paper-with-me

Papers zero-shot-classification

“zero-shot-classification” 태그가 달린 논문 422편 · 필터 해제

DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation

2025-07-14 · Ivan Martinović, Josip Šarić, Marin Oršić, Matej Kristan 외

Pixel-level annotation is expensive and time-consuming. Semi-supervised segmentation methods address this challenge by learning models on few labeled images alongside a large corpus of unlabeled images. Although foundati…

DecoderGPUPanoptic SegmentationSemantic Segmentation+3

Comparison of ConvNeXt and Vision-Language Models for Breast Density Assessment in Screening Mammography

2025-06-16 · Yusdivia Molina-Román, David Gómez-Ortiz, Ernestina Menasalvas-Ruiz, José Gerardo Tamez-Peña 외

Mammographic breast density classification is essential for cancer risk assessment but remains challenging due to subjective interpretation and inter-observer variability. This study compares multimodal and CNN-based met…

breast density classificationClassificationzero-shot-classificationZero-Shot Learning

Harmonizing and Merging Source Models for CLIP-based Domain Generalization

2025-06-11 · Yuhe Ding, Jian Liang, Bo Jiang, Zi Wang 외

CLIP-based domain generalization aims to improve model generalization to unseen domains by leveraging the powerful zero-shot classification capabilities of CLIP and multiple source datasets. Existing methods typically tr…

Domain Generalizationzero-shot-classificationZero-Shot Learning

Efficient Medical Vision-Language Alignment Through Adapting Masked Vision Models

2025-06-10 · Chenyu Lian, Hong-Yu Zhou, Dongyun Liang, Jing Qin 외

Medical vision-language alignment through cross-modal contrastive learning shows promising performance in image-text matching tasks, such as retrieval and zero-shot classification. However, conventional cross-modal contr…

Contrastive LearningImage-text matchingImage to textImage-to-Text Retrieval+5

GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language Models

2025-05-30 · Gilles Quentin Hacheme, Girmaw Abebe Tadesse, Caleb Robinson, Akram Zaytar 외

Classifying geospatial imagery remains a major bottleneck for applications such as disaster response and land-use monitoring-particularly in regions where annotated data is scarce or unavailable. Existing tools (e.g., RS…

ClassificationDisaster Responseimage-classificationImage Classification+6

AmorLIP: Efficient Language-Image Pretraining via Amortization

2025-05-25 · Haotian Sun, Yitong Li, Yuchen Zhuang, Niao He 외

Contrastive Language-Image Pretraining (CLIP) has demonstrated strong zero-shot performance across diverse downstream text-image tasks. Existing CLIP methods typically optimize a contrastive objective using negative samp…

Contrastive LearningRepresentation Learningzero-shot-classificationZero-Shot Learning

Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation

2025-05-25 · Daniel Csizmadia, Andrei Codreanu, Victor Sim, Vighnesh Prabhu 외

We present Distill CLIP (DCLIP), a fine-tuned variant of the CLIP model that enhances multimodal image-text retrieval while preserving the original model's strong zero-shot classification capabilities. CLIP models are ty…

Contrastive LearningImage-text RetrievalRetrievalText Retrieval+2

Beginning with You: Perceptual-Initialization Improves Vision-Language Representation and Alignment

2025-05-20 · Yang Hu, Runchen Wang, Stephen Chong Zhao, Xuhui Zhan 외

We introduce Perceptual-Initialization (PI), a paradigm shift in visual representation learning that incorporates human perceptual structure during the initialization phase rather than as a downstream fine-tuning step. B…

Representation LearningRetrievalSelf-Supervised LearningTriplet+2

Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruption

2025-05-19 · Kazuki Adachi, Shin'ya Yamaguchi, Tomoki Hamagami

Pre-trained vision-language models such as contrastive language-image pre-training (CLIP) have demonstrated a remarkable generalizability, which has enabled a wide range of applications represented by zero-shot classific…

Knowledge DistillationTest-time Adaptationzero-shot-classificationZero-Shot Learning

StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment

2025-05-19 · Younghyun Kim, Jongheon Jeong, Sangkyung Kwak, Kyungmin Lee 외

Learning robust representations from data often requires scale, which has led to the success of recent zero-shot models such as CLIP. However, the obtained robustness can easily be deteriorated when these models are fine…

zero-shot-classificationZero-Shot Learning

From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection

2025-05-19 · Lincan Cai, Jingxuan Kang, Shuang Li, Wenxuan Ma 외

Pretrained vision-language models (VLMs), e.g., CLIP, demonstrate impressive zero-shot capabilities on downstream tasks. Prior research highlights the crucial role of visual augmentation techniques, like random cropping,…

feature selectionOut-of-Distribution GeneralizationTest-time Adaptationzero-shot-classification+1

Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner

2025-05-16 · Wenchuan Zhang, Penghao Zhang, Jingru Guo, Tao Cheng 외

Recent advances in vision language models (VLMs) have enabled broad progress in the general medical field. However, pathology still remains a more challenging subdomain, with current pathology specific VLMs exhibiting li…

Cross-Modal RetrievalDiagnosticImage DescriptionMultimodal Reasoning+5

Advanced Crash Causation Analysis for Freeway Safety: A Large Language Model Approach to Identifying Key Contributing Factors

2025-05-15 · Ahmed S. Abdelrahman, Mohamed Abdel-Aty, Samgyu Yang, Abdulrahman Faden

Understanding the factors contributing to traffic crashes and developing strategies to mitigate their severity is essential. Traditional statistical methods and machine learning models often struggle to capture the compl…

Language ModelingLanguage ModellingLarge Language Modelzero-shot-classification+1

TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining

2025-05-12 · Paul Primus, Florian Schmid, Gerhard Widmer

Learning to associate audio with textual descriptions is valuable for a range of tasks, including pretraining, zero-shot classification, audio retrieval, audio captioning, and text-conditioned audio generation. Existing …

Audio captioningAudio GenerationSentencezero-shot-classification+1

Image Classification Using a Diffusion Model as a Pre-Training Model

2025-05-11 · Kosuke Ukita, Ye Xiaolong, Tsuyoshi Okita

In this paper, we propose a diffusion model that integrates a representation-conditioning mechanism, where the representations derived from a Vision Transformer (ViT) are used to condition the internal process of a Trans…

Contrastive Learningimage-classificationImage Classificationmodel+3

MM-Skin: Enhancing Dermatology Vision-Language Model with an Image-Text Dataset Derived from Textbooks

2025-05-09 · Wenqi Zeng, Yuqi Sun, Chenxi Ma, Weimin Tan 외

Medical vision-language models (VLMs) have shown promise as clinical assistants across various medical fields. However, specialized dermatology VLM capable of delivering professional and detailed diagnostic analysis rema…

DiagnosticInstruction FollowingLanguage ModelingLanguage Modelling+4

FG-CLIP: Fine-Grained Visual and Textual Alignment

2025-05-08 · Chunyu Xie, Bin Wang, Fanjing Kong, Jincheng Li 외

Contrastive Language-Image Pre-training (CLIP) excels in multimodal tasks such as image-text retrieval and zero-shot classification but struggles with fine-grained understanding due to its focus on coarse-grained short c…

Image-text Retrievalobject-detectionObject DetectionOpen-vocabulary object detection+5

Fill the Gap: Quantifying and Reducing the Modality Gap in Image-Text Representation Learning

2025-05-06 · François Role, Sébastien Meyer, Victor Amblard

Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separatio…

Representation Learningzero-shot-classificationZero-Shot Learning

Helping Large Language Models Protect Themselves: An Enhanced Filtering and Summarization System

2025-05-02 · Sheikh Samit Muhaimin, Spyridon Mastorakis

The recent growth in the use of Large Language Models has made them vulnerable to sophisticated adversarial assaults, manipulative prompts, and encoded malicious inputs. Existing countermeasures frequently necessitate re…

zero-shot-classificationZero-Shot Learning

On the effectiveness of Large Language Models in the mechanical design domain

2025-05-02 · Daniele Grandi, Fabian Riquelme

In this work, we seek to understand the performance of large language models in the mechanical engineering domain. We leverage the semantic data found in the ABC dataset, specifically the assembly names that designers as…

ClassificationSentenceSentence-Pair Classificationzero-shot-classification+1
1–20 / 422 다음 →