Few-Shot Domain Adaptation

Follow this topic Ask about this topic

Few-shot domain adaptation studies how to transfer a model to settings where the target data differ from its training data and labels are scarce, such as new hospitals, sensors, users, or environments. Common approaches fine-tune all or part of a pretrained model, use lightweight adapters or prompts, align features with prototypes, or augment sparse examples with pseudo-labels and synthetic data. Researchers evaluate these methods on tasks including image classification, object detection, segmentation, speech, and sensor recognition, increasingly using foundation models and source-free settings where original training data are unavailable. A central tension is gaining target-domain accuracy without overfitting to a few examples or erasing useful pretrained capabilities; results also depend strongly on the type and severity of the domain shift.

Latest papers

53 papers9 papers in the last four weeks, up 80% on the four weeks before. 0.1% of all new papers.

Bridging the Data Gap: Source-Informed Task-Space Transport for Few-Shot Diffusion
Oct 22, 2026Jinjian Jiang, Jing Peng, Rehan Deen +4Diffusion Model Adaptation Few-Shot Domain Adaptation
University of Warwick · Columbia University · Independent Researcher +1
GDBA-Net: A Gated Dual-Branch Adaptation of SAM2 for Robust Cross-Domain Nuclei Segmentation
Oct 14, 2026Biplab Poudel, Betserai Albert Magarire, Anish Kumar Shah +2Histopathology Image Segmentation Medical Image Segmentation
Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211, USA · Bond Life Sciences Center, University of Missouri, Columbia, MO 65211, USA · Department of Applied Computing, Lander University, Greenwood, SC 29649, USA +2
PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation
Oct 8, 2026Heng Li, Yong Zhang, Ning Cheng +5Few-Shot Text Classification Adaptive Knowledge Distillation
Ping An Technology (Shenzhen) Co., Ltd., China · University of Science and Technology of China
AutoAdapt: Reliable Few-Shot Adaptation under Clinical Distribution Shifts
Oct 8, 2026Song Wang, Jie Peng, Davis Hobley +2Few-Shot Domain Adaptation Domain Adaptation
Foci
Few-Shot Learning for Personalised Automated Pain Assessment
Oct 7, 2026Heinke Hihn, Ibrahim Eisawy, Patrick Thiam +2Few-Shot Learning Classification
IU International University of Applied Sciences, Berlin, Germany · Institute of Neural Information Processing, Ulm University, Ulm, Germany · Institute of Medical Systems Biology, Ulm University, Ulm, Germany
EMG-FM-Bench: A Comprehensive Benchmark for Foundation Model Transfer and Adaptation on Electromyography
Oct 5, 2026Tianhao Wu, Jiawei Yu, Xiangdong Hu +8Few-Shot Domain Adaptation Neural Decoding
University of Georgia · University of Oklahoma · University of Massachusetts Amherst
From Language Priors to Field Adaptation: Preference Learning for Traversability Estimation
Oct 2, 2026Simon Schwaiger, David Seyser, Alessandro Scherl +3Robot Traversability Estimation Robot Navigation
Graz University of Technology, Institute of Software Engineering and Artificial Intelligence, Graz, Austria · University of Applied Sciences Technikum Wien, Research Group Automation Technology and Robotic Systems, Vienna, Austria · University of Alicante, Department of Computer Technology, Alicante, Spain +1
Inductive Visual Logic for Few-Shot Out-Of-Distribution Adaptation in VLMs
Sep 29, 2026Hung-Jen Chen, Yu-Heng Ho, Ting-Yao Huang +4Vision-Language Models Few-Shot Domain Adaptation
National Tsing Hua University, Hsinchu, Taiwan · National Taiwan University, Taipei, Taiwan
A Model-Agnostic Physics-Guided Adapter for Few-Shot Transfer of Coastal Flood Prediction Models to Unseen Regions
Sep 29, 2026Bilal Hassan, Areg Karapetyan, Samer MadanatFlood Inundation Mapping Few-Shot Domain Adaptation
Division of Engineering New York University Abu Dhabi Abu Dhabi, UAE
Cross-Domain Few-Shot Writer Adaptation for Real-World Handwritten Mathematical Expression Recognition
Sep 26, 2026Paulo Grane Gabriel Silva, Lorenz Bernard Marqueses, Joel IlaoHandwritten Mathematical Expression Recognition Optical Character Recognition
Department of Computer Technology De La Salle University Manila, Philippines
CSI-Agent: LLM-Assisted Few-Shot Adaptation for Cross-Domain Wi-Fi CSI Sensing
Sep 25, 2026Tianya Zhao, Chuan Liu, Xuyu WangFew-Shot Domain Adaptation Wi-Fi Sensing
Knight Foundation School of Computing and Information Sciences, Florida International University, Miami, FL 33199, US
Bridging the Synthetic-to-Real Gap for Few-Shot Cryo-ET Classification
Sep 12, 2026Siddhant Bharadwaj, Ashish Vashist, Rashi Singh +5Synthetic-to-Real Domain Adaptation Few-Shot Domain Adaptation
