# Harnessing the Power of Local Representations for Few-Shot Classification

arXiv: https://arxiv.org/abs/2407.01967 · HTML: https://mlsanity.com/paper/2407.01967/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 58 references that are in the map.
- First posted on arXiv 2 Jul 2024.

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [A Comprehensive Overhaul of Feature Distillation](https://mlsanity.com/paper/1904.01866/) (2019)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions](https://mlsanity.com/paper/1812.03664/) (2018)
- [Paraphrasing Complex Network: Network Compression via Factor Transfer](https://mlsanity.com/paper/1802.04977/) (2018)
- [Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning](https://mlsanity.com/paper/2003.04390/) (2020)
- [Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference](https://mlsanity.com/paper/2204.07305/) (2022)
- [Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning](https://mlsanity.com/paper/1903.12290/) (2019)
- [Few-Shot Classification with Feature Map Reconstruction Networks](https://mlsanity.com/paper/2012.01506/) (2020)
- [Interventional Few-Shot Learning](https://mlsanity.com/paper/2009.13000/) (2020)
- [Delta-encoder: an effective sample synthesis method for few-shot object recognition](https://mlsanity.com/paper/1806.04734/) (2018)
- [Self-Distillation as Instance-Specific Label Smoothing](https://mlsanity.com/paper/2006.05065/) (2020)
- [Associative Alignment for Few-shot Image Classification](https://mlsanity.com/paper/1912.05094/) (2019)
- [Few-Shot Learning Through an Information Retrieval Lens](https://mlsanity.com/paper/1707.02610/) (2017)
- [DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning](https://mlsanity.com/paper/2003.06777/) (2020)
- [Partner-Assisted Learning for Few-Shot Image Classification](https://mlsanity.com/paper/2109.07607/) (2021)

## Built on by (most cited first, 1 of 1)

- [Adaptive receptive field-based spatial-frequency feature reconstruction network for fine-grained few-shot image classification](https://mlsanity.com/paper/2604.16936/) (2026)

## Abstract (arXiv)

Generalizing to novel classes unseen during training is a key challenge of few-shot classification. Recent metric-based methods try to address this by local representations. However, they are unable to take full advantage of them due to (i) improper supervision for pretraining the feature extractor, and (ii) lack of adaptability in the metric for handling various possible compositions of local feature sets. In this work, we harness the power of local representations in improving novel-class generalization. For the feature extractor, we design a novel pretraining paradigm that learns randomly cropped patches by soft labels. It utilizes the class-level diversity of patches while diminishing the impact of their semantic misalignments to hard labels. To align network output with soft labels, we also propose a UniCon KL-Divergence that emphasizes the equal contribution of each base class in describing "non-base" patches. For the metric, we formulate measuring local feature sets as an entropy-regularized optimal transport problem to introduce the ability to handle sets consisting of homogeneous elements. Furthermore, we design a Modulate Module to endow the metric with the necessary adaptability. Our method achieves new state-of-the-art performance on three popular benchmarks. Moreover, it exceeds state-of-the-art transductive and cross-modal methods in the fine-grained scenario.