mlsanityData to 14 Oct 2026

LDCA: Local Descriptors with Contextual Augmentation for Few-Shot Learning

arXiv 2401.13499 ↗First posted 24 Jan 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Few-shot image classification has emerged as a key challenge in the field of computer vision, highlighting the capability to rapidly adapt to new tasks with minimal labeled data. Existing methods predominantly rely on image-level features or local descriptors, often overlooking the holistic context surrounding these descriptors. In this work, we introduce a novel approach termed "Local Descriptor with Contextual Augmentation (LDCA)". Specifically, this method bridges the gap between local and global understanding uniquely by leveraging an adaptive global contextual enhancement module. This module incorporates a visual transformer, endowing local descriptors with contextual awareness capabilities, ranging from broad global perspectives to intricate surrounding nuances. By doing so, LDCA transcends traditional descriptor-based approaches, ensuring each local feature is interpreted within its larger visual narrative. Extensive experiments underscore the efficacy of our method, showing a maximal absolute improvement of 20% over the next-best on fine-grained classification datasets, thus demonstrating significant advancements in few-shot classification tasks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 59 references that are in the map. First posted on arXiv 24 Jan 2024.

Builds on

42 of 59 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020End-to-End Object Detection with Transformerscited by 7,414
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  6. 2016Pyramid Scene Parsing Networkcited by 2,479
  7. 2017Non-local Neural Networkscited by 2,293
  8. 2016Matching Networks for One Shot Learningcited by 2,255
  9. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  10. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  11. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  12. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 576
30 more
  1. 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
  2. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  3. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  4. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  5. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  6. 2019YOLACT: Real-time Instance Segmentationcited by 443
  7. 2018Meta-learning with differentiable closed-form solverscited by 397
  8. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
  9. 2020Visual Transformers: Token-based Image Representation and Processing for Computer Visioncited by 334
  10. 2020Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentationcited by 326
  11. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  12. 2018Context Encoding for Semantic Segmentationcited by 290
  13. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 211
  14. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  15. 2018A2-Nets: Double Attention Networkscited by 136
  16. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  17. 2020Context Prior for Scene Segmentationcited by 121
  18. 2020Strip Pooling: Rethinking Spatial Pooling for Scene Parsingcited by 114
  19. 2020Feature Pyramid Transformercited by 96
  20. 2020Meta-Learning with Adaptive Hyperparameterscited by 79
  21. 2019Transductive Episodic-Wise Adaptive Metric for Few-Shot Learningcited by 67
  22. 2018Memory Matching Networks for One-Shot Image Recognitioncited by 65
  23. 2019Few-Shot Learning with Embedded Class Models and Shot-Free Meta Trainingcited by 57
  24. 2022HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learningcited by 55
  25. 2017Few-Shot Learning Through an Information Retrieval Lenscited by 51
  26. 2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
  27. 2018Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examplescited by 27
  28. 2019Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learningcited by 4
  29. 2022Kernel Relative-prototype Spectral Filtering for Few-shot Learningcited by 4
  30. 2023Learning More Discriminative Local Descriptors for Few-shot Learningcited by 2

Built on by

Not cited yet.