Source-Free Cross-Domain Few-Shot Learning

Latest papers

9 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Query-Conditioned Prototype Adaptation for Cross-Domain Few-Shot Learning: Single-Query Inference, Controlled Comparisons, and Failure Modes
Sep 25, 2026Rushab Rasik Karania, Tomas MaulSource-Free Cross-Domain Few-Shot Learning Few-Shot Learning
School of Computer Science, University of Nottingham Malaysia, Semenyih, 43500, Selangor, Malaysia
When Semantics Saturate or Emerge: Adaptation-Conditional Semantic Utility in Source-Free Cross-Domain Few-Shot Learning
Aug 7, 2026Wei Liu, Xing Deng, Haijian ShaoSource-Free Cross-Domain Few-Shot Learning Few-Shot Domain Adaptation
College of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212003, China
Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning
May 28, 2026Shuai Yi, Yixiong Zou, Yuhua Li +1Source-Free Cross-Domain Few-Shot Learning Source-Free Domain Adaptation
Institute of Artificial Intelligence, Huazhong University of Science and Technology, Wuhan, China · School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China.
Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning
May 25, 2026Shuai Yi, Yixiong Zou, Yuhua Li +1Source-Free Cross-Domain Few-Shot Learning Source-Free Domain Adaptation
Huazhong University of Science and Technology
Reviving In-domain Fine-tuning Methods for Source-Free Cross-domain Few-shot Learning
May 12, 2026Yaze Zhao, Yicong Liu, Yixiong Zou +2Source-Free Cross-Domain Few-Shot Learning Source-Free Domain Adaptation
Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment
Mar 18, 2026Yaze Zhao, Yixiong Zou, Yuhua Li +1Cycle Consistency Source-Free Cross-Domain Few-Shot Learning
School of Computer Science and Technology, Huazhong University of Science and Technology
Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning
Mar 7, 2026Zhenyu Zhang, Yixiong Zou, Yuhua Li +2Source-Free Cross-Domain Few-Shot Learning Few-Shot Learning
School of Computer Science and Technology, Huazhong University of Science and Technology · National Key Laboratory for Multimedia Information Processing, Peking University
Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning
Mar 5, 2026Zhenyu Zhang, Guangyao Chen, Yixiong Zou +2Source-Free Cross-Domain Few-Shot Learning Few-Shot Learning
School of Computer Science and Technology, Huazhong University of Science and Technology · National Key Laboratory for Multimedia Information Processing, Peking University
SRasP: Self-Reorientation Adversarial Style Perturbation for Cross-Domain Few-Shot Learning
Mar 5, 2026Wenqian Li, Pengfei Fang, Hui XueSource-Free Cross-Domain Few-Shot Learning Few-Shot Learning
the School of Computer Science and Engineering, Southeast University, Nanjing 210096, China · the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing 211189, China

Sep 25, 2026J/K move · Enter open · S save

Query-Conditioned Prototype Adaptation for Cross-Domain Few-Shot Learning: Single-Query Inference, Controlled Comparisons, and Failure Modes

Rushab Rasik Karania, Tomas Maul

School of Computer Science, University of Nottingham Malaysia, Semenyih, 43500, Selangor, Malaysia

Source-Free Cross-Domain Few-Shot Learning Few-Shot Learning Few-Shot Image Classification Prototype-Based Learning Test-Time Adaptation

Open paper AskPDF arXiv

Cross-domain few-shot learning requires adapting a classifier to a new visual domain from very few labelled examples without target-time parameter updates. We isolate one question: under a fixed global representation, what does joint query-support adaptation contribute to prototype construction? The Within-Instance Prototypical Transformer (WIPT) implements single-query test-time prototype adaptation by jointly transforming one unlabelled query and the labelled support embeddings, then forming query-specific class means. Using a shared frozen ViT-S/16 encoder, miniImageNet source training, and CUB, EuroSAT and ISIC targets, we replicate the key comparisons across five independent training seeds. In 1-shot evaluation, WIPT improves frozen ProtoNet in every run on CUB (+0.21 percentage points) and EuroSAT (+2.07), but decreases ISIC (-0.22). In 5-shot evaluation, ProtoNet remains strongest overall, while WIPT consistently improves a capacity-matched support-only Transformer on ISIC (+0.99). Joint processing of up to five queries yields no reliable accuracy gain; in a head-only 5-shot benchmark, g = 5 reduces analytical attention-token pairs by 73% and peak allocated memory by 29% relative to g = 1, although latency is non-monotonic. Across all target/shot conditions, WIPT changes uncertain ProtoNet decisions far more than confident ones, and rescue/break decomposition accounts for the observed gains and losses. Source-shift and scorer controls further show that the benefit is not universal. Overall, WIPT provides a streaming-compatible form of test-time prototype adaptation that can improve difficult low-shot cross-domain decisions without target-time optimization.