English
Related papers

Related papers: TIMA: Text-Image Mutual Awareness for Balancing Ze…

200 papers

Current SOTA adversarially robust models are mostly based on adversarial training (AT) and differ only by some regularizers either at inner maximization or outer minimization steps. Being repetitive in nature during the inner maximization…

Machine Learning · Computer Science 2021-11-02 Anindya Sarkar , Anirban Sarkar , Sowrya Gali , Vineeth N Balasubramanian

Despite its remarkable success in zero-shot image-text matching, CLIP remains highly vulnerable to adversarial perturbations on images. As adversarial fine-tuning is prohibitively costly, recent works explore various test-time defense…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Linxiang Su , András Balogh

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Dong Lao , Yuxiang Zhang , Haniyeh Ehsani Oskouie , Yangchao Wu , Alex Wong , Stefano Soatto

Contrastive language-image pretraining (CLIP) has demonstrated remarkable success in various image tasks. However, how to extend CLIP with effective temporal modeling is still an open and crucial problem. Existing factorized or joint…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Shuyuan Tu , Qi Dai , Zuxuan Wu , Zhi-Qi Cheng , Han Hu , Yu-Gang Jiang

Many adversarial defense methods have been proposed to enhance the adversarial robustness of natural language processing models. However, most of them introduce additional pre-set linguistic knowledge and assume that the synonym candidates…

Computation and Language · Computer Science 2024-02-28 Yichen Yang , Xin Liu , Kun He

Recently, CLIP has become an important model for aligning images and text in multi-modal contexts. However, researchers have identified limitations in the ability of CLIP's text and image encoders to extract detailed knowledge from pairs of…

Artificial Intelligence · Computer Science 2024-12-10 Kuei-Chun Kao

This paper focuses on multimodal alignment within the realm of Artificial Intelligence, particularly in text and image modalities. The semantic gap between the textual and visual modality poses a discrepancy problem towards the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Khang H. N. Vo , Duc P. T. Nguyen , Thong Nguyen , Tho T. Quan

Recent research has shown that aligning fine-grained text descriptions with localized image patches can significantly improve the zero-shot performance of pre-trained vision-language models (e.g., CLIP). However, we find that both…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Yuhao Sun , Chengyi Cai , Jiacheng Zhang , Zesheng Ye , Xingliang Yuan , Feng Liu

In this paper, we aim to build an adversarially robust zero-shot image classifier. We ground our work on CLIP, a vision-language pre-trained encoder model that can perform zero-shot classification by matching an image with text prompts ``a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Mingkun Zhang , Keping Bi , Wei Chen , Jiafeng Guo , Xueqi Cheng

Existing works have advanced Text-to-Image (TTI) diffusion models for video editing in a one-shot learning manner. Despite their low requirements of data and computation, these methods might produce results of unsatisfied consistency with…

Computer Vision and Pattern Recognition · Computer Science 2023-05-30 Zicheng Zhang , Bonan Li , Xuecheng Nie , Congying Han , Tiande Guo , Luoqi Liu

Adopting contrastive image-text pretrained models like CLIP towards video classification has gained attention due to its cost-effectiveness and competitive performance. However, recent works in this area face a trade-off. Finetuning the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Syed Talal Wasim , Muzammal Naseer , Salman Khan , Fahad Shahbaz Khan , Mubarak Shah

Research on multi-modal contrastive learning strategies for audio and text has rapidly gained interest. Contrastively trained Audio-Language Models (ALMs), such as CLAP, which establish a unified representation across audio and language…

Sound · Computer Science 2025-04-22 Anshuman Sinha , Camille Migozzi , Aubin Rey , Chao Zhang

Balancing fidelity and editability is essential in text-based image editing (TIE), where failures commonly lead to over- or under-editing issues. Existing methods typically rely on attention injections for structure preservation and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Qi Mao , Lan Chen , Yuchao Gu , Mike Zheng Shou , Ming-Hsuan Yang

In recent literature, few-shot classification has predominantly been defined by the N-way k-shot meta-learning problem. Models designed for this purpose are usually trained to excel on standard benchmarks following a restricted setup,…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Constance Ferragu , Philomene Chagniot , Vincent Coyette

Vision-language models trained with contrastive learning on large-scale noisy data are becoming increasingly popular for zero-shot recognition problems. In this paper we improve the following three aspects of the contrastive pre-training…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Filip Radenovic , Abhimanyu Dubey , Abhishek Kadian , Todor Mihaylov , Simon Vandenhende , Yash Patel , Yi Wen , Vignesh Ramanathan , Dhruv Mahajan

Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from…

Computer Vision and Pattern Recognition · Computer Science 2024-02-22 Ahmet Iscen , Mathilde Caron , Alireza Fathi , Cordelia Schmid

Transductive few-shot learning has triggered an abundant literature focusing on vision-only models, but is still at a nascent stage within the recent context of foundational vision-language models (VLMs). Only a few recent methods addressed…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Ghassen Baklouti , Maxime Zanella , Ismail Ben Ayed

Vision-Language Models (VLMs) such as CLIP have yielded unprecedented performance for zero-shot image classification, yet their generalization capability may still be seriously challenged when confronted to domain shifts. In response, we…

Transferring visual-language knowledge from large-scale foundation models for video recognition has proved to be effective. To bridge the domain gap, additional parametric modules are added to capture the temporal information. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Minghao Zhu , Zhengpu Wang , Mengxian Hu , Ronghao Dang , Xiao Lin , Xun Zhou , Chengju Liu , Qijun Chen

It has recently been discovered that using a pre-trained vision-language model (VLM), e.g., CLIP, to align a whole query image with several finer text descriptions generated by a large language model can significantly enhance zero-shot…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Jinhao Li , Haopeng Li , Sarah Erfani , Lei Feng , James Bailey , Feng Liu