Research map / Label-efficient and robust learning / Recognition and long-tail
Saliency-based Sequential Image Attention with Multiset Prediction
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 |
|---|---|---|---|
| Use permutation-invariant RL multiset training instead of cross-entropy on randomly ordered labels | HSAL · MNIST Set | macro-F1: 0.735 -> 0.990 | Helped |
| Use permutation-invariant RL multiset training instead of cross-entropy on randomly ordered labels | HSAL · MNIST Multiset | macro-F1: 0.726 -> 0.978 | Helped |
| Use permutation-invariant RL multiset training instead of cross-entropy on randomly ordered labels | HSAL · SVHN Multiset | macro-F1: 0.589 -> 0.973 | Helped |
| Use permutation-invariant RL multiset training instead of cross-entropy on randomly ordered labels | HSAL · SVHN Multiset | exact match (0-1): 0.307 -> 0.947 | Helped |
| Add reward for selecting glimpse locations with high priority-map values | HSAL controller · Training | attn_saliency: 58.7 -> 126.5 | Helped |
Closest papers by meaning
- Recurrent Attentional Reinforcement Learning for Multi-Label Image Recognition (AAAI 2018 · similarity 0.90)
- A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning (CVPR 2020 · similarity 0.88)
- Bi-Directional Object-Context Prioritization Learning for Saliency Ranking (CVPR 2022 · similarity 0.88)
- Understanding and Visualizing Deep Visual Saliency Models (CVPR 2019 · similarity 0.88)
- Explainable Saliency: Articulating Reasoning with Contextual Prioritization (CVPR 2025 · similarity 0.86)
- CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion (AAAI 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.