Research map / Label-efficient and robust learning / Knowledge distillation
Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation
Bingchen Zhao, Kai Han
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 |
|---|---|---|---|
| combine global and local branches with mutual distillation | Novel visual category discovery · CUB-200, Stanford-Cars, FGVC-Aircraft | ACC: 39.5 ± 1.7% -> 47.8 ± 2.4%; 53.8 ± 2.0% -> 61.9 ± 2.5%; 66.3 ± 0.7% -> 70.4 ± 0.9% | Improved |
| add the local branch and its part-level ranking statistics (ablation) | Global-branch RankStat baseline · CUB-200 | ACC: 39.5 ± 1.7% -> 43.1 ± 2.3% | Improved |
| add the BCE loss for dual ranking pseudo-label training (ablation) | Ours full · CUB-200, Stanford-Cars, FGVC-Aircraft, ImageNet-100 | ACC: 2.2 ± 1.3% -> 47.8 ± 2.4%; 3.1 ± 0.4% -> 61.9 ± 2.5%; 5.1 ± 0.4% -> 70.4 ± 0.9%; 3.0 ± 0.3% -> 69.4 ± 2.1% | Improved |
| add mutual-distillation sKLD loss between the branches (ablation) | Ours full · CUB-200, Stanford-Cars, FGVC-Aircraft, ImageNet-100 | ACC: 39.8 ± 1.8% -> 47.8 ± 2.4%; 50.6 ± 2.1% -> 61.9 ± 2.5%; 60.8 ± 1.5% -> 70.4 ± 0.9%; 58.2 ± 1.2% -> 69.4 ± 2.1% | Improved |
| add supervised cross-entropy loss on labelled data (ablation) | Ours full · CUB-200, Stanford-Cars, FGVC-Aircraft, ImageNet-100 | ACC: 41.2 ± 2.4% -> 47.8 ± 2.4%; 52.4 ± 4.3% -> 61.9 ± 2.5%; 60.2 ± 2.7% -> 70.4 ± 0.9%; 59.1 ± 2.7% -> 69.4 ± 2.1% | Improved |
| add consistency MSE loss across image transformations (ablation) | Ours full · CUB-200, Stanford-Cars, FGVC-Aircraft, ImageNet-100 | ACC: 37.9 ± 4.5% -> 47.8 ± 2.4%; 50.6 ± 6.2% -> 61.9 ± 2.5%; 58.9 ± 5.7% -> 70.4 ± 0.9%; 57.2 ± 3.6% -> 69.4 ± 2.1% | Improved |
| add self-supervised pretraining (ablation) | Ours full · CUB-200, Stanford-Cars, FGVC-Aircraft, ImageNet-100 | ACC: 44.3 ± 3.5% -> 47.8 ± 2.4%; 58.2 ± 1.8% -> 61.9 ± 2.5%; 67.4 ± 1.3% -> 70.4 ± 0.9%; 65.3 ± 1.3% -> 69.4 ± 2.1% | Improved |
| use two branches of the same type with mutual distillation (ablation) | Global-branch configuration · CUB-200 | ACC: 39.5 ± 1.7% -> 41.2 ± 0.8% | Improved |
| use two local branches with mutual distillation instead of one (ablation) | Local-branch configuration · CUB-200 | ACC: 43.1 ± 0.9% -> 44.7 ± 1.1% | Improved |
| use global and local branches rather than two local branches (ablation) | Two-branch design · CUB-200, Stanford-Cars, ImageNet-100 | ACC: 44.7 ± 1.1% -> 47.8 ± 2.4%; 57.9 ± 0.5% -> 61.9 ± 2.5%; 65.7 ± 1.4% -> 69.4 ± 2.1% | Improved |
| increase global/local feature-bank size from 2048 to 32768 (ablation) | Ours full · CIFAR-10, CUB-200, Stanford-Cars, ImageNet-100 | ACC: 91.6% -> 93.0%; 47.8% -> 48.4%; 61.9% -> 62.9%; 69.4% -> 71.3% | Improved |
| increase local part dictionary V size from 2048 to 32768 (ablation) | Ours full · CIFAR-10, CUB-200, Stanford-Cars, ImageNet-100 | ACC: 91.6% -> 92.0%; 47.8% -> 49.3%; 61.9% -> 63.7%; 69.4% -> 71.4% | Improved |
Closest papers by meaning
- Automatically Discovering and Learning New Visual Categories with Ranking Statistics (ICLR 2020 · similarity 0.90)
- Labeled Data Selection for Category Discovery (ECCV 2024 · similarity 0.90)
- Semantic-Guided Novel Category Discovery (AAAI 2024 · similarity 0.89)
- Automatically Discovering Novel Visual Categories With Adaptive Prototype Learning (TPAMI 2023 · similarity 0.89)
- Democratizing Fine-grained Visual Recognition with Large Language Models (ICLR 2024 · similarity 0.86)
- CAKE: Category Aware Knowledge Extraction for Open-Vocabulary Object Detection (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.
