Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning
Shiming Chen, Ziming Hong, Wenjin Hou, Guo-Sen Xie, Yibing Song, Jian Cun Zhao, Xinge You, Shuicheng Yan, Ling Shao
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 |
|---|---|---|---|
| add AVT sub-net (ablation) | TransZero++ · CUB | accuracy: 49.0 -> 78.3 | Improved |
| add VAT sub-net (ablation) | TransZero++ · CUB | accuracy: 75.6 -> 78.3 | Improved |
| add feature augmentation encoder (FAE) (ablation) | TransZero++ · CUB | accuracy: 70.7 -> 78.3 | Improved |
| add feature augmentation (FA) in FAE (ablation) | TransZero++ · CUB | accuracy: 76.4 -> 78.3 | Improved |
| add visual-semantic decoder (DEC) (ablation) | TransZero++ · CUB | accuracy: 62.7 -> 78.3 | Improved |
| add self-calibration loss L_SC (ablation) | TransZero++ · CUB | H: 58.9 -> 70.4 | Improved |
| add attribute regression loss L_AR (ablation) | TransZero++ · SUN | accuracy: 64.7 -> 67.6 | Improved |
| add semantical collaborative loss to AVT (ablation) | TransZero++(AVT) · CUB | accuracy: 75.6 -> 77.6 | Improved |
| add semantical collaborative loss to VAT (ablation) | TransZero++(VAT) · SUN | accuracy: 57.7 -> 63.3 | Improved |
| l2 distance instead of l1 in collaborative loss (ablation) | TransZero++ · CUB | accuracy: 53.6 -> 78.3 | Improved |
| l2 instead of KL(p1||p2) in collaborative loss (ablation) | TransZero++ · CUB | accuracy: 76.4 -> 78.3 | Improved |
| add TransZero++ features to f-VAEGAN | f-VAEGAN · CUB | accuracy: 61.0 -> 71.2 | Improved |
Closest papers by meaning
- TransZero: Attribute-Guided Transformer for Zero-Shot Learning (AAAI 2022 · similarity 0.97)
- Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning (CVPR 2024 · similarity 0.92)
- Mutually Causal Semantic Distillation Network for Zero-Shot Learning (IJCV 2026 · similarity 0.91)
- ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning (AAAI 2025 · similarity 0.91)
- MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning (CVPR 2022 · similarity 0.91)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.90)
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.
