Research map / Detection and segmentation / CNN features
Learning From Pixel-Level Noisy Label: A New Perspective for Light Field Saliency Detection
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 |
|---|---|---|---|
| Add mutual feature fusion between the all-focus view and focal slices (ablation) | Light-field saliency model · DUT-LF | F-measure: 0.641 -> 0.689 | Helped |
| Add the pixel forgetting matrix to identify inconsistent pixels (ablation) | Light-field saliency model · DUT-LF | F-measure: 0.689 -> 0.741 | Helped |
| Add the cross-scene noise penalty loss (ablation) | Light-field saliency model · DUT-LF | MAE: 0.279 -> 0.147 | Helped |
| Combine the proposed components in the full model (ablation) | Light-field saliency model · DUT-LF | F-measure: 0.641 -> 0.813 | Helped |
| Vary the pixel-learning threshold δ (ablation) | Ours · DUT-LF | F-measure: 0.744; 0.786; 0.813; 0.801; 0.792; 0.761; 0.771 | Mixed |
| Vary the pixel-learning threshold δ (ablation) | Ours · DUT-LF | MAE: 0.221; 0.183; 0.091; 0.091; 0.163; 0.155; 0.160 | Mixed |
Closest papers by meaning
- Memory-oriented Decoder for Light Field Salient Object Detection (NeurIPS 2019 · similarity 0.92)
- Exploit and Replace: An Asymmetrical Two-Stream Architecture for Versatile Light Field Saliency Detection (AAAI 2020 · similarity 0.90)
- Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective (CVPR 2018 · similarity 0.88)
- Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection (ICLR 2022 · similarity 0.87)
- LF-BVN: Blind-View Network for Self-Supervised Light Field Denoising (CVPR 2026 · similarity 0.86)
- Unsupervised Salient Instance Detection (CVPR 2024 · 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.