Related papers: AA-CLIP: Enhancing Zero-shot Anomaly Detection via…

Zero-shot anomaly detection (ZSAD) often leverages pretrained vision or vision-language models, but many existing methods use prompt learning or complex modeling to fit the data distribution, resulting in high training or inference cost and…

Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods, such as prompt learning and adapter, to enhance CLIP's…

Humans show an innate capability to identify tools to support specific actions. The association between objects parts and the actions they facilitate is usually named affordance. Being able to segment objects parts depending on the tasks…

CLIP (Contrastive Language-Image Pre-training) has attained great success in pattern recognition and computer vision. Transferring CLIP to downstream tasks (e.g. zero- or few-shot classification) is a hot topic in multimodal learning.…

Human action recognition plays a critical role in healthcare and medicine, supporting applications such as patient behavior monitoring, fall detection, surgical robot supervision, and procedural skill assessment. While traditional models…

A sliding-window inference strategy is commonly adopted in recent training-free open-vocabulary semantic segmentation methods to overcome limitation of the CLIP in processing high-resolution images. However, this approach introduces a new…

Zero-shot learning (ZSL) aims to recognize unseen classes by leveraging semantic information from seen classes, but most existing methods assume accurate class labels for training instances. However, in real-world scenarios, noise and…

Object detection is a pivotal task in computer vision that has received significant attention in previous years. Nonetheless, the capability of a detector to localise objects out of the training distribution remains unexplored. Whilst…

While vision-language models like CLIP have advanced zero-shot surgical phase recognition, they struggle with fine-grained surgical activities, especially action triplets. This limitation arises because current CLIP formulations rely on…

Recently, there have been breakthroughs in computer vision ("CV") models that are more generalizable with the advent of models such as CLIP and ALIGN. In this paper, we analyze CLIP and highlight some of the challenges such models pose.…

Large-scale contrastive vision-language pre-training has shown significant progress in visual representation learning. Unlike traditional visual systems trained by a fixed set of discrete labels, a new paradigm was introduced in…

Anomaly detection is a challenging task that frequently arises in practically all areas of industry and science, from fraud detection and data quality monitoring to finding rare cases of diseases and searching for new physics. Most of the…

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…

Contrastive Language-Image Pretraining (CLIP) achieves strong generalization in vision-language tasks by aligning images and texts in a shared embedding space. However, recent findings show that CLIP-like models still underutilize…

Image Aesthetics Assessment (IAA) is a challenging task due to its subjective nature and expensive manual annotations. Recent large-scale vision-language models, such as Contrastive Language-Image Pre-training (CLIP), have shown their…

Anomaly detection becomes increasingly important for the dependability and serviceability of IT services. As log lines record events during the execution of IT services, they are a primary source for diagnostics. Thereby, unsupervised…

Anomaly detection (AD), separating anomalies from normal data, has many applications across domains, from security to healthcare. While most previous works were shown to be effective for cases with fully or partially labeled data, that…

In unsupervised adaptation for vision-language models such as CLIP, pseudo-labels derived from zero-shot predictions often exhibit significant noise, particularly under domain shifts or in visually complex scenarios. Conventional…

Recently, the rapid advancements of vision-language models, such as CLIP, leads to significant progress in zero-/few-shot anomaly detection (ZFSAD) tasks. However, most existing CLIP-based ZFSAD methods commonly assume prior knowledge of…

Self-supervised models trained with a contrastive loss such as CLIP have shown to be very powerful in zero-shot classification settings. However, to be used as a zero-shot classifier these models require the user to provide new captions…