Research map / Detection and segmentation / CNN features
Exploit and Replace: An Asymmetrical Two-Stream Architecture for Versatile Light Field Saliency Detection
Read the paperCheck 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 MFRM diversity loss to cross-entropy supervision (ablation) | teacher network · DUT-LFSD | MAE: .066 -> .040 | Helped |
| add MFRM diversity loss to cross-entropy supervision (ablation) | teacher network · HFUT-LFSD | MAE: .090 -> .082 | Helped |
| add MFRM diversity loss (ablation) | teacher network · DUT-LFSD | E-measure: .920 -> .943 | Helped |
| increase MFSM time steps from 1 to 4 (ablation) | teacher network · DUT-LFSD | MAE: .218 -> .040 | Helped |
| increase MFSM time steps from 3 to 4 (ablation) | teacher network · DUT-LFSD | MAE: .041 -> .040 | No clear effect |
| add multi-focusness distillation (MFD) (ablation) | ResNet18 student · DUT-LFSD | MAE: .119 -> .093 | Helped |
| add screened focusness distillation (SFD) on top of MFD (ablation) | ResNet18 student · DUT-LFSD | MAE: .093 -> .061 | Helped |
| add MFD and SFD (ablation) | ResNet18 student · HFUT-LFSD | MAE: .142 -> .085 | Helped |
| add MFD and SFD (ablation) | VGG16 student · DUT-LFSD | MAE: .086 -> .067 | Helped |
| add MFD and SFD (ablation) | MobileNetV2Plus student · DUT-LFSD | MAE: .250 -> .128 | Helped |
| replace focal-stack teacher with RGB student distilled (ablation) | student vs CPD · complexity | FPS: 66 -> 171 | Helped |
Closest papers by meaning
- Memory-oriented Decoder for Light Field Salient Object Detection (NeurIPS 2019 · similarity 0.90)
- Learning From Pixel-Level Noisy Label: A New Perspective for Light Field Saliency Detection (CVPR 2022 · similarity 0.90)
- Alignment-Free RGB-T Salient Object Detection: A Large-Scale Dataset and Progressive Correlation Network (AAAI 2025 · similarity 0.85)
- NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis (CVPR 2024 · similarity 0.84)
- Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images (AAAI 2025 · similarity 0.84)
- UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback (NeurIPS 2025 · similarity 0.84)
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.