Research map / Detection and segmentation / Weakly supervised detection and segmentation
Tell Me Where to Look: Guided Attention Inference Network
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 |
|---|---|---|---|
| Trainable self-guided attention instead of classification-only attention | SEC-based semantic segmentation · PASCAL VOC 2012 val | mIoU: 50.7 -> 55.3 | Helped |
| Trainable self-guided attention instead of classification-only attention | SEC-based semantic segmentation · PASCAL VOC 2012 test | mIoU: 51.7 -> 56.8 | Helped |
| Add external pixel-level attention supervision using 200 labels | GAIN_ext-based SEC · PASCAL VOC 2012 val | mIoU: 54.3 -> 58.3 | Helped |
| Increase external pixel-level attention supervision from 200 to 1464 labels (ablation) | GAIN_ext-based SEC · PASCAL VOC 2012 val | mIoU: 58.3 -> 60.5 | Helped |
| Replace Grad-CAM attention with self-guided GAIN | Image classification on the biased boat dataset · Biased Boat overall | classification accuracy: 36% -> 55% | Helped |
| Add pixel-level boat attention guidance | GAIN · Biased Boat overall | classification accuracy: 55% -> 66% | Helped |
| Add pixel-level boat attention guidance | GAIN · Boats without water | classification accuracy: 48% -> 64% | Helped |
| Add pixel-level boat attention guidance | GAIN · Water without boat | classification accuracy: 62% -> 68% | Helped |
| Increase pixel-level boat attention guidance from 9 to 78 labels (ablation) | GAIN_ext · Biased Boat overall | classification accuracy: 66% -> 84% | Helped |
Closest papers by meaning
- L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation (CVPR 2022 · similarity 0.89)
- Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation (CVPR 2017 · similarity 0.88)
- Learning what and where to attend (ICLR 2019 · similarity 0.88)
- Learning Affinity From Attention: End-to-End Weakly-Supervised Semantic Segmentation With Transformers (CVPR 2022 · similarity 0.87)
- Attention Guided CAM: Visual Explanations of Vision Transformer Guided by Self-Attention (AAAI 2024 · similarity 0.86)
- ResCLIP: Residual Attention for Training-free Dense Vision-language Inference (CVPR 2025 · 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.