paper-with-me

Papers Few-Shot Image Classification

“Few-Shot Image Classification” 태그가 달린 논문 367편 · 필터 해제

Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners

2026-06-30 · Yunhan Wang, Eshika Khandelwal, Edson Araujo, Walid Bousselham 외 arxiv

Multimodal Large Language Models (MLLMs) have demonstrated remarkable abilities when analyzing images, yet translating these capabilities to few-shot image classification remains challenging. To bridge this gap, we prese…

Few-Shot Image Classification

Hippocampus-DETR: An Explicit Memory Object Detection Framework Based on Hippocampus Modeling

2026-06-26 · Zhaoning Shi, Bo Ma, Hao Xu, Zepeng Yang 외 arxiv

This paper addresses the lack of explicit memory mechanisms in current object detection models and proposes Hippocampus-DETR, a novel detection framework based on biological hippocampal memory modeling. This framework in…

Few-Shot Image ClassificationNovel Object DetectionImage Restoration

MAIL++: Multi-Modal Bi-directional Agent Layer for Vision-Language Models

2026-05-25 · Kaixiang Chen, Pengfei Fang, Hui Xue arxiv

Adapting large vision-language models (VLMs) such as CLIP to downstream tasks remains challenging, as full fine-tuning is computationally prohibitive and prone to overfitting in low-data regimes. Parameter-efficient fine…

parameter-efficient fine-tuningFew-Shot Image ClassificationComputational Efficiency

A$_3$B$_2$: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning

2026-05-13 · Yiyun Zhou, Zhonghua Jiang, Wenkang Han, Kunxi Li 외 arxiv

Efficient transfer learning methods for large-scale vision-language models ($e.g.$, CLIP) enable strong few-shot transfer, yet existing adaptation methods follow a fixed fine-tuning paradigm that implicitly assumes a uni…

Few-Shot Image ClassificationFew-Shot LearningTransfer Learning

SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification

2026-05-13 · Giries Abu Ayoub, Morad Tukan, Loay Mualem arxiv

Few-shot classification (FSC) is widely used for learning from limited labeled data, yet most evaluations implicitly assume that target concepts are independent of contextual cues. In real-world settings, however, exampl…

Few-Shot Image ClassificationFew-Shot Audio Classification

Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification

2026-03-25 · Dipam Goswami, Simone Magistri, Gido M. van de Ven, Bartłomiej Twardowski 외 arxiv

Vision-language models (VLMs) like CLIP are trained with the objective of aligning text and image pairs. To improve CLIP-based few-shot image classification, recent works have observed that, along with text embeddings, i…

Few-Shot Image Classification

Semi-Supervised Few-Shot Adaptation of Vision-Language Models

2026-03-03 · Julio Silva-Rodríguez, Ender Konukoglu arxiv

Vision-language models (VLMs) pre-trained on large, heterogeneous data sources are becoming increasingly popular, providing rich multi-modal embeddings that enable efficient transfer to new tasks. A particularly relevant…

Few-Shot Image Classification

Adapting Multimodal Foundation Models for Few-Shot Learning: A Comprehensive Study on Contrastive Captioners

2025-12-14 · N. K. B. M. P. K. B. Narasinghe, Uthayasanker Thayasivam arxiv

Large-scale multimodal foundation models, particularly Contrastive Captioners (CoCa), have achieved state-of-the-art results by unifying contrastive alignment with generative captioning. While zero-shot transfer capabili…

parameter-efficient fine-tuningFew-Shot Image ClassificationFew-Shot LearningData Augmentation

Advancing Cache-Based Few-Shot Classification via Patch-Driven Relational Gated Graph Attention

2025-12-13 · Tasweer Ahmad, Arindam Sikdar, Sandip Pradhan, Ardhendu Behera arxiv

Few-shot image classification remains difficult under limited supervision and visual domain shift. Recent cache-based adaptation approaches (e.g., Tip-Adapter) address this challenge to some extent by learning lightweigh…

Few-Shot Image Classification

Training-Free Synthetic Data Generation with Dual IP-Adapter Guidance

2025-09-26 · Luc Boudier, Loris Manganelli, Eleftherios Tsonis, Nicolas Dufour 외 arxiv

Few-shot image classification remains challenging due to the limited availability of labeled examples. Recent approaches have explored generating synthetic training data using text-to-image diffusion models, but often re…

