P3DC-Shot: Prior-Driven Discrete Data Calibration for Nearest-Neighbor Few-Shot Classification
Not on the map. Why?
Abstract (arXiv)
Nearest-Neighbor (NN) classification has been proven as a simple and effective approach for few-shot learning. The query data can be classified efficiently by finding the nearest support class based on features extracted by pretrained deep models. However, NN-based methods are sensitive to the data distribution and may produce false prediction if the samples in the support set happen to lie around the distribution boundary of different classes. To solve this issue, we present P3DC-Shot, an improved nearest-neighbor based few-shot classification method empowered by prior-driven data calibration. Inspired by the distribution calibration technique which utilizes the distribution or statistics of the base classes to calibrate the data for few-shot tasks, we propose a novel discrete data calibration operation which is more suitable for NN-based few-shot classification. Specifically, we treat the prototypes representing each base class as priors and calibrate each support data based on its similarity to different base prototypes. Then, we perform NN classification using these discretely calibrated support data. Results from extensive experiments on various datasets show our efficient non-learning based method can outperform or at least comparable to SOTA methods which need additional learning steps.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 52 of its 71 references that are in the map. First posted on arXiv 2 Jan 2023.
Builds on
52 of 71 references.
References · 52
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2017Mask R-CNNcited by 7,259
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
38 more
- 2016Wide Residual Networkscited by 3,057
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2015Fast R-CNNcited by 2,930
- 2021Learning to Prompt for Vision-Language Modelscited by 2,269
- 2016Matching Networks for One Shot Learningcited by 2,246
- 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
- 2019A Comprehensive Survey on Transfer Learningcited by 1,154
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
- 2020Meta-Learning in Neural Networks: A Surveycited by 944
- 2019A Closer Look at Few-shot Classificationcited by 679
- 2018Meta-Learning with Latent Embedding Optimizationcited by 476
- 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
- 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
- 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
- 2018A Survey on Deep Transfer Learningcited by 417
- 2019A Baseline for Few-Shot Image Classificationcited by 298
- 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
- 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
- 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
- 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
- 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
- 2020More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classificationcited by 126
- 2022UIU-Net: U-Net in U-Net for Infrared Small Object Detectioncited by 124
- 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
- 2020Graph Convolutional Networks for Hyperspectral Image Classificationcited by 113
- 2019Prototype Rectification for Few-Shot Learningcited by 96
- 2018An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixingcited by 65
- 2017Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuningcited by 48
- 2019A Theoretical Analysis of the Number of Shots in Few-Shot Learningcited by 39
- 2021A Survey of Self-Supervised and Few-Shot Object Detectioncited by 35
- 2022Memorizing Complementation Network for Few-Shot Class-Incremental Learningcited by 30
- 2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20
- 2020One-Shot Image Classification by Learning to Restore Prototypescited by 14
- 2020Learning to Select Base Classes for Few-shot Classificationcited by 11
- 2020Impact of base dataset design on few-shot image classificationcited by 9
- 2021DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Networkcited by 9
- 2021Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learningcited by 6
50 most cited of 52 All 52 (JSON)
Built on by
Citing papers per year: 2023: 1.
1 paper.