相关论文: Language Plays a Pivotal Role in the Object-Attrib…

An increasingly massive number of remote-sensing images spurs the development of extensible object detectors that can detect objects beyond training categories without costly collecting new labeled data. In this paper, we aim to develop…

Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected from the web. However, the presence of intrinsic noise and…

Severe data imbalance naturally exists among web-scale vision-language datasets. Despite this, we find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance compared to supervised learning, and demonstrates…

Traditional semi-supervised object detection methods assume a fixed set of object classes (in-distribution or ID classes) during training and deployment, which limits performance in real-world scenarios where unseen classes…

Most deep-learning-based image classification methods assume that all samples are generated under an independent and identically distributed (IID) setting. However, out-of-distribution (OOD) generalization is more common in practice, which…

In recent years, it has been shown empirically that standard disentangled latent variable models do not support robust compositional learning in the visual domain. Indeed, in spite of being designed with the goal of factorising datasets…

Pretrained vision-language models, such as CLIP, show promising zero-shot performance across a wide variety of datasets. For closed-set classification tasks, however, there is an inherent limitation: CLIP image encoders are typically…

Vision-language models like CLIP are widely used in zero-shot image classification due to their ability to understand various visual concepts and natural language descriptions. However, how to fully leverage CLIP's unprecedented human-like…

This paper presents a detailed study of