mlsanityData to 14 Oct 2026

Partner-Assisted Learning for Few-Shot Image Classification

arXiv 2109.07607 ↗First posted 15 Sep 2021cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

Few-shot Learning has been studied to mimic human visual capabilities and learn effective models without the need of exhaustive human annotation. Even though the idea of meta-learning for adaptation has dominated the few-shot learning methods, how to train a feature extractor is still a challenge. In this paper, we focus on the design of training strategy to obtain an elemental representation such that the prototype of each novel class can be estimated from a few labeled samples. We propose a two-stage training scheme, Partner-Assisted Learning (PAL), which first trains a partner encoder to model pair-wise similarities and extract features serving as soft-anchors, and then trains a main encoder by aligning its outputs with soft-anchors while attempting to maximize classification performance. Two alignment constraints from logit-level and feature-level are designed individually. For each few-shot task, we perform prototype classification. Our method consistently outperforms the state-of-the-art method on four benchmarks. Detailed ablation studies of PAL are provided to justify the selection of each component involved in training.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Builds on 42 of its 65 references that are in the map. First posted on arXiv 15 Sep 2021.

Builds on

42 of 65 references.

References · 42

  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. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2017Mask R-CNNcited by 7,277
  8. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  9. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  10. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  11. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  12. 2017Prototypical Networks for Few-shot Learningcited by 3,015
30 more
  1. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  2. 2020Supervised Contrastive Learningcited by 2,829
  3. 2016Matching Networks for One Shot Learningcited by 2,255
  4. 2013Describing Textures in the Wildcited by 2,125
  5. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  6. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  8. 2017Deep Mutual Learningcited by 628
  9. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  10. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  11. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  12. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  13. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  14. 2018Meta-learning with differentiable closed-form solverscited by 397
  15. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  16. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 315
  17. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  18. 2019A Baseline for Few-Shot Image Classificationcited by 298
  19. 2016Large-Margin Softmax Loss for Convolutional Neural Networkscited by 296
  20. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  21. 2020Boosting Few-Shot Learning With Adaptive Margin Losscited by 83
  22. 2019Diversity with Cooperation: Ensemble Methods for Few-Shot Classificationcited by 70
  23. 2019Transductive Episodic-Wise Adaptive Metric for Few-Shot Learningcited by 67
  24. 2017Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networkscited by 66
  25. 2019Associative Alignment for Few-shot Image Classificationcited by 58
  26. 2019Few-Shot Learning with Embedded Class Models and Shot-Free Meta Trainingcited by 57
  27. 2021Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignmentcited by 57
  28. 2018Ring loss: Convex Feature Normalization for Face Recognitioncited by 39
  29. 2018Rethinking Feature Distribution for Loss Functions in Image Classificationcited by 39
  30. 2020MUSCLE: Strengthening Semi-Supervised Learning Via Concurrent Unsupervised Learning Using Mutual Information Maximizationcited by 4

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 17; 2023: 9; 2024: 6; 2025: 3.

36 papers.

Sort:

By area:

  1. 2022Few-Shot Object Detection with Fully Cross-Transformercited by 64
  2. 2021Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networkscited by 55
  3. 2022Rethinking Generalization in Few-Shot Classificationcited by 36
  4. 2022Few-Shot Classification with Contrastive Learningcited by 31
  5. 2022Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learningcited by 27
  6. 2023Supervised Masked Knowledge Distillation for Few-Shot Transformerscited by 23
  7. 2024MoDE: CLIP Data Experts via Clusteringcited by 22
  8. 2023DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detectioncited by 21
  9. 2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20
  10. 2022EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredientscited by 16
  11. 2022TempCLR: Temporal Alignment Representation with Contrastive Learningcited by 15
  12. 2022Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detectioncited by 14
24 more
  1. 2022Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Promptingcited by 11
  2. 2022Cap2Aug: Caption guided Image to Image data Augmentationcited by 10
  3. 2023MalProtect: Stateful Defense Against Adversarial Query Attacks in ML-based Malware Detectioncited by 8
  4. 2022Transductive Decoupled Variational Inference for Few-Shot Classificationcited by 7
  5. 2022RankDNN: Learning to Rank for Few-shot Learningcited by 7
  6. 2023Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognitioncited by 6
  7. 2023The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentationcited by 5
  8. 2022StratDef: Strategic Defense Against Adversarial Attacks in ML-based Malware Detectioncited by 3
  9. 2023Few-shot Classification via Ensemble Learning with Multi-Order Statisticscited by 3
  10. 2023Towards Robust Few-shot Point Cloud Semantic Segmentationcited by 3
  11. 2023Disentangled Representation Learning with Transmitted Information Bottleneckcited by 3
  12. 2024Robust Few-Shot Ensemble Learning with Focal Diversity-Based Pruningcited by 3
  13. 2022A Statistical Model for Predicting Generalization in Few-Shot Classificationcited by 2
  14. 2022Bayesian Evidential Learning for Few-Shot Classificationcited by 1
  15. 2022BaseTransformers: Attention over base data-points for One Shot Learningcited by 1
  16. 2022Disentangled Generation with Information Bottleneck for Few-Shot Learningcited by 1
  17. 2024Intra-task Mutual Attention based Vision Transformer for Few-Shot Learningcited by 1
  18. 2024Class-relevant Patch Embedding Selection for Few-Shot Image Classificationcited by 1
  19. 2024Harnessing the Power of Local Representations for Few-Shot Classificationcited by 1
  20. 2023Disambiguation of One-Shot Visual Classification Tasks: A Simplex-Based Approachcited by 0
  21. 2024Siamese Transformer Networks for Few-shot Image Classificationcited by 0
  22. 2025Enhancing Environmental Robustness in Few-shot Learning via Conditional Representation Learningcited by 0
  23. 2025Color as the Impetus: Transforming Few-Shot Learnercited by 0
  24. 2025Element2Vec: Build Chemical Element Representation from Text for Property Predictioncited by 0