paper-with-me

Papers

Class-relevant Patch Embedding Selection for Few-Shot Image Classification

2024-05-06 · Weihao Jiang, Haoyang Cui, Kun He

Effective image classification hinges on discerning relevant features from both foreground and background ele- ments, with the foreground typically holding the critical informa- tion. While humans adeptly classify images with limited exposure, artificial neural networks often struggle with feature selection from rare samples. To address this challenge, we propose a novel method for selecting class-relevant patch embeddings. Our ap- proach involves splitting support and query images into patches, encoding them using a pre-trained Vision Transformer (ViT) to obtain class embeddings and patch embeddings, respectively. Subsequently, we filter patch embeddings using class embeddings to retain only the class-relevant ones. For each image, we calculate the similarity between class embedding and each patch embed- ding, sort the similarity sequence in descending order, and only retain top-ranked patch embeddings. By prioritizing similarity between the class embedding and patch embeddings, we select top-ranked patch embeddings to be fused with class embedding to form a comprehensive image representation, enhancing pattern recognition across instances. Our strategy effectively mitigates the impact of class-irrelevant patch embeddings, yielding improved performance in pre-trained models. Extensive experiments on popular few-shot classification benchmarks demonstrate the sim- plicity, efficacy, and computational efficiency of our approach, outperforming state-of-the-art baselines under both 5-shot and 1-shot scenarios.

📄 PDF Abstract BibTeX arXiv:2405.03722

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiencyfeature selectionFew-Shot Image Classificationimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음
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 $x$…
Position-Wise Feed-Forward Layer 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Class-Aware Patch Embedding Adaptation for Few-Shot Image Classification

2023-01-01 · ICCV 2023 1 · Fusheng Hao, Fengxiang He, Liu Liu, Fuxiang Wu 외

"A picture is worth a thousand words", significantly beyond mere a categorization. Accompanied by that, many patches of the image could have completely irrelevant meanings with the categorization if they were indepen…

Few-Shot Image ClassificationFew-Shot Learningimage-classificationImage Classification

Leveraging Vision-Language Embeddings for Zero-Shot Learning in Histopathology Images

2025-03-13 · Md Mamunur Rahaman, Ewan K. A. Millar, Erik Meijering

Zero-shot learning holds tremendous potential for histopathology image analysis by enabling models to generalize to unseen classes without extensive labeled data. Recent advancements in vision-language models (VLMs) have…

Diagnosticimage-classificationImage Classificationzero-shot-classification+1

Stochastic-based Patch Filtering for Few-Shot Learning

2025-08-13 · Javier Rodenas, Eduardo Aguilar, Petia Radeva arxiv

Food images present unique challenges for few-shot learning models due to their visual complexity and variability. For instance, a pasta dish might appear with various garnishes on different plates and in diverse lightin…

Few-Shot Learning

Soft Head Selection for Injecting ICL-Derived Task Embeddings

2025-07-28 · Jungwon Park, Jimyeong Kim, Changin Choi, Wonjong Rhee arxiv

Large language models (LLMs) are commonly adapted to downstream tasks using parameter-efficient fine-tuning (PEFT) or in-context learning (ICL). Recently, ICL-driven embedding-based adaptation has been proposed as a dist…

parameter-efficient fine-tuningNatural Language Understanding

A Two-Fold Patch Selection Approach for Improved 360-Degree Image Quality Assessment

2024-12-17 · Abderrezzaq Sendjasni, Seif-Eddine Benkabou, Mohamed-Chaker Larabi

This article presents a novel approach to improving the accuracy of 360-degree perceptual image quality assessment (IQA) through a two-fold patch selection process. Our methodology combines visual patch selection with em…

Image Quality Assessment