Research map / Probabilistic and scientific modeling / Variational and generative sampling
Uncertainty Inspired RGB-D Saliency Detection
Jing Zhang, Deng-Ping Fan, Yuchao Dai, Saeed Anwar, Fatemeh Sadat Saleh, Sadegh Aliakbarian, Nick M. Barnes
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 early fusion of latent z instead of late fusion (ablation) | Ours CVAE · LFSD | S-measure: .868 -> .839 | Improved |
| add early fusion of latent z instead of middle fusion (ablation) | Ours CVAE · NJU2K | S-measure: .902 -> .897 | Improved |
| add saliency consensus module instead of averaging predictions (ablation) | Ours CVAE · NJU2K | S-measure: .902 -> .900 | Improved |
| add saliency consensus module instead of averaging z (ablation) | Ours CVAE · NJU2K | S-measure: .902 -> .901 | Improved |
| add hybrid CVAE+GSNN loss instead of CVAE loss only (ablation) | Ours CVAE · NJU2K | S-measure: .902 -> .900 | Improved |
| add smoothness loss (ablation) | Ours CVAE · SSB | S-measure: .898 -> .885 | Improved |
| add structure-aware loss instead of cross-entropy (ablation) | Ours CVAE · LFSD | S-measure: .868 -> .851 | Improved |
| add structure-aware loss instead of cross-entropy (ablation) | Ours CVAE · SIP | F-measure: .877 -> .856 | Improved |
| replace raw depth with HHA encoding (ablation) | Ours CVAE · SIP | S-measure: .883 -> .870 | No clear effect |
| add KL annealing (ablation) | Ours CVAE · NJU2K | S-measure: .902 -> .900 | No clear effect |
| add KL annealing (ablation) | Ours CVAE · RGB-D test sets | prediction variance | Improved |
| increase latent dimension from 3 up to 32 (ablation) | Ours CVAE · six RGB-D datasets | MAE | Improved |
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.
- UC-Net — UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders (CVPR 2020) · 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
- UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders (CVPR 2020 · similarity 0.95)
- RGB-D Saliency Detection via Cascaded Mutual Information Minimization (ICCV 2021 · similarity 0.91)
- Select, Supplement and Focus for RGB-D Saliency Detection (CVPR 2020 · similarity 0.91)
- Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection (ICLR 2022 · similarity 0.91)
- An Energy-Based Prior for Generative Saliency (TPAMI 2023 · similarity 0.90)
- Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction (NeurIPS 2021 · 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.
