相关论文: Online Zero-Shot Classification with CLIP

The emergence of CLIP has opened the way for open-world image perception. The zero-shot classification capabilities of the model are impressive but are harder to use for dense tasks such as image segmentation. Several methods have proposed…

Vision language models such as CLIP have shown remarkable performance in zero shot classification, but remain susceptible to spurious correlations, where irrelevant visual features influence predictions. Existing debiasing methods often…

Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training (CLIP) have shown inspirational performance on 2D visual recognition, which learns to match images with their corresponding texts in open-vocabulary…

Pre-trained vision-language models, e.g. CLIP, have been increasingly used to address the challenging Open-Vocabulary Segmentation (OVS) task, benefiting from their well-aligned vision-text embedding space. Typical solutions involve either…

In some of object recognition problems, labeled data may not be available for all categories. Zero-shot learning utilizes auxiliary information (also called signatures) describing each category in order to find a classifier that can…

Zero-shot learning (ZSL) aims to recognize instances of unseen classes solely based on the semantic descriptions of the classes. Existing algorithms usually formulate it as a semantic-visual correspondence problem, by learning mappings from…

In the era of foundation models, CLIP has emerged as a powerful tool for aligning text & visual modalities into a common embedding space. However, the alignment objective used to train CLIP often results in subpar visual features for…

Despite their impressive zero-shot abilities, vision-language models such as CLIP have been shown to be susceptible to adversarial attacks. To enhance its adversarial robustness, recent studies finetune the pretrained vision encoder of CLIP…

Machine Learning (ML) techniques for image classification routinely require many labelled images for training the model and while testing, we ought to use images belonging to the same domain as those used for training. In this paper, we…

Vision-language models (VLMs) like CLIP exhibit strong zero-shot capabilities but often fail to generalize under distribution shifts. Test-time adaptation (TTA) allows models to update at inference time without labeled data, typically via…

Recent adaptations can boost the low-shot capability of Contrastive Vision-Language Pre-training (CLIP) by effectively facilitating knowledge transfer. However, these adaptation methods are usually operated on the global view of an input…

In an out-of-distribution (OOD) detection problem, samples of known classes(also called in-distribution classes) are used to train a special classifier. In testing, the classifier can (1) classify the test samples of known classes to their…

Vision-language models such as CLIP are capable of mapping the different modality data into a unified feature space, enabling zero/few-shot inference by measuring the similarity of given images and texts. However, most existing methods…

Multi-modal foundation models such as CLIP have showcased impressive zero-shot capabilities. However, their applicability in resource-constrained environments is limited due to their large number of parameters and high inference time. While…

Contrastive Language-Image Pre-training (CLIP) models excel in zero-shot classification, yet face challenges in complex multi-object scenarios. This study offers a comprehensive analysis of CLIP's limitations in these contexts using a…

Given the recent advances in multimodal image pretraining where visual models trained with semantically dense textual supervision tend to have better generalization capabilities than those trained using categorical attributes or through…

Recent Vision-Language Models (VLMs) enable zero-shot classification by aligning images and text in a shared space, a promising approach for data-scarce conditions. However, the influence of prompt design on recognizing visually similar…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Adapting CLIP for anomaly detection on unseen objects has shown strong potential in a zero-shot manner. However, existing methods typically rely on a single textual space to align with visual semantics across diverse objects and domains.…

Large vision-language models (VLMs) are shown to learn rich joint image-text representations enabling high performances in relevant downstream tasks. However, they fail to showcase their quantitative understanding of objects, and they lack…