Columbia University · Carnegie Mellon University · National Institute of Technology Karnataka +1
Your Model Already Knows Don't Teach It, Learn to Ask It: Soft Prompting for Few-Shot Adaptation of Vision-Language Models
Sep 10, 2026Gautam Rajendrakumar Gare, Siyi Li, Hewei Wang +5Few-Shot Object Detection Few-Shot Domain Adaptation
Carnegie Mellon University · Apple
BIDETA: Brain-Inspired Data-Efficient Tactile Adaptation for Unseen Sensors
Sep 8, 2026Boheng Liu, Lan Wei, Ziyu Li +4Vision-Based Tactile Sensing Few-Shot Domain Adaptation
School of Computer Science and Technology Beijing Institute of Technology Beijing, China
Benchmarking_Fast_Domain_Adaptation_for_Unsupervised_Speech_Units
Aug 27, 2026Robin San Roman, Manel Khentout, Tu Anh Nguyen +3Few-Shot Domain Adaptation Self-Supervised Speech Representation Learning
CoML team, ENS, PSL university, CNRS, EHESS
On the Transferability of Agricultural Weed Detection Under Cross-Field Distribution Shift
Aug 21, 2026Nikhilesh Prabhakar, Pranuthi Tenali, Wilfredo Abudeye Fernandez +5Weed Detection Cross-Dataset Generalization
The University of Texas at Dallas · The University of Texas at Tyler · Air Force Research Lab
SED-FOD: Scattering-Aware Expert Decomposition for Few-Shot Cross-Sensor SAR Object Detection
Aug 19, 2026Shu Yang, Zhen Chen, Zhiyu Jiang +2Synthetic Aperture Radar Few-Shot Domain Adaptation
National Key Laboratory of Microwave Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China, and also with the School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China.
Few-Shot Cross-Dataset Adaptation for Tuberculosis Detection Using DenseNet
Aug 16, 2026Bidhan Biswas, Shahadat Hossain Sohag, Nabil Ashab +2Cross-Dataset Generalization Few-Shot Domain Adaptation
Department of Computer Science and Engineering, Dhaka International University, Dhaka, Bangladesh.
Link-adaptive digital twin for robust physical-layer modeling in hybrid-amplified ultra-wideband optical networks
Aug 11, 2026Xiaoxuan Gao, Rentao Gu, Yingchun Wang +3Neural Surrogate Modeling Few-Shot Domain Adaptation
State Key Lab of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing, 100876, China · China Mobile Group Design Institute Co., Ltd., Beijing, 100080, China
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
Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detection
Aug 2, 2026Linhai Zhuo, Junxi Cai, Tianwen Qian +2Synthetic Data Augmentation Few-Shot Domain Adaptation
Fuzhou University · East China Normal University · Xiamen University +1
Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization
Aug 1, 2026Xuefei Wang, Jun Han, Zixuan Wang +4Few-Shot Domain Adaptation LLM Personalization
Beihang University · Nankai University
DA-MergeLoRA: Hypernetwork-Based LoRA Merging for Few-Shot Test-Time Domain Adaptation
Jul 20, 2026Siobhan Reid, Zhixiang Chi, Li Gu +3Test-Time Adaptation Few-Shot Domain Adaptation
Concordia University, Montreal QC H3G 1M8, Canada · University of Toronto, Toronto ON M5S 1A1, Canada · Mila – Quebec AI Institute, Montreal QC H2S 3H1, Canada
TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models
Jul 10, 2026Tianyou Jiang, Ziyu ZhouFew-Shot Domain Adaptation Logit Adjustment
University of Bern, Bern, Switzerland · Shanghai Jiao Tong University, Shanghai, China
Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data
Jun 29, 2026Hyunwoo Park, Sang-Hyun LeeSynthetic-to-Real Domain Adaptation Few-Shot Domain Adaptation
Department of Mobility Engineering, Ajou University, Suwon, Republic of Korea
FADA: Few-Shot Domain Adaptation via Dynamics Alignment for Humanoid Control
Jun 26, 2026Angchen Xie, Nikhil Sobanbabu, Ishayu Shikhare +3Few-Shot Domain Adaptation Humanoid Robot Control
Carnegie Mellon University
Cross-Platform Chinese Offensive Comment Detection via Dual-Threshold Hard Example Mining
Jun 26, 2026Ruixing Ren, Junhui Zhao, Fangfang WangFew-Shot Domain Adaptation Domain Adaptation
School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China
An LLM-based Two-Stage Transformer Framework for Cross-Domain Bearing Fault Diagnosis with Limited Data
Jun 23, 2026Jinghan Wang, Feng Cheng, Wentao Wu +3Few-Shot Domain Adaptation Predictive Maintenance
School of Mechatronics Engineering, Harbin Institute of Technology, Harbin 150001, China
GaMi: Geometry-Agnostic Material Identification via Cross-Modal Subtractive Disentanglement
May 29, 2026Zhiwei Chen, Yijie Li, Yimo Zhang +9Few-Shot Domain Adaptation Multimodal Sensor Fusion
UESTC, Chengdu, China · UESTC Chengdu, China · National University of Singapore, Singapore +5
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.

