Vision-Language Models (VLMs) rely heavily on pretrained vision encoders to support downstream tasks such as image captioning, visual question answering, and zero-shot classification. Despite their strong performance, these encoders remain highly vulnerable to imperceptible adversarial perturbations, which can severely degrade both robustness and semantic quality in multimodal reasoning. In this work, we introduce Sim-CLIP, an unsupervised adversarial fine-tuning framework that enhances the robustness of the CLIP vision encoder while preserving overall semantic representations. Sim-CLIP adopts a Siamese training architecture with a cosine similarity objective and a symmetric stop-gradient mechanism to enforce semantic alignment between clean and adversarial views. This design avoids large-batch contrastive learning and additional momentum encoders, enabling robust training with low computational overhead. We evaluate Sim-CLIP across multiple Vision-Language Models and tasks under both targeted and untargeted adversarial attacks. Experimental results demonstrate that Sim-CLIP consistently outperforms state-of-the-art robust CLIP variants, achieving stronger adversarial robustness while maintaining or improving semantic fidelity. These findings highlight the limitations of existing adversarial defenses and establish Sim-CLIP as an effective and scalable solution for robust vision-language representation learning.
Contrastive Self-supervised Learning (CSL) is a practical solution that learns meaningful visual representations from massive data in an unsupervised approach. The ordinary CSL embeds the features extracted from neural networks onto specific topological structures. During the training progress, the contrastive loss draws the different views of the same input together while pushing the embeddings from different inputs apart. One of the drawbacks of CSL is that the loss term requires a large number of negative samples to provide better mutual information bound ideally. However, increasing the nu…
Leveraging Data Augmentation and Siamese Learning for Predictive Process Monitoring
Department of Mathematics and Computer Science, Eindhoven University of Technology, The Netherlands（数学与计算机科学系，埃因霍温理工大学，荷兰）；Department of Mathematics and Computer Science, University of Padua, Italy（数学与计算机科学系，帕多瓦大学，意大利）
TGC-Net: A Structure-Aware and Semantically-Aligned Framework for Text-Guided Medical Image Segmentation
School of Computer Science, Wuhan University（武汉大学计算机学院）；Department of Orthopedics, Tongji Hospital, Tongji Medical College, Huazhong University of Science（同济大学同济医学学院骨科部，华中科技大学）
Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks
School of Computing, Southern Illinois University（南伊利诺伊大学计算学院）；Security, Privacy and Intelligence for Edge Devices Laboratory (SPEED Lab)（边缘设备安全、隐私与智能实验室（SPEED Lab））
Frame-Difference Guided Dynamic Region Perception for CLIP Adaptation in Text-Video Retrieval
School of Computer Science and Technology, East China Normal University, China（上海师范大学计算机科学与技术学院）；School of Information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学与技术学院）
ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training
School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院）；Miner School of Computer & Information Sciences, University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校Miner计算机与信息科学学院）
CLIP-IT: CLIP-based Pairing for Histology Images Classification
LIVIA, ILLS, Dept. of Systems Engineering, ETS Montreal, Canada（LIVIA、ILLs、系统工程系、蒙特利尔大学ETSMontreal加拿大）；Dept. of Computer Engineering, University of Cagliari, Italy（计算机工程系、卡利亚里大学意大利）；Goodman Cancer Research, Centre, Dept. of Oncology, McGill University, Canada（Goodman癌症研究中心、肿瘤学系、麦吉尔大学加拿大）
Semantically Guided Adversarial Testing of Vision Models Using Language Models
Institute of Theoretical and Applied Informatics, Polish Academy of Sciences（波兰科学院理论与应用信息学研究所）；University of Lille, CNRS, Inria, Centrale Lille, UMR 9189 CRIStAL（里尔大学）
Swiss Federal Institute of Technology (EPFL)（瑞士联邦理工学院（洛桑））；Tel-Aviv University（特拉维夫大学）；Reichman University（赖希曼大学）
Abstraction is at the heart of sketching due to the simple and minimal nature of line drawings. Abstraction entails identifying the essential visual properties of an object or scene, which requires semantic understanding and prior knowledge of high-level concepts. Abstract depictions are therefore challenging for artists, and even more so for machines. We present CLIPasso, an object sketching method that can achieve different levels of abstraction, guided by geometric and semantic simplifications. While sketch generation methods often rely on explicit sketch datasets for training, we utilize t…
