mlsanityData to 14 Oct 2026

Cross-domain Few-shot Learning with Task-specific Adapters

arXiv 2107.00358 ↗First posted 1 Jul 2021cs.CVcited by 80

Not on the map. Why?

Abstract (arXiv)

In this paper, we look at the problem of cross-domain few-shot classification that aims to learn a classifier from previously unseen classes and domains with few labeled samples. Recent approaches broadly solve this problem by parameterizing their few-shot classifiers with task-agnostic and task-specific weights where the former is typically learned on a large training set and the latter is dynamically predicted through an auxiliary network conditioned on a small support set. In this work, we focus on the estimation of the latter, and propose to learn task-specific weights from scratch directly on a small support set, in contrast to dynamically estimating them. In particular, through systematic analysis, we show that task-specific weights through parametric adapters in matrix form with residual connections to multiple intermediate layers of a backbone network significantly improves the performance of the state-of-the-art models in the Meta-Dataset benchmark with minor additional cost.

Key facts. Cited by 80 papers in the map (data through 14 Oct 2026). Builds on 33 of its 52 references that are in the map. First posted on arXiv 1 Jul 2021.

Builds on

33 of 52 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  7. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  8. 2016Matching Networks for One Shot Learningcited by 2,255
  9. 2013Describing Textures in the Wildcited by 2,125
  10. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  11. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  12. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 834
21 more
  1. 2017Learning multiple visual domains with residual adapterscited by 557
  2. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  3. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  4. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  5. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  6. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  7. 2016Dynamic Filter Networkscited by 319
  8. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 315
  9. 2019A Baseline for Few-Shot Image Classificationcited by 298
  10. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  11. 2018Efficient parametrization of multi-domain deep neural networkscited by 168
  12. 2019Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processescited by 131
  13. 2019Improved Few-Shot Visual Classificationcited by 115
  14. 2016Learning feed-forward one-shot learnerscited by 93
  15. 2020A Universal Representation Transformer Layer for Few-Shot Image Classificationcited by 65
  16. 2021Learning a Universal Template for Few-shot Dataset Generalizationcited by 61
  17. 2021Universal Representation Learning from Multiple Domains for Few-shot Classificationcited by 56
  18. 2017Universal representations:The missing link between faces, text, planktons, and cat breedscited by 45
  19. 2020Enhancing Few-Shot Image Classification with Unlabelled Examplescited by 32
  20. 2020Cross-Domain Few-Shot Learning by Representation Fusioncited by 32
  21. 2020Optimized Generic Feature Learning for Few-shot Classification across Domainscited by 23

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 11; 2023: 27; 2024: 22; 2025: 13; 2026: 7.

80 papers.

Sort:

By area:

  1. 2023Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunitycited by 56
  2. 2023A Closer Look at Few-shot Classification Againcited by 46
  3. 2023Strong Baselines for Parameter Efficient Few-Shot Fine-tuningcited by 37
  4. 2024How to build the best medical image segmentation algorithm using foundation models: a comprehensive empirical study with Segment Anything Modelcited by 32
  5. 2023Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classificationcited by 30
  6. 2023Lossless Adaptation of Pretrained Vision Models For Robotic Manipulationcited by 29
  7. 2024Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentationcited by 22
  8. 2022Channel Importance Matters in Few-Shot Image Classificationcited by 20
  9. 2023TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edgecited by 18
  10. 2025Reliable Few-shot Learning under Dual Noisescited by 17
  11. 2023Exploring Efficient Few-shot Adaptation for Vision Transformerscited by 16
  12. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
38 more
  1. 2024Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognitioncited by 14
  2. 2022Continual Learning with Evolving Class Ontologiescited by 13
  3. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  4. 2024A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Modelscited by 13
  5. 2022Universal Deep Image Compression via Content-Adaptive Optimization with Adapterscited by 11
  6. 2023Meta-Learning with a Geometry-Adaptive Preconditionercited by 11
  7. 2023Learning to Drive Anywherecited by 10
  8. 2023Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancementcited by 10
  9. 2024Expanding Sparse Tuning for Low Memory Usagecited by 10
  10. 2024Exploring Cross-Domain Few-Shot Classification via Frequency-Aware Promptingcited by 9
  11. 2023Episodic Multi-Task Learning with Heterogeneous Neural Processescited by 8
  12. 2023Taxonomy Adaptive Cross-Domain Adaptation in Medical Imaging via Optimization Trajectory Distillationcited by 7
  13. 2024Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learningcited by 7
  14. 2022Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classificationcited by 6
  15. 2022Federated Learning for Inference at Anytime and Anywherecited by 6
  16. 2023How Will It Drape Like? Capturing Fabric Mechanics from Depth Imagescited by 6
  17. 2023Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalizationcited by 6
  18. 2025OSLoPrompt: Bridging Low-Supervision Challenges and Open-Set Domain Generalization in CLIPcited by 6
  19. 2023Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapterscited by 5
  20. 2023Improved Region Proposal Network for Enhanced Few-Shot Object Detectioncited by 5
  21. 2024MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlationcited by 5
  22. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  23. 2025Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigationcited by 5
  24. 2022Cross-Domain Few-Shot Classification via Inter-Source Stylizationcited by 4
  25. 2022Schedule-Robust Online Continual Learningcited by 4
  26. 2023DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learningcited by 4
  27. 2023Neural Fine-Tuning Search for Few-Shot Learningcited by 4
  28. 2024MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependencecited by 4
  29. 2024DiffCLIP: Few-shot Language-driven Multimodal Classifiercited by 4
  30. 2022NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline resultscited by 3
  31. 2023A Survey of Deep Visual Cross-Domain Few-Shot Learningcited by 3
  32. 2023Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learningcited by 3
  33. 2024Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Expertscited by 3
  34. 2024OUCopula: Bi-Channel Multi-Label Copula-Enhanced Adapter-Based CNN for Myopia Screening Based on OU-UWF Imagescited by 3
  35. 2024Mind the Gap Between Prototypes and Images in Cross-domain Finetuningcited by 3
  36. 2022Feature Extractor Stacking for Cross-domain Few-shot Learningcited by 2
  37. 2022Robust Meta-Representation Learning via Global Label Inference and Classificationcited by 2
  38. 2024Understanding the Cross-Domain Capabilities of Video-Based Few-Shot Action Recognition Modelscited by 2

50 most cited of 80 All 80 (JSON)