Research map / Detection and segmentation / Weakly supervised detection and segmentation
Learning to Detect Salient Objects With Image-Level Supervision
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use image-level tags for weakly supervised saliency training instead of unsupervised saliency methods | WSS · ECSSD, SED, PASCAL-S, THUR, HKU-IS, DUTS | Fβ measure: 0.823 vs 0.705; 0.838 vs 0.786; 0.720 vs 0.604; 0.663 vs 0.547; 0.821 vs 0.677; 0.657 vs 0.511 | Helped |
| Use image-level tags for weakly supervised saliency training instead of fully supervised saliency training | WSS · SED | Fβ measure: 0.838 vs 0.825 | Helped |
| Use image-level tags for weakly supervised saliency training instead of fully supervised saliency training | WSS · ECSSD, PASCAL-S, THUR, HKU-IS, DUTS | Fβ measure: 0.823 vs 0.834; 0.720 vs 0.747; 0.663 vs 0.694; 0.821 vs 0.856; 0.657 vs 0.714 | Mixed |
| Add iterative CRF refinement and self-training to the pretrained FIN (ablation) | FIN1 · ECSSD, SED, THUR, HKU-IS, DUTS | Fβ measure | Helped |
| Use the proposed iterative CRF instead of a CRF with a fixed unary term (ablation) | WSS1 · ECSSD, SED, PASCAL-S, THUR, HKU-IS | Fβ measure | Helped |
| Use GSP instead of GAP (ablation) | WSS1 · ECSSD, SED, PASCAL-S, THUR, HKU-IS | Fβ measure | Helped |
| Use GSP instead of GMP (ablation) | WSS1 · ECSSD, SED, PASCAL-S, THUR, HKU-IS | Fβ measure | Helped |
| Use the FIN rather than averaging score-map channels (ablation) | WSS1 · ECSSD, SED, PASCAL-S, THUR, HKU-IS | Fβ measure | Helped |
Closest papers by meaning
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · similarity 0.91)
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision (CVPR 2019 · similarity 0.90)
- Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence (AAAI 2021 · similarity 0.90)
- An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection (CVPR 2019 · similarity 0.90)
- Multi-Source Weak Supervision for Saliency Detection (CVPR 2019 · similarity 0.90)
- Deep Embedding Features for Salient Object Detection (AAAI 2019 · similarity 0.90)
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.