UC Santa Cruz（加州大学圣克鲁兹分校）；UC Santa Barbara（加州大学圣巴巴拉分校）；Google（谷歌）
Prompt tuning is a new few-shot transfer learning technique that only tunes the learnable prompt for pre-trained vision and language models such as CLIP. However, existing prompt tuning methods tend to learn spurious or entangled representations, which leads to poor generalization to unseen concepts. Towards non-spurious and efficient prompt learning from limited examples, this paper presents a novel \underline{\textbf{C}}ounterfactual \underline{\textbf{P}}rompt \underline{\textbf{L}}earning (CPL) method for vision and language models, which simultaneously employs counterfactual generation an…
Tsinghua University（清华大学）；University of Science and Technology of China（中国科学技术大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）
Self-supervised learning (SSL) has delivered superior performance on a variety of downstream vision tasks. Two main-stream SSL frameworks have been proposed, i.e., Instance Discrimination (ID) and Masked Image Modeling (MIM). ID pulls together representations from different views of the same image, while avoiding feature collapse. It lacks spatial sensitivity, which requires modeling the local structure within each image. On the other hand, MIM reconstructs the original content given a masked image. It instead does not have good semantic alignment, which requires projecting semantically simila…
Motivated by the increasing need of saving search effort by obtaining relevant video clips instead of whole videos, we propose a new task, named Semantic Video Moments Retrieval at scale (SVMR), which aims at finding relevant videos coupled with re-localizing the video clips in them. Instead of a simple combination of video retrieval and video re-localization, our task is more challenging because of several essential aspects. In the 1st stage, our SVMR should take into account the fact that: 1) a positive candidate long video can contain plenty of irrelevant clips which are also semantically m…
Understanding manipulation scenarios allows intelligent robots to plan for appropriate actions to complete a manipulation task successfully. It is essential for intelligent robots to semantically interpret manipulation knowledge by describing entities, relations and attributes in a structural manner. In this paper, we propose an implementing framework to generate high-level conceptual dynamic knowledge graphs from video clips. A combination of a Vision-Language model and an ontology system, in correspondence with visual perception and contextual semantics, is used to represent robot manipulati…
PAII Inc.（PAII 公司）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Rochester（罗切斯特大学）；Chang Gung Memorial Hospital（长庚纪念医院）；Ping An Technology（平安科技）
Visual cues of enforcing bilaterally symmetric anatomies as normal findings are widely used in clinical practice to disambiguate subtle abnormalities from medical images. So far, inadequate research attention has been received on effectively emulating this practice in CAD methods. In this work, we exploit semantic anatomical symmetry or asymmetry analysis in a complex CAD scenario, i.e., anterior pelvic fracture detection in trauma PXRs, where semantically pathological (refer to as fracture) and non-pathological (e.g., pose) asymmetries both occur. Visually subtle yet pathologically critical f…
University of California, San Diego（加利福尼亚大学圣地亚哥分校）；Carnegie Mellon University（卡内基梅隆大学）；Amazon AI（亚马逊人工智能）；Stanford University（斯坦福大学）；University of California San Diego（加利福尼亚大学圣地亚哥分校）
We propose a new algorithm for training generative adversarial networks that jointly learns latent codes for both identities (e.g. individual humans) and observations (e.g. specific photographs). By fixing the identity portion of the latent codes, we can generate diverse images of the same subject, and by fixing the observation portion, we can traverse the manifold of subjects while maintaining contingent aspects such as lighting and pose. Our algorithm features a pairwise training scheme in which each sample from the generator consists of two images with a common identity code. Corresponding …
