Research map / Label-efficient and robust learning / Self-supervised and contrastive
Concept Generalization in Visual Representation Learning
Mert Bulent Sariyildiz, Yannis Kalantidis, Diane Larlus, Karteek Alahari
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 |
|---|---|---|---|
| use self-supervised pretraining (DINO, SwAV, BYOL, OBoW, SimCLR-v2) instead of supervised training | ResNet50 · ImageNet-CoG L1-L5 (linear, all data) | top-1 accuracy | Improved |
| replace ResNet50 by ResNet50-sized visual transformers (DeiT-S, T2T-ViT-t-14) | ResNet50 · ImageNet-CoG L5 (linear, all data) | top-1 accuracy | Hurt |
| use transformer-based models in few-shot linear classification | ResNet50 · ImageNet-CoG L5 (few-shot, N<=128) | top-1 accuracy: consistent 3-4% accuracy gain | Improved |
| pretrain on additional noisy web data (Semi-Sup, Semi-Weakly-Sup, CLIP) | ResNet50 · ImageNet-CoG L1-L5 (linear, all data) | top-1 accuracy | Improved |
| add distillation (MEAL-v2, DeiT-S-distilled) | ResNet50 / DeiT-S · ImageNet-CoG L1-L5 (linear, all data) | top-1 accuracy | Improved |
| add adversarial training (Adv-Robust) | ResNet50 · ImageNet-CoG L1-L5 (linear, all data) | top-1 accuracy | No clear effect |
| use NAS-designed backbones (EfficientNet-B1/B4, NAT-M4) | ResNet50 · ImageNet-CoG L1-L5 (linear, all data) | top-1 accuracy | Improved |
| add label-associated augmentation (MixUp, Manifold-MixUp, CutMix, ReLabel) | ResNet50 · ImageNet-CoG L1-L5 (linear, all data) | top-1 accuracy | Hurt |
| build levels with word2vec text similarity instead of WordNet Lin similarity (ablation) | ImageNet-CoG levels · ImageNet-CoG L3-L5 (ResNet50 linear) | top-1 accuracy | Improved |
| class-balance levels by subsampling to 732 training images per concept (ablation) | ImageNet-CoG · ImageNet-CoG (subset of models) | top-1 accuracy | No clear effect |
Closest papers by meaning
- ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models (AAAI 2024 · similarity 0.89)
- Restyling Unsupervised Concept Based Interpretable Networks with Generative Models (ICLR 2025 · similarity 0.88)
- Bridging the gap to real-world language-grounded visual concept learning (NeurIPS 2025 · similarity 0.88)
- Explaining Domain Shifts in Language: Concept Erasing for Interpretable Image Classification (CVPR 2025 · similarity 0.88)
- Concept-Guided Prompt Learning for Generalization in Vision-Language Models (AAAI 2024 · similarity 0.87)
- Concept-Aware Batch Sampling Improves Language-Image Pretraining (CVPR 2026 · 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.
