Research map / Label-efficient and robust learning / Self-supervised and contrastive
Self-Supervised Classification Network
Elad Amrani, Leonid Karlinsky, Alex Bronstein
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 |
|---|---|---|---|
| replace SCAN clustering-step loss with the Self-Classifier loss (ablation) | SCAN · ImageNet unsupervised classification | ACC: 39.9 -> 40.4 | Improved |
| use a learnable classifier instead of a fixed one (ablation) | Self-Classifier · ImageNet (100 epochs) | k-NN | clustering accuracy: 57.6|32.2 -> 61.7|37.3 | Improved |
| use heads with different class counts (1k+2k+4k+8k) instead of 15x1k (ablation) | Self-Classifier · ImageNet (100 epochs) | k-NN accuracy: 58.8 -> 61.7 | Improved |
| use multiple heads of 1k classes instead of a single 1k head (ablation) | Self-Classifier · ImageNet (100 epochs) | k-NN accuracy: 59.6 -> 58.6 | Hurt |
| increase batch size from 256 to 4096 (ablation) | Self-Classifier · ImageNet (100 epochs) | k-NN | clustering accuracy: 49.0|20.9 -> 61.7|37.3 | Improved |
| use smaller MLP (1x4096 hidden, 128 output) instead of 2x8192 hidden (ablation) | Self-Classifier · ImageNet (100 epochs) | k-NN accuracy: 60.0 -> 61.7 | Improved |
| set column temperature 0.05 with row temperature 0.1 instead of row 0.07 (ablation) | Self-Classifier · ImageNet (100 epochs) | clustering accuracy: 29.2 -> 37.3 | Improved |
| increase NN queue length from 256K to 1M (ablation) | Self-Classifier · ImageNet (100 epochs) | k-NN | clustering accuracy: 61.7|37.3 -> 56.8|35.5 | Hurt |
| increase NN queue length from 128K to 256K (ablation) | Self-Classifier · ImageNet (100 epochs) | k-NN | clustering accuracy: 59.2|36.8 -> 61.7|37.3 | Improved |
| increase training epochs from 100 to 800 | Self-Classifier · ImageNet unsupervised classification | ACC: 37.3 -> 41.1 | Improved |
| use hidden-layer output 256 instead of 128 with 1x4096 MLP (ablation) | Self-Classifier · ImageNet (100 epochs) | clustering accuracy: 37.3 -> 33.5 | Hurt |
Closest papers by meaning
- A Survey on Self-Supervised Learning: Algorithms, Applications, and Future Trends (TPAMI 2024 · similarity 0.90)
- Self-labelling via simultaneous clustering and representation learning (ICLR 2020 · similarity 0.90)
- Self-Contrastive Learning: Single-Viewed Supervised Contrastive Framework Using Sub-network (AAAI 2023 · similarity 0.89)
- Beyond Learning Features: Training a Fully-Functional Classifier with ZERO Instance-Level Labels (AAAI 2022 · similarity 0.89)
- Self-Supervised Learning via Maximum Entropy Coding (NeurIPS 2022 · similarity 0.89)
- Measuring Self-Supervised Representation Quality for Downstream Classification Using Discriminative Features (AAAI 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.
