Related papers: Online Zero-Shot Classification with CLIP
Finetuning image-text models such as CLIP achieves state-of-the-art accuracies on a variety of benchmarks. However, recent works like WiseFT (Wortsman et al., 2021) and LP-FT (Kumar et al., 2022) have shown that even subtle differences in…
Semantic segmentation, which aims to acquire a detailed understanding of images, is an essential issue in computer vision. However, in practical scenarios, new categories that are different from the categories in training usually appear.…
This paper presents a novel method that leverages a visual-language model, CLIP, as a data source for zero-shot anomaly detection. Tremendous efforts have been put towards developing anomaly detectors due to their potential industrial…
Large pre-trained vision-language models like CLIP have shown great potential in learning representations that are transferable across a wide range of downstream tasks. Different from the traditional representation learning that is based…
We propose CLIP-Lite, an information efficient method for visual representation learning by feature alignment with textual annotations. Compared to the previously proposed CLIP model, CLIP-Lite requires only one negative image-text sample…
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…
CLIP has achieved impressive zero-shot performance after pre-training on a large-scale dataset consisting of paired image-text data. Previous works have utilized CLIP by incorporating manually designed visual prompts like colored circles…
Zero-shot learning (ZSL) for image classification focuses on recognizing novel categories that have no labeled data available for training. The learning is generally carried out with the help of mid-level semantic descriptors associated…
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…
Inspired by the remarkable zero-shot generalization capacity of vision-language pre-trained model, we seek to leverage the supervision from CLIP model to alleviate the burden of data labeling. However, such supervision inevitably contains…
Treating texts as images, combining prompts with textual labels for prompt tuning, and leveraging the alignment properties of CLIP have been successfully applied in zero-shot multi-label image recognition. Nonetheless, relying solely on…
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…
Audio-visual zero-shot learning methods commonly build on features extracted from pre-trained models, e.g. video or audio classification models. However, existing benchmarks predate the popularization of large multi-modal models, such as…
Object localization is a hot issue in computer vision area, which aims to identify and determine the precise location of specific objects from image or video. Most existing object localization methods heavily rely on extensive labeled data,…
Large-scale pretrained vision-language models like CLIP have demonstrated remarkable zero-shot image classification capabilities across diverse domains. To enhance CLIP's performance while preserving the zero-shot paradigm, various…
Deep Learning (DL) is undergoing a paradigm shift with the emergence of foundation models. In this work, we focus on Contrastive Language-Image Pre-training (CLIP), a Vision-Language foundation model that achieves high accuracy across…
Contrastive Language-Image Pretraining (CLIP) has shown impressive zero-shot performance on image classification. However, state-of-the-art methods often rely on fine-tuning techniques like prompt learning and adapter-based tuning to…
The performance of vision-language models (VLMs), such as CLIP, in visual classification tasks, has been enhanced by leveraging semantic knowledge from large language models (LLMs), including GPT. Recent studies have shown that in zero-shot…
Large vision-language representation learning models like CLIP have demonstrated impressive performance for zero-shot transfer to downstream tasks while largely benefiting from inter-modal (image-text) alignment via contrastive objectives.…
Contrastive Language-Image Pre-training (CLIP) has drawn increasing attention recently for its transferable visual representation learning. However, due to the semantic gap within datasets, CLIP's pre-trained image-text alignment becomes…