Few-Shot Image ClassificationImage-to-Image TranslationSynthetic Data Generation

Dual-View Alignment Learning with Hierarchical-Prompt for Class-Imbalance Multi-Label Classification

2025-09-22 · Sheng Huang, Jiexuan Yan, Beiyan Liu, Bo Liu 외 arxiv

Real-world datasets often exhibit class imbalance across multiple categories, manifesting as long-tailed distributions and few-shot scenarios. This is especially challenging in Class-Imbalanced Multi-Label Image Classifi…

Multi-Label Image ClassificationFew-Shot Image ClassificationMulti-Label ClassificationObject Recognition

Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning

2025-08-18 · Dexia Chen, Qianjie Zhu, Weibing Li, Yue Yu 외 arxiv

Pretrained vision-language models (VLMs), such as CLIP, have shown remarkable potential in few-shot image classification and led to numerous effective transfer learning strategies. These methods leverage the pretrained k…

Few-Shot Image ClassificationFew-Shot LearningTransfer LearningDomain Adaptation

Object-Centric Cropping for Visual Few-Shot Classification

2025-07-31 · Aymane Abdali, Bartosz Boguslawski, Lucas Drumetz, Vincent Gripon arxiv

In the domain of Few-Shot Image Classification, operating with as little as one example per class, the presence of image ambiguities stemming from multiple objects or complex backgrounds can significantly deteriorate per…

Few-Shot Image Classification

ProtoConNet: Prototypical Augmentation and Alignment for Open-Set Few-Shot Image Classification

2025-07-16 · Kexuan Shi, Zhuang Qi, Jingjing Zhu, Lei Meng 외 arxiv

Open-set few-shot image classification aims to train models using a small amount of labeled data, enabling them to achieve good generalization when confronted with unknown environments. Existing methods mainly use visual…

Few-Shot Image ClassificationRepresentation Learning

ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark Evaluation

2025-07-12 · Abdulvahap Mutlu, Şengül Doğan, Türker Tuncer

The remarkable representational power of Vision Transformers (ViTs) remains underutilized in few-shot image classification. In this work, we introduce ViT-ProtoNet, which integrates a ViT-Small backbone into the Prototyp…

Few-Shot Image Classificationimage-classificationImage Classification

Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts

2025-06-05 · Zhong Ji, Rongshuai Wei, Jingren Liu, Yanwei Pang 외

Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable, but they often struggle in data-scarce settings where insufficient training samp…

Explainable ModelsFew-Shot Image Classificationimage-classificationImage Classification

Provably Improving Generalization of Few-Shot Models with Synthetic Data

2025-05-30 · Lan-Cuong Nguyen, Quan Nguyen-Tri, Bang Tran Khanh, Dung D. Le 외

Few-shot image classification remains challenging due to the scarcity of labeled training examples. Augmenting them with synthetic data has emerged as a promising way to alleviate this issue, but models trained on synthe…

Few-Shot Image Classificationimage-classificationImage Classification

Simple Semi-supervised Knowledge Distillation from Vision-Language Models via $\mathbf{\texttt{D}}$ual-$\mathbf{\texttt{H}}$ead $\mathbf{\texttt{O}}$ptimization

2025-05-12 · Seongjae Kang, Dong Bok Lee, Hyungjoon Jang, Sung Ju Hwang

Vision-language models (VLMs) have achieved remarkable success across diverse tasks by leveraging rich textual information with minimal labeled data. However, deploying such large models remains challenging, particularly…

Few-Shot Image ClassificationKnowledge DistillationSemi-Supervised Image ClassificationSemi-Supervised Image Classification on ImageNet - 10% labeled data

Brain Inspired Adaptive Memory Dual-Net for Few-Shot Image Classification

2025-03-10 · Kexin Di, Xiuxing Li, Yuyang Han, Ziyu Li 외

Few-shot image classification has become a popular research topic for its wide application in real-world scenarios, however the problem of supervision collapse induced by single image-level annotation remains a major cha…

Few-Shot Image ClassificationHippocampusimage-classificationImage Classification

InPK: Infusing Prior Knowledge into Prompt for Vision-Language Models

2025-02-27 · Shuchang Zhou, Jiwei Wei, Shiyuan He, Yuyang Zhou 외

Prompt tuning has become a popular strategy for adapting Vision-Language Models (VLMs) to zero/few-shot visual recognition tasks. Some prompting techniques introduce prior knowledge due to its richness, but when learnabl…

Few-Shot Image Classificationimage-classificationImage Classification
1–20 / 367 다음 →