Research map / Label-efficient and robust learning / Semi-supervised learning
Adaptive Consistency Regularization for Semi-Supervised Transfer Learning
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 |
|---|---|---|---|
| Add AKC and ARC | Semi-supervised transfer learning · CUB-200-2011, 400 labels | accuracy: 32.79 -> 41.69 | Helped |
| Add AKC and ARC | Semi-supervised transfer learning · MURA, 400 labels | accuracy: 69.43 -> 71.34 | Helped |
| Add AKC and ARC | Semi-supervised transfer learning · CIFAR-10, 4000, 250, and 40 labels | top-1 error rate: 4.24 -> 6.55; 5.04 -> 13.93; 9.05 -> 24.17 | Hurt |
| Add AKC and ARC | FixMatch · CIFAR-10, 4000, 250, and 40 labels | top-1 error rate: 4.24 -> 4.19; 5.04 -> 4.99; 9.05 -> 7.62 | Helped |
| Add AKC and ARC | MixMatch · CUB-200-2011, 2000 and 200 labels | accuracy: 73.84 -> 77.51; 22.66 -> 29.55 | Helped |
| Add AKC and ARC | FixMatch · MURA, 1000 and 400 labels | accuracy: 75.10 -> 76.60; 69.43 -> 72.14 | Helped |
| Add AKC and ARC | FixMatch · Indoor-67, 1340 and 134 labels | accuracy: 74.27 -> 76.64; 44.13 -> 48.34 | Helped |
| Add AKC and ARC | Standard supervised transfer learning · CUB-200-2011 | accuracy: 81.77 -> 83.52 | Helped |
| Use adaptive entropy-gated AKC rather than non-adaptive AKC on all samples (ablation) | AKC · CUB-200-2011, 400 labels | accuracy: 34.62 -> 38.71 | Helped |
| Use adaptive entropy-gated ARC rather than non-adaptive ARC on all samples (ablation) | ARC · CUB-200-2011, 400 labels | accuracy: 39.63 -> 41.88 | Helped |
| Set AKC threshold to 0.7 instead of disabling AKC with threshold 0 (ablation) | AKC · CUB-200-2011, 400 labels | accuracy: 28.82 -> 38.71 | Helped |
| Set ARC threshold to 0.5 instead of disabling ARC with threshold 0 (ablation) | ARC · CUB-200-2011, 400 labels | accuracy: 28.82 -> 41.88 | Helped |
Closest papers by meaning
- Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions (ICML 2023 · similarity 0.88)
- There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average (ICLR 2019 · similarity 0.87)
- Controller-Guided Partial Label Consistency Regularization with Unlabeled Data (AAAI 2024 · similarity 0.86)
- RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised Learning (AAAI 2025 · similarity 0.86)
- InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning (ICML 2024 · similarity 0.86)
- A Unified Framework for Heterogeneous Semi-supervised Learning (CVPR 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.