Research map / Detection and segmentation / CNN features
SESS: Saliency Enhancing with Scaling and Sliding
Osman Tursun, Simon Denman, Sridha Sridharan, Clinton Fookes
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 SESS | Guided-BP (ResNet-50) · ImageNet-1k val (5000 images) | overall: 36.8 -> 41.0 | Improved |
| add SESS | Grad-CAM (ResNet-50) · ImageNet-1k val (5000 images) | overall: 56.0 -> 57.3 | Improved |
| add SESS | Grad-CAM (VGG-16) · ImageNet-1k val (5000 images) | insertion: 60.6 -> 60.3 | No clear effect |
| add SESS | Guided-BP (ResNet-50) · ImageNet-1k val (5000 images) | deletion (lower better): 11.0 -> 12.0 | Hurt |
| add SESS | Group-CAM (VGG-16) · ImageNet-1k val (5000 images) | insertion: 61.1 -> 61.1 | No clear effect |
| add SESS | Group-CAM (ResNet-50) · Pointing Game VOC07 (All) | pointing accuracy: 84.2 -> 92.4 | Improved |
| add SESS | Grad-CAM (ResNet-50) · Pointing Game COCO (Difficult) | pointing accuracy: 52.3 -> 63.2 | Improved |
| add SESS | Guided-BP (VGG-16) · Pointing Game COCO (All) | pointing accuracy: 39.1 -> 39.5 | Improved |
| add SESS | all base methods · Pointing Game VOC07 and COCO | pointing accuracy: 11.2% average, 19.8% on difficult | Improved |
| increase number of scales (ablation) | Grad-CAM · ImageNet-1k val (2000 images) | insertion/deletion | Improved |
| increase pre-filter ratio above 0.6 (ablation) | Grad-CAM · ImageNet-1k val (2000 images) | insertion/deletion | Hurt |
| add channel-wise weights in fusion (ablation) | SESS · qualitative | saliency focus | Improved |
Closest papers by meaning
- Weakly-Supervised Salient Object Detection Using Point Supervision (AAAI 2022 · similarity 0.87)
- Xaitk-Saliency: An Open Source Explainable AI Toolkit for Saliency (AAAI 2023 · similarity 0.87)
- Weakly-Supervised Salient Object Detection via Scribble Annotations (CVPR 2020 · similarity 0.86)
- Inferring Salient Objects from Human Fixations (TPAMI 2019 · similarity 0.86)
- Salient Object Detection: A Discriminative Regional Feature Integration Approach (IJCV 2016 · similarity 0.86)
- CAMERAS: Enhanced Resolution and Sanity Preserving Class Activation Mapping for Image Saliency (CVPR 2021 · similarity 0.86)
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.
