Related papers: CLIP-AD: A Language-Guided Staged Dual-Path Model …

Despite its prevalent use in image-text matching tasks in a zero-shot manner, CLIP has been shown to be highly vulnerable to adversarial perturbations added onto images. Recent studies propose to finetune the vision encoder of CLIP with…

In this paper, we study the problem of zero-shot sketch-based image retrieval (ZS-SBIR). The prior methods tackle the problem in a two-modality setting with only category labels or even no textual information involved. However, the growing…

Recent studies on visual anomaly detection (AD) of industrial objects/textures have achieved quite good performance. They consider an unsupervised setting, specifically the one-class setting, in which we assume the availability of a set of…

Learning discriminative 3D representations that generalize well to unknown testing categories is an emerging requirement for many real-world 3D applications. Existing well-established methods often struggle to attain this goal due to…

This paper studies zero-shot object recognition using event camera data. Guided by CLIP, which is pre-trained on RGB images, existing approaches achieve zero-shot object recognition by optimizing embedding similarities between event data…

Unsupervised anomaly detection (AD) is critical for a wide range of practical applications, from network security to health and medical tools. Due to the diversity of problems, no single algorithm has been found to be superior for all AD…

Industrial anomaly detection (IAD) plays a crucial role in the maintenance and quality control of manufacturing processes. In this paper, we propose a novel approach, Vision-Language Anomaly Detection via Contrastive Cross-Modal Training…

Recent advances in visual-language models have shown remarkable zero-shot text-image matching ability that is transferable to downstream tasks such as object detection and segmentation. Adapting these models for object counting, however,…

Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP to help the learning in 3D scene understanding has yet to be explored.…

Universal visual anomaly detection aims to identify anomalies from novel or unseen vision domains without additional fine-tuning, which is critical in open scenarios. Recent studies have demonstrated that pre-trained vision-language models…

Generalized Zero-shot Semantic Segmentation aims to segment both seen and unseen categories only under the supervision of the seen ones. To tackle this, existing methods adopt the large-scale Vision Language Models (VLMs) which obtain…

Recognizing the activities causing distraction in real-world driving scenarios is critical for ensuring the safety and reliability of both drivers and pedestrians on the roadways. Conventional computer vision techniques are typically…

Zero-Shot Video Anomaly Detection (ZS-VAD) requires temporally localizing anomalies without target domain training data, which is a crucial task due to various practical concerns, e.g., data privacy or new surveillance deployments.…

Contrastive language-image pretraining (CLIP) links vision and language modalities into a unified embedding space, yielding the tremendous potential for vision-language (VL) tasks. While early concurrent works have begun to study this…

Human-centric visual analysis plays a pivotal role in diverse applications, including surveillance, healthcare, and human-computer interaction. With the emergence of large-scale unlabeled human image datasets, there is an increasing need…

Vision-language models (VLMs) such as CLIP demonstrate strong generalization in zero-shot classification but remain highly vulnerable to adversarial perturbations. Existing methods primarily focus on adversarial fine-tuning or prompt…

We study the problem of few-shot out-of-distribution (OOD) detection, which aims to detect OOD samples from unseen categories during inference time with only a few labeled in-domain (ID) samples. Existing methods mainly focus on training…

Although deep learning models have shown impressive performance on supervised learning tasks, they often struggle to generalize well when the training (source) and test (target) domains differ. Unsupervised domain adaptation (DA) has…

Responding to the challenge of detecting unusual radar targets in a well identified environment, innovative anomaly and novelty detection methods keep emerging in the literature. This work aims at presenting a benchmark gathering common and…

A vision-language foundation model pretrained on very large-scale image-text paired data has the potential to provide generalizable knowledge representation for downstream visual recognition and detection tasks, especially on supplementing…