Co-Salient Object Detection (TPAMI 2021 · similarity 0.88)
- CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection (NeurIPS 2020 · similarity 0.87)
- Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection (CVPR 2025 · similarity 0.86)
- Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts (NeurIPS 2025 · similarity 0.85)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.85)
- Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection (NeurIPS 2025 · similarity 0.85)
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.
