Research map / Label-efficient and robust learning / Recognition and long-tail
SCOUTER: Slot Attention-Based Classifier for Explainable Image Recognition
Liangzhi Li, Bowen Wang, Manisha Verma, Yuta Nakashima, Ryo Kawasaki, Hajime Nagahara
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 |
|---|---|---|---|
| increase area-loss weight lambda from 1 to 10 (ablation) | SCOUTER+ · ImageNet-100 positive | explanation area size: 0.1561 -> 0.0476 | Improved |
| increase area-loss weight lambda from 1 to 10 (ablation) | SCOUTER+ · ImageNet-100 positive | precision: 0.8493 -> 0.9257 | Improved |
| increase lambda from 1 to 10 (ablation) | SCOUTER+ · ImageNet-100 positive | DAUC: 0.1753 -> 0.2713 | Hurt |
| increase lambda from 1 to 10 (ablation) | SCOUTER+ · ImageNet-100 classification | accuracy | No clear effect |
| threshold heatmap (a>=0.2) to shrink explanation area | SS-CAM · ImageNet-100 positive | IAUC: 0.7143 -> 0.6010 | Hurt |
| threshold heatmap (a>=0.2) to shrink explanation area | SS-CAM · ImageNet-100 positive | DAUC: 0.4570 -> 0.7781 | Hurt |
| add GRU slot update instead of averaging (ablation) | SCOUTER+ · ImageNet-100 positive | IAUC: 0.7456 -> 0.7647 | Improved |
| add GRU slot update instead of averaging (ablation) | SCOUTER- · ImageNet-100 negative | IAUC: 0.5959 -> 0.6730 | Improved |
| add position embedding (ablation) | SCOUTER- · ImageNet-100 negative | IAUC: 0.6141 -> 0.6730 | Improved |
| add position embedding (ablation) | SCOUTER+ · ImageNet-100 positive | precision: 0.8973 -> 0.9257 | Improved |
| replace FC classifier with SCOUTER+ | ResNeSt 26 · ImageNet-100 | accuracy: 0.8080 -> 0.7991 | Mixed |
| replace FC classifier with SCOUTER+ | ResNeSt 26 · CUB-200 | accuracy: 0.7538 -> 0.7362 | Hurt |
Closest papers by meaning
- Adaptive Slot Attention: Object Discovery with Dynamic Slot Number (CVPR 2024 · similarity 0.84)
- Generating Visual Explanations (ECCV 2016 · similarity 0.84)
- I-CEE: Tailoring Explanations of Image Classification Models to User Expertise (AAAI 2024 · similarity 0.84)
- A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis (ICLR 2024 · similarity 0.83)
- MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning (NeurIPS 2025 · similarity 0.83)
- Explaining in Diffusion: Explaining a Classifier with Diffusion Semantics (CVPR 2025 · 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.
