Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification
Kai Yi, Xiaoqian Shen, Yunhao Gou, Mohamed Elhoseiny
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 hierarchical contrastive fine-tuning to CLIP | CLIP ResNet-50 · ImageNet-21K-D (unseen classes) | Hit@1: 15.22 -> 16.39 | Improved |
| use CLIP Transformer text features instead of word2vec (ablation) | HGR-Net · ImageNet-21K-D (unseen classes) | Hit@1: 2.35 -> 16.39 | Improved |
| add outer-loop (ancestor labels) loss (ablation) | HGR-Net · ImageNet-21K-D (unseen classes) | Hit@1: 15.47 -> 16.39 | Improved |
| add inner-loop (sibling negatives) loss (ablation) | HGR-Net · ImageNet-21K-D (unseen classes) | Hit@1: 16.16 -> 16.39 | Improved |
| use TopM negative sampling instead of random (ablation) | HGR-Net · ImageNet-21K-D (unseen classes) | Hit@1: 15.72 -> 16.39 | Improved |
| use TopM negative sampling instead of sibling sampling (ablation) | HGR-Net · ImageNet-21K-D (unseen classes) | POR: 13.46 -> 16.19 | Improved |
| use adaptive learnable layer weights instead of equal weights (ablation) | HGR-Net · ImageNet-21K-D (unseen classes) | Hit@1: 15.97 -> 16.39 | Improved |
| use adaptive weights instead of non-linear increasing weights (ablation) | HGR-Net · ImageNet-21K-D (unseen classes) | Hit@1: 15.58 -> 16.39 | Improved |
| raise outer ratio K (ablation) | HGR-Net · ImageNet-21K-D (unseen classes) | TOR and POR | Improved |
| add HGR loss to CNZSL with CLIP Transformer text | CNZSL(Tr) · ImageNet-21K-D (unseen classes) | Hit@1: 5.77 -> 5.91 | Improved |
| add HGR loss to CNZSL with word2vec | CNZSL(w2v) · ImageNet-21K-D (unseen classes) | Hit@1: 1.94 -> 1.96 | No clear effect |
| separate adjacency into ancestors and descendants (ablation) | DGP(Tr) · ImageNet-21K-D (unseen classes) | Hit@1: 5.42 -> 5.78 | Improved |
Closest papers by meaning
- Zero-Shot Recognition via Semantic Embeddings and Knowledge Graphs (CVPR 2018 · similarity 0.92)
- Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective (ICCV 2019 · similarity 0.91)
- Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning (ICCV 2017 · similarity 0.90)
- Zero-Shot Learning on Semantic Class Prototype Graph (TPAMI 2017 · similarity 0.89)
- Class Semantic Attribute Perception Guided Zero-Shot Learning (AAAI 2025 · similarity 0.88)
- Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names (CVPR 2024 · similarity 0.88)
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.
