Research map / Detection and segmentation / CNN features
Multiple Saliency and Channel Sensitivity Network for Aggregated Convolutional Feature
Xuanlu Xiang, Zhipeng Wang, Zhicheng Zhao, Fei Su
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 |
|---|---|---|---|
| replace SSW with Gram-CS channel weighting (off-the-shelf) (ablation) | SW weighting · Oxford5K | mAP: 70.8 -> 71.4 | Improved |
| replace SSW with Gram-CS channel weighting (off-the-shelf) (ablation) | SW weighting · Paris6K | mAP: 79.7 -> 81.5 | Improved |
| replace SSW with Gram-CS channel weighting (supervised) (ablation) | SW weighting · Oxford5K | mAP: 78.7 -> 80.6 | Improved |
| replace SSW with Gram-CS channel weighting (supervised) (ablation) | SW weighting · Paris6K | mAP: 84.9 -> 87.1 | Improved |
| multi-scale instead of single-scale input (ablation) | MSB+Gram-CS · Oxford5K | mAP: 81.5 -> 86.1 | Improved |
| multi-scale instead of single-scale input (ablation) | MSB+Gram-CS · Paris6K | mAP: 86.5 -> 90.1 | Improved |
| increase saliency masks from 1 to 5 (ablation) | MSCNet supervised · Oxford5K | mAP: 82.5 -> 86.1 | Improved |
| increase saliency masks from 5 to 10 (ablation) | MSCNet supervised · Oxford5K | mAP: 86.1 -> 83.0 | Hurt |
| increase saliency masks from 5 to 10 (ablation) | MSCNet supervised · Paris6K | mAP: 90.1 -> 87.4 | Hurt |
| add NGD loss to multiple saliency block (ablation) | MSCNet SU-STA1 · Oxford5K | mAP | Improved |
| supervised vs unsupervised training on Holidays (ablation) | MSCNet · Holidays | mAP: 85.4 -> 90.2 | Mixed |
| add query expansion (QE) | MSCNet (5-512) supervised · Paris6K | mAP: 90.1 -> 93.1 | Improved |
Closest papers by meaning
- DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection (CVPR 2016 · similarity 0.85)
- Recurrently Aggregating Deep Features for Salient Object Detection (AAAI 2018 · similarity 0.84)
- Learning Deep Local Features With Multiple Dynamic Attentions for Large-Scale Image Retrieval (ICCV 2021 · similarity 0.84)
- Temporal Saliency Query Network for Efficient Video Recognition (ECCV 2022 · similarity 0.84)
- Progressive Attention Guided Recurrent Network for Salient Object Detection (CVPR 2018 · similarity 0.83)
- MCA: Moment Channel Attention Networks (AAAI 2024 · similarity 0.83)
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.
