Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Semantic Dictionary Learning for Multi-label Image Classification
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 DSDL instead of CoP | Multi-label image classification · Pascal VOC 2007 test | mAP: 93.8 -> 94.4 | Helped |
| Use DSDL instead of RCP | Multi-label image classification · Pascal VOC 2012 test | mAP: 92.2 -> 93.2 | Helped |
| Use DSDL instead of CoP | Multi-label image classification · Microsoft COCO validation | mAP: 81.1 -> 81.7 | Helped |
| Increase the L2 regularization weight lambda (ablation) | DSDL · Pascal VOC 2007, Pascal VOC 2012, and Microsoft COCO | classification performance | Mixed |
| Increase the dictionary-loss weight beta (ablation) | DSDL · Pascal VOC 2007, Pascal VOC 2012, and Microsoft COCO | classification performance | Mixed |
| Increase beta from zero to 10^{-4} (ablation) | DSDL · Pascal VOC 2007, Pascal VOC 2012, and Microsoft COCO | classification performance | No clear effect |
Closest papers by meaning
- CNN-RNN: A Unified Framework for Multi-Label Image Classification (CVPR 2016 · similarity 0.89)
- Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels (AAAI 2022 · similarity 0.88)
- Learning Spatial Regularization With Image-Level Supervisions for Multi-Label Image Classification (CVPR 2017 · similarity 0.87)
- Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuning (CVPR 2025 · similarity 0.86)
- Theory-Inspired Deep Multi-View Multi-Label Learning with Incomplete Views and Noisy Labels (CVPR 2025 · similarity 0.85)
- Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport (CVPR 2025 · similarity 0.85)
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.