paper-with-me

Papers

Spatial Contrastive Learning for Few-Shot Classification

2020-12-26 · Yassine Ouali, Céline Hudelot, Myriam Tami

In this paper, we explore contrastive learning for few-shot classification, in which we propose to use it as an additional auxiliary training objective acting as a data-dependent regularizer to promote more general and transferable features. In particular, we present a novel attention-based spatial contrastive objective to learn locally discriminative and class-agnostic features. As a result, our approach overcomes some of the limitations of the cross-entropy loss, such as its excessive discrimination towards seen classes, which reduces the transferability of features to unseen classes. With extensive experiments, we show that the proposed method outperforms state-of-the-art approaches, confirming the importance of learning good and transferable embeddings for few-shot learning.

📄 PDF Abstract BibTeX arXiv:2012.13831

Code (1)

yassouali/SCL 공식 구현 pytorch

Tasks

ClassificationContrastive LearningFew-Shot LearningGeneral Classification

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

S3Net: Spectral–Spatial Siamese Network for Few-Shot Hyperspectral Image Classification

2022-06-08

Deep learning (DL) has shown great potential for hyperspectral image (HSI) classification due to its powerful ability of nonlinear modeling and end-to-end optimization. However, DL models easily get trapped into overfitt…

ClassificationHyperspectral Image Classificationimage-classificationImage Classification

FLAVARS: A Multimodal Foundational Language and Vision Alignment Model for Remote Sensing

2025-01-14 · Isaac Corley, Simone Fobi Nsutezo, Anthony Ortiz, Caleb Robinson 외

Remote sensing imagery is dense with objects and contextual visual information. There is a recent trend to combine paired satellite images and text captions for pretraining performant encoders for downstream tasks. Howev…

ClassificationContrastive LearningSemantic Segmentationzero-shot-classification+1

Dual Contrastive Network for Few-Shot Remote Sensing Image Scene Classification

2026-03-24 · Zhong Ji, Liyuan Hou, Xuan Wang, Gang Wang 외 arxiv

Few-shot remote sensing image scene classification (FS-RSISC) aims at classifying remote sensing images with only a few labeled samples. The main challenges lie in small inter-class variances and large intra-class varian…

Scene ClassificationContrastive Learning

SCENEFORGE: Enhancing 3D-text alignment with Structured Scene Compositions

2025-09-19 · Cristian Sbrolli, Matteo Matteucci arxiv

The whole is greater than the sum of its parts-even in 3D-text contrastive learning. We introduce SceneForge, a novel framework that enhances contrastive alignment between 3D point clouds and text through structured mult…

Visual Question AnsweringContrastive LearningSpatial ReasoningPoint Clouds

PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification

2023-05-24 · Yau-Shian Wang, Ta-Chung Chi, Ruohong Zhang, Yiming Yang

We present PESCO, a novel contrastive learning framework that substantially improves the performance of zero-shot text classification. We formulate text classification as a neural text matching problem where each documen…

ClassificationContrastive Learningtext-classificationText Classification+2