Research map / Label-efficient and robust learning / Recognition and long-tail
Enriching ImageNet With Human Similarity Judgments and Psychological Embeddings
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 cosine distance instead of L1 or L2 distance | Target-model triplet evaluation · ImageNet-HSJ seed and full (v0.1 and v0.2) | triplet accuracy | Helped |
| Use a psychological embedding rather than a pretrained target model | Triplet evaluation on ImageNet-HSJ · Seed and full (v0.1 and v0.2) | triplet accuracy | Helped |
| Increase task-specific classification performance with newer supervised models | Supervised image representations · ImageNet-HSJ human similarity judgments | psychological embedding correlation | No clear effect |
| Use an unsupervised representation (DeepCluster VGG16) instead of supervised representations | ImageNet-HSJ target-model evaluation · Seed and full (v0.1 and v0.2) | triplet accuracy and psychological embedding correlation | Hurt |
Closest papers by meaning
- The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric (NeurIPS 2026 · similarity 0.88)
- Perception Encoder: The best visual embeddings are not at the output of the network (NeurIPS 2025 · similarity 0.88)
- Evaluating Multiview Object Consistency in Humans and Image Models (NeurIPS 2024 · similarity 0.87)
- Evaluating alignment between humans and neural network representations in image-based learning tasks (NeurIPS 2024 · similarity 0.87)
- L-WISE: Boosting Human Visual Category Learning Through Model-Based Image Selection and Enhancement (ICLR 2025 · similarity 0.87)
- When does perceptual alignment benefit vision representations? (NeurIPS 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.