Research map / Label-efficient and robust learning / Test-time adaptation
Blocking the Leakage: Manifold-Aware Gradient Projection for Long-Horizon Test-Time Adaptation
Haoyu Xiong, Chengchao Wang, ZhongQiang Wang, He Huang, Qiuxia Yang, Zhengpeng Zhao, Yuanyuan Pu
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 |
|---|---|---|---|
| project entropy gradients onto the orthogonal complement of a tracked low-rank subspace | TENT-style entropy minimization · ImageNet-C long-horizon revisits (40 rounds) | accuracy: TENT 37.51 -> 0.46 vs MGP 41.90 -> 42.96 | Improved |
| add MGP to the stream with only misclassified samples (blind-spot) | entropy-based TTA · ImageNet-K, ImageNet-R blind-spot | accuracy: IN-K 27.01, IN-R 32.85 vs baselines near 0% | Improved |
| tighten entropy gating threshold to 0.1 on TENT (ablation) | TENT · ImageNet-C (ViT-B/16) long-horizon | rounds before collapse: collapse delayed to 11 rounds, not prevented | Mixed |
| loosen entropy gating threshold to 0.4 or above on TENT (ablation) | TENT · ImageNet-C (ViT-B/16) long-horizon | rounds before collapse: collapse within 3 rounds | Hurt |
| project out the protected subspace from spurious-sample gradients (ablation) | entropy minimization · ImageNet-C | accuracy over time | Improved |
| project reliable-sample gradients onto the residual space (ablation) | entropy minimization with reliable samples · ImageNet-C | accuracy | No clear effect |
| increase refresh interval K from 100 to 1000 (ablation) | MGP · ImageNet-C long-horizon | final accuracy change: -1.89% | Hurt |
| inject strong rank-1 anisotropy into residual updates (kappa=100) (ablation) | MGP · ImageNet-C long-horizon | final accuracy change: -1.80% | Hurt |
| use automatic MP bulk-edge rank selection instead of fixed rank (ablation) | MGP · ImageNet-C long-horizon | accuracy | Improved |
| shuffle domain order every round (ablation) | MGP · ImageNet-C (ViT-B/16) | accuracy: 53.13 -> 55.26 | No clear effect |
| abrupt shift from ImageNet-C to imbalanced ImageNet-K (ablation) | MGP · two-stage shift (ViT-B/16) | accuracy: 36.68 -> 44.36 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- TENT — Tent: Fully Test-Time Adaptation by Entropy Minimization (ICLR 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts (NeurIPS 2026 · similarity 0.88)
- A Layer Selection Approach to Test Time Adaptation (AAAI 2025 · similarity 0.87)
- ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains (NeurIPS 2025 · similarity 0.87)
- Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment (NeurIPS 2025 · similarity 0.87)
- EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample (NeurIPS 2026 · similarity 0.87)
- Backpropagation-free Network for 3D Test-time Adaptation (CVPR 2024 · 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.
