Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning
Chaoqun Wang, Xuejin Chen, Shaobo Min, Xiaoyan Sun, Houqiang Li
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 VCM instance discrimination to Basic-ZSL (ablation) | Basic-ZSL · CUB | H: 63.5 -> 68.5 | Improved |
| increase the instance-discrimination loss weight from 0 to 0.1 (ablation) | Basic-ZSL with VCM · CUB and aPY | H | Improved |
| increase the instance-discrimination loss weight from 0.1 to 1.0 (ablation) | Basic-ZSL with VCM · CUB and aPY | H | Hurt |
| add attribute masking (ablation) | Basic-ZSL with VCM · CUB | H: 68.5 -> 69.5 | Improved |
| add cross-modal triplet loss (ablation) | VCM with attribute masking · CUB | H: 69.5 -> 69.9; 0.4% improvement | Improved |
| add masked attribute prediction loss (ablation) | VCM with attribute masking and cross-modal triplet · CUB | H: 69.9 -> 70.4 | Improved |
| add grayscale augmentation (ablation) | VCM with cropping and horizontal flipping · CUB | H: 66.0 -> 65.5 | Hurt |
| add color jittering (ablation) | VCM with cropping and horizontal flipping · CUB | H: 66.0 -> 63.8; 66.0 -> 65.3; 66.0 -> 65.2 | Hurt |
| add Gaussian blurring (ablation) | VCM with cropping and horizontal flipping · CUB | H: 66.0 -> 67.1 | Improved |
| add rotation; larger tested angles perform worse than the 30-degree setting (ablation) | VCM with cropping and horizontal flipping · CUB | H: 66.0 -> 64.4; 66.0 -> 64.7; 66.0 -> 66.5 | Mixed |
| add jigsaw swapping; larger tested patch counts perform worse than 3 (ablation) | VCM with cropping and horizontal flipping · CUB | H: 66.0 -> 64.2; 66.0 -> 65.8; 66.0 -> 66.7 | Mixed |
| combine positive low-level augmentations (ablation) | Basic-ZSL with VCM · CUB | H: 65.3 -> 68.5; 3.2% | Improved |
Closest papers by meaning
- Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot Learning (CVPR 2023 · similarity 0.89)
- Adaptive and Generative Zero-Shot Learning (ICLR 2021 · similarity 0.89)
- Dual Progressive Prototype Network for Generalized Zero-Shot Learning (NeurIPS 2021 · similarity 0.89)
- Attend and Enrich: Enhanced Visual Prompt for Zero-Shot Learning (AAAI 2025 · similarity 0.89)
- Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learning (CVPR 2025 · similarity 0.88)
- Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning (CVPR 2024 · similarity 0.87)
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.
