Research map / Detection and segmentation / CNN features
Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection
Yongri Piao, Wei Ji, Jingjing Li, Miao Zhang, Huchuan Lu
This paper tried a common change: Add attention module
add the recurrent attention module RAM on top of DMSW · RGB-D saliency, proposed dataset · F-measure: 0.861 -> 0.883 Improved
What 492 accepted papers report for this change
- 444 improved
- 20 no clear effect
- 4 mixed
- 24 hurt
- Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems ICML 2026 · add wavelet attention block · CKF step 64 · Rel L2: 1.09 -> 0.35Improved
- DA-DFGAS:Differentiable Federated Graph Neural Architecture Search with Distribution-Aware Attentive Aggregation AAAI 2026 · add attention mechanism to aggregation · Table 4 datasets · parameters: about 5-10% more parametersHurt
- Caracal: Causal Architecture via Spectral Mixing ICML 2026 · add sliding window attention layers to MHF stack · Avg accuracy · avg accuracy (%): 48.22 -> 49.01Improved
See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.
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 the DRB multi-level fusion module over the common fusion baseline (ablation) | DMRANet · RGB-D saliency, proposed dataset | F-measure: 0.828 -> 0.839 | Improved |
| add the DRB multi-level fusion module over the common fusion baseline (ablation) | DMRANet · RGB-D saliency, proposed dataset | MAE: 0.070 -> 0.065 | Improved |
| add the DMSW module (depth-induced multi-scale weighting) on top of DRB (ablation) | DMRANet · RGB-D saliency, proposed dataset | F-measure: 0.839 -> 0.861 | Improved |
| add depth guidance to multi-scale feature integration in DMSW (ablation) | DMRANet · RGB-D saliency, proposed dataset | F-measure: 0.855 -> 0.861 | Improved |
| add depth guidance to multi-scale feature integration in DMSW (ablation) | DMRANet · RGB-D saliency, NLPR | F-measure: 0.805 -> 0.801 | Hurt |
| add the recurrent attention module RAM on top of DMSW (ablation) | DMRANet · RGB-D saliency, proposed dataset | F-measure: 0.861 -> 0.883 | Improved |
| use RAM instead of common channel-spatial attention (ablation) | DMRANet · RGB-D saliency, proposed dataset | F-measure: 0.869 -> 0.883 | Improved |
| use RAM instead of common channel-spatial attention (ablation) | DMRANet · RGB-D saliency, proposed dataset | MAE: 0.054 -> 0.048 | Improved |
| add common channel-spatial attention on top of DMSW (ablation) | DMRANet · RGB-D saliency, proposed dataset | F-measure: 0.861 -> 0.869 | Improved |
| use DMRANet instead of the best prior RGB-D CNN (PAGRN) | RGB-D saliency · RGB-D saliency, proposed dataset | F-measure: 0.836 -> 0.883 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PiCANet — PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection (CVPR 2018) · better on 2 of 2 shared results
- Amulet — Amulet: Aggregating Multi-Level Convolutional Features for Salient Object Detection (ICCV 2017) · better on 2 of 2 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
- Progressive Attention Guided Recurrent Network for Salient Object Detection (CVPR 2018 · similarity 0.91)
- Learning Selective Self-Mutual Attention for RGB-D Saliency Detection (CVPR 2020 · similarity 0.90)
- Learning Gaze Transitions From Depth to Improve Video Saliency Estimation (ICCV 2017 · similarity 0.90)
- Recurrent Attentional Networks for Saliency Detection (CVPR 2016 · similarity 0.90)
- Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detection (TPAMI 2021 · similarity 0.90)
- Salient Object Detection with Recurrent Fully Convolutional Networks (TPAMI 2018 · 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.
