English
Related papers

Related papers: Patching open-vocabulary models by interpolating w…

200 papers

Task arithmetic has recently emerged as a promising method for editing pre-trained \textit{open-vocabulary} models, offering a cost-effective alternative to standard multi-task fine-tuning. However, despite the abundance of…

Machine Learning · Computer Science 2025-11-19 Adam Hazimeh , Alessandro Favero , Pascal Frossard

Vision-language models like CLIP demonstrate impressive zero-shot generalization but remain highly vulnerable to adversarial attacks. In this work, we propose Confidence-Aware Weighting (CAW) to enhance zero-shot robustness in…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Nikoo Naghavian , Mostafa Tavassolipour

The task of open-vocabulary object-centric image retrieval involves the retrieval of images containing a specified object of interest, delineated by an open-set text query. As working on large image datasets becomes standard, solving this…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Hila Levi , Guy Heller , Dan Levi , Ethan Fetaya

We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between the patch tokens of the vision encoder and the CLS token of the text encoder.…

Computer Vision and Pattern Recognition · Computer Science 2022-12-12 Jishnu Mukhoti , Tsung-Yu Lin , Omid Poursaeed , Rui Wang , Ashish Shah , Philip H. S. Torr , Ser-Nam Lim

Contrastive Language-Image Pre-training (CLIP) formulates image classification as an image-to-text matching task, i.e., matching images to the corresponding natural language descriptions instead of discrete category IDs. This allows for…

Computer Vision and Pattern Recognition · Computer Science 2023-05-09 Shuhuai Ren , Lei Li , Xuancheng Ren , Guangxiang Zhao , Xu Sun

Vision-Language Models like CLIP create aligned embedding spaces for text and images, making it possible for anyone to build a visual classifier by simply naming the classes they want to distinguish. However, a model that works well in one…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Kevin Robbins , Xiaotong Liu , Yu Wu , Le Sun , Grady McPeak , Abby Stylianou , Robert Pless

Pre-trained Vision-Language Models (VLMs), such as CLIP, have shown enhanced performance across a range of tasks that involve the integration of visual and linguistic modalities. When CLIP is used for depth estimation tasks, the patches,…

Computer Vision and Pattern Recognition · Computer Science 2023-11-03 Xueting Hu , Ce Zhang , Yi Zhang , Bowen Hai , Ke Yu , Zhihai He

Long-tailed multi-label visual recognition poses a significant challenge, as images typically contain multiple labels with highly imbalanced class distributions, leading to biased models that favor head classes while underperforming on tail…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Wei Tang , Zuo-Zheng Wang , Kun Zhang , Tong Wei , Min-Ling Zhang

Large pre-trained, zero-shot capable models have shown considerable success both for standard transfer and adaptation tasks, with particular robustness towards distribution shifts. In addition, subsequent fine-tuning can considerably…

Machine Learning · Computer Science 2022-11-08 Zafir Stojanovski , Karsten Roth , Zeynep Akata

We propose a simple strategy for masking image patches during visual-language contrastive learning that improves the quality of the learned representations and the training speed. During each iteration of training, we randomly mask clusters…

Computer Vision and Pattern Recognition · Computer Science 2024-05-15 Zihao Wei , Zixuan Pan , Andrew Owens

One little-explored frontier of image generation and editing is the task of interpolating between two input images, a feature missing from all currently deployed image generation pipelines. We argue that such a feature can expand the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Clinton J. Wang , Polina Golland

Efficient fine-tuning of vision-language models (VLMs) like CLIP for specific downstream tasks is gaining significant attention. Previous works primarily focus on prompt learning to adapt the CLIP into a variety of downstream tasks,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Jinlong Li , Dong Zhao , Zequn Jie , Elisa Ricci , Lin Ma , Nicu Sebe

Large vision-language models (VLMs), such as CLIP, learn rich joint image-text representations, facilitating advances in numerous downstream tasks, including zero-shot classification and text-to-image generation. Nevertheless, existing VLMs…

Computer Vision and Pattern Recognition · Computer Science 2023-02-24 Roni Paiss , Ariel Ephrat , Omer Tov , Shiran Zada , Inbar Mosseri , Michal Irani , Tali Dekel

CLIP is a widely used foundational vision-language model that is used for zero-shot image recognition and other image-text alignment tasks. We demonstrate that CLIP is vulnerable to change in image quality under compression. This surprising…

Computer Vision and Pattern Recognition · Computer Science 2023-11-27 Cangxiong Chen , Vinay P. Namboodiri , Julian Padget

Recent advancements in pre-trained vision-language models like CLIP have enabled the task of open-vocabulary segmentation. CLIP demonstrates impressive zero-shot capabilities in various downstream tasks that require holistic image…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Sule Bai , Yong Liu , Yifei Han , Haoji Zhang , Yansong Tang , Jie Zhou , Jiwen Lu

Calibration of deep learning models is crucial to their trustworthiness and safe usage, and as such, has been extensively studied in supervised classification models, with methods crafted to decrease miscalibration. However, there has yet…

Computer Vision and Pattern Recognition · Computer Science 2023-04-20 Will LeVine , Benjamin Pikus , Pranav Raja , Fernando Amat Gil

Transfer learning enables the sharing of common knowledge among models for a variety of downstream tasks, but traditional methods suffer in limited training data settings and produce narrow models incapable of effectively generalizing under…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Kevin Vogt-Lowell , Noah Lee , Theodoros Tsiligkaridis , Marc Vaillant

Visual Question Answering is a challenging task, as it requires seamless interaction between perceptual, linguistic, and background knowledge systems. While the recent progress of visual and natural language models like BLIP has led to…

Computer Vision and Pattern Recognition · Computer Science 2023-06-02 Jiarui Zhang , Mahyar Khayatkhoei , Prateek Chhikara , Filip Ilievski

Vision-language models such as CLIP learn a generic text-image embedding from large-scale training data. A vision-language model can be adapted to a new classification task through few-shot prompt tuning. We find that such a prompt tuning…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Cheng-En Wu , Yu Tian , Haichao Yu , Heng Wang , Pedro Morgado , Yu Hen Hu , Linjie Yang

Classifiers in machine learning are often brittle when deployed. Particularly concerning are models with inconsistent performance on specific subgroups of a class, e.g., exhibiting disparities in skin cancer classification in the presence…

Machine Learning · Computer Science 2020-08-18 Karan Goel , Albert Gu , Yixuan Li , Christopher Ré