Oct 22, 2026J/K move · Enter open · S save

Bridging the Data Gap: Source-Informed Task-Space Transport for Few-Shot Diffusion

Jinjian Jiang, Jing Peng, Rehan Deen, Yu Cao+3

University of Warwick · Columbia University · Independent Researcher+1

Diffusion Model Adaptation Few-Shot Domain Adaptation

Open paper AskPDF arXiv

Many deployments require a model to move rapidly from a data-rich source to a related target observed only sparsely. This is especially consequential where target data are difficult to collect, as in healthcare settings with persistent population or acquisition imbalances. Retraining or fine-tuning a high-capacity generator for every target is costly and can be statistically unreliable when target data are scarce. We introduce Meta-Diff, which instead learns a recurring source--target relation once in a compact task space. A shared encoder maps each distribution to a low-dimensional coordinate; a learned relation transports a new source coordinate to its predicted target, and a shared diffusion backbone generates from that prediction without target-specific retraining. Controlled Gaussian-mixture experiments identify when this works: task identity must survive the representation, the relation must generalise across tasks, and the source--target shift must leave useful headroom for transport. On held-out CIFAR-100 validation tasks, correct source

+

transport achieves 13.9% lower mean SW than transport from the wrong source. With validation-selected adaptation settings in the final-test one-target comparison, its mean SW is 14.7% lower than target-only modelling and 32.7% lower than full fine-tuning; the main route itself uses no target image and assumes the applicable relation is known. On matched CIFAR test episodes, generating from the clean-source coordinate and then applying the known corruption yields lower SW than task-space transport. Office-Home exposes a complementary boundary: transport can align target-domain statistics without reliable object identity. Together, these results recast extreme-few-shot adaptation as reusable transport in task space, while making the conditions for its success and failure directly measurable.