paper-with-me

Papers

Rethinking Generalization in Few-Shot Classification

2022-06-15 · Markus Hiller, Rongkai Ma, Mehrtash Harandi, Tom Drummond

Single image-level annotations only correctly describe an often small subset of an image's content, particularly when complex real-world scenes are depicted. While this might be acceptable in many classification scenarios, it poses a significant challenge for applications where the set of classes differs significantly between training and test time. In this paper, we take a closer look at the implications in the context of $\textit{few-shot learning}$. Splitting the input samples into patches and encoding these via the help of Vision Transformers allows us to establish semantic correspondences between local regions across images and independent of their respective class. The most informative patch embeddings for the task at hand are then determined as a function of the support set via online optimization at inference time, additionally providing visual interpretability of `$\textit{what matters most}$' in the image. We build on recent advances in unsupervised training of networks via masked image modelling to overcome the lack of fine-grained labels and learn the more general statistical structure of the data while avoiding negative image-level annotation influence, $\textit{aka}$ supervision collapse. Experimental results show the competitiveness of our approach, achieving new state-of-the-art results on four popular few-shot classification benchmarks for $5$-shot and $1$-shot scenarios.

📄 PDF Abstract BibTeX arXiv:2206.07267

Code (1)

mrkshllr/FewTURE 공식 구현 pytorch

Tasks

ClassificationFew-Shot Image ClassificationFew-Shot Learning

Methods 이 논문이 사용한 방법론

Test 설명 없음
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Swin Transformer 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Multi-Head Attention 설명 없음
Attention 설명 없음

Similar Papers 제목 키워드 기반

Rethinking Domain Adaptation and Generalization in the Era of CLIP

2024-07-21 · Ruoyu Feng, Tao Yu, Xin Jin, Xiaoyuan Yu 외

In recent studies on domain adaptation, significant emphasis has been placed on the advancement of learning shared knowledge from a source domain to a target domain. Recently, the large vision-language pre-trained model,…

Domain AdaptationZero-Shot Learning

Rethinking Few Shot CLIP Benchmarks: A Critical Analysis in the Inductive Setting

2025-07-28 · Alexey Kravets, Da Chen, Vinay P. Namboodiri arxiv

CLIP is a foundational model with transferable classification performance in the few-shot setting. Several methods have shown improved performance of CLIP using few-shot examples. However, so far, all these techniques ha…

Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy

2025-09-16 · Yunchuan Guan, Yu Liu, Ke Zhou, Zhiqi Shen 외 arxiv

Meta-learning is a powerful paradigm for tackling few-shot tasks. However, recent studies indicate that models trained with the whole-class training strategy can achieve comparable performance to those trained with meta-…

Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?

2020-03-25 · ECCV 2020 8 · Yonglong Tian, Yue Wang, Dilip Krishnan, Joshua B. Tenenbaum 외

The focus of recent meta-learning research has been on the development of learning algorithms that can quickly adapt to test time tasks with limited data and low computational cost. Few-shot learning is widely used as on…

AllFew-Shot Image ClassificationFew-Shot LearningGeneral Classification+3

Text Augmented Correlation Transformer For Few-shot Classification & Segmentation

2025-01-01 · CVPR 2025 1 · Srinivasa Rao Nandam, Sara Atito, ZhenHua Feng, Josef Kittler 외

Foundation models like CLIP and ALIGN have transformed few-shot and zero-shot vision applications by fusing visual and textual data, yet the integrative few-shot classification and segmentation (FS-CS) task primarily…

Few-Shot Classification and SegmentationFew-Shot LearningSegmentation