Research map / Vision-language and multimodal / CLIP and zero-shot
D$^2$O: A Dual Debiasing Operator for Training-Free Test-Time Adaptation of Vision–Language Models
Yihong Luo, Wenwu He, Dong Liang, Yihang Zhou, Zhuo-Xu Cui
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 |
|---|---|---|---|
| add D2O to ADAPT | ADAPT · PUG (online) | top-1 accuracy (avg): 51.87 -> 58.28 (+6.41) | Improved |
| add D2O to ADAPT | ADAPT · PUG (transductive) | top-1 accuracy (avg): 52.85 -> 56.85 (+4.00) | Improved |
| add D2O to TDA | TDA · PUG (online) | top-1 accuracy (avg): 51.50 -> 52.22 (+0.72) | Improved |
| add D2O to ADAPT | ADAPT · ImageNet OOD avg (online) | top-1 accuracy: 65.44 -> 65.92 (+0.48) | Improved |
| add D2O to ADAPT | ADAPT · ImageNet-C (online) | top-1 accuracy (avg): 28.56 -> 29.15 | Improved |
| add D2O to ADAPT | ADAPT · Fine-grained 10 datasets (online) | top-1 accuracy (avg): 70.76 -> 71.12 | Improved |
| add prior debiasing (ablation) | ADAPT with content evidence only · PUG+ImageNet (online) | top-1 accuracy: 58.70 -> 62.10 | Improved |
| add retrieval-oriented content evidence (ablation) | ADAPT baseline · PUG+ImageNet (online) | top-1 accuracy: 58.66 -> 58.70 | No clear effect |
| add retrieval-oriented content evidence (ablation) | ADAPT with prior debias · PUG+ImageNet (online) | top-1 accuracy: 62.01 -> 62.10 | No clear effect |
| add content features for retrieval (ablation) | raw-feature retrieval · PUG-ImageNet Camera factor | Top-5 retrieval purity: +2.5% | Improved |
| use routed bias instead of single global EMA bias (ablation) | D2O · Mixed-style PUG streams (online) | top-1 accuracy: 47.56 -> 42.78 (-4.78 for G-EMA) | Improved |
| increase number of routing clusters to 32 or more (ablation) | D2O+ADAPT · PUG-ImageNet (online) | top-1 accuracy | Hurt |
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.
- ADAPT — ADAPT: Vision-Language Navigation With Modality-Aligned Action Prompts (CVPR 2022) · better on 9 of 9 shared results
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
- Frustratingly Easy Test-Time Adaptation of Vision-Language Models (NeurIPS 2024 · similarity 0.92)
- Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts (NeurIPS 2026 · similarity 0.91)
- BendVLM: Test-Time Debiasing of Vision-Language Embeddings (NeurIPS 2024 · similarity 0.90)
- BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping (NeurIPS 2024 · similarity 0.90)
- Efficient Test-Time Adaptation of Vision-Language Models (CVPR 2024 · similarity 0.90)
- Bayesian Test-Time Adaptation for Vision-Language Models (CVPR 2025 · similarity 0.90)
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.
