Research map / Label-efficient and robust learning / Recognition and long-tail
From $t$-SNE to UMAP with contrastive learning
Read the paperCheck 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 |
|---|---|---|---|
| Increase InfoNCE noise samples from m=2 to m=16 (ablation) | SimCLR with ResNet18 · CIFAR-10 test set | kNN classifier accuracy: 86.9±0.2 -> 91.7±0.1 | Helped |
| Increase InfoNCE noise samples from m=2 to m=16 (ablation) | SimCLR with ResNet18 · CIFAR-10 test set | Linear classifier accuracy: 90.7± 0.2 -> 93.1± 0.2 | Helped |
| Increase InfoNCE noise samples beyond m=16 (ablation) | SimCLR with ResNet18 · CIFAR-10 test set | kNN classifier accuracy: 91.7±0.1 -> 92.0±0.3; 92.2±0.2; 91.9± 0.1 | No clear effect |
| Increase InfoNCE noise samples beyond m=16 (ablation) | SimCLR with ResNet18 · CIFAR-10 test set | Linear classifier accuracy: 93.1± 0.2 -> 93.3± 0.3; 93.2± 0.3; 93.3± 0.1 | No clear effect |
Closest papers by meaning
- Embedding Dimension of Contrastive Learning and $k$-Nearest Neighbors (NeurIPS 2024 · similarity 0.87)
- $\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs (ICLR 2025 · similarity 0.87)
- On the Similarities of Embeddings in Contrastive Learning (ICML 2025 · similarity 0.87)
- BECLR: Batch Enhanced Contrastive Few-Shot Learning (ICLR 2024 · similarity 0.87)
- Single-View Graph Contrastive Learning with Soft Neighborhood Awareness (AAAI 2025 · similarity 0.86)
- Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling (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.