Research map / Image generation / Autoregressive and latent generation
Energy-Based Generative Cooperative Saliency Prediction
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 |
|---|---|---|---|
| Use cooperative LVM–EBM prediction instead of deterministic saliency prediction | Fully supervised saliency prediction · DUTS | Sα: .900 -> .902 | Helped |
| Use cooperative learning while recovering from scribble labels | Weakly supervised saliency prediction · ECSSD | Sα: .879 -> .896 | Helped |
| Add trained EBM refinement to BASN | BASN saliency predictions · DUTS | Sα | Helped |
| Add trained EBM refinement to SCRN | SCRN saliency predictions · DUTS | Sα | Helped |
| Add latent noise vector h to the encoder-decoder (ablation) | Saliency generator Gα · DUTS | Sα: .878 -> .902 | Helped |
| Add cooperative EBM training to the latent variable model (ablation) | Gα(X,h) saliency generator · DUTS | Sα: .897 -> .902 | Helped |
| Replace the proposed decoder with the ITSD decoder (ablation) | Cooperative saliency framework · DUTS | Sα: .885 -> .914 | Helped |
| Replace ResNet50 with VGG16 as the encoder backbone (ablation) | Cooperative saliency framework · DUTS | Sα: .857 -> .906 | Helped |
| Use Monte Carlo dropout for uncertainty estimation | Saliency prediction · DUTS | Sα: .881 vs .902 | Hurt |
| Use deep ensembles for uncertainty estimation | Saliency prediction · DUTS | Sα: .885 vs .902 | Hurt |
Closest papers by meaning
- Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction (NeurIPS 2021 · similarity 0.90)
- UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders (CVPR 2020 · similarity 0.88)
- Understanding and Visualizing Deep Visual Saliency Models (CVPR 2019 · similarity 0.88)
- Shallow and Deep Convolutional Networks for Saliency Prediction (CVPR 2016 · similarity 0.88)
- CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion (AAAI 2025 · similarity 0.87)
- H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition (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.