相关论文: AutoCLIP: Auto-tuning Zero-Shot Classifiers for Vi…

Vision-language foundation models such as CLIP have shown impressive zero-shot performance on many tasks and datasets, especially thanks to their free-text inputs. However, they struggle to handle some downstream tasks, such as fine-grained…

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…

Labeling large image datasets with attributes such as facial age or object type is tedious and sometimes infeasible. Supervised machine learning methods provide a highly accurate solution, but require manual labels which are often…

In this study, we define and tackle zero shot "real" classification by description, a novel task that evaluates the ability of Vision-Language Models (VLMs) like CLIP to classify objects based solely on descriptive attributes, excluding…

Image-text contrastive learning models such as CLIP have demonstrated strong task transfer ability. The high generality and usability of these visual models is achieved via a web-scale data collection process to ensure broad concept…

Scene understanding is essential for enhancing driver safety, generating human-centric explanations for Automated Vehicle (AV) decisions, and leveraging Artificial Intelligence (AI) for retrospective driving video analysis. This study…

In recent studies on domain adaptation, significant emphasis has been placed on the advancement of learning shared knowledge from a source domain to a target domain. Recently, the large vision-language pre-trained model, i.e., CLIP has…

Current pre-trained vision-language models, such as CLIP, have demonstrated remarkable zero-shot generalization capabilities across various downstream tasks. However, their performance significantly degrades when test inputs exhibit…

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…

CLIP has shown a remarkable zero-shot capability on a wide range of vision tasks. Previously, CLIP is only regarded as a powerful visual encoder. However, after being pre-trained by language supervision from a large amount of image-caption…

Recently, large-scale Contrastive Language-Image Pre-training (CLIP) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferability to downstream tasks. However, CLIP is quite…

Multi-label classification is an essential task utilized in a wide variety of real-world applications. Multi-label zero-shot learning is a method for classifying images into multiple unseen categories for which no training data is…

Image captioning aims at generating descriptive and meaningful textual descriptions of images, enabling a broad range of vision-language applications. Prior works have demonstrated that harnessing the power of Contrastive Image Language…

General-purpose foundation models have led to recent breakthroughs in artificial intelligence. In remote sensing, self-supervised learning (SSL) and Masked Image Modeling (MIM) have been adopted to build foundation models. However, these…

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification. The class token in the image encoder is trained to capture the global features to distinguish different text…

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…

Existing computer vision research in artwork struggles with artwork's fine-grained attributes recognition and lack of curated annotated datasets due to their costly creation. To the best of our knowledge, we are one of the first methods to…

Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations using large-scale image-text pairs. It shows impressive performance on downstream tasks by zero-shot knowledge…

Dense visual prediction tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have…

Contrastive vision-language pre-training frameworks such as CLIP have demonstrated impressive zero-shot performance across a range of vision-language tasks. Recent studies have shown that aligning individual text tokens with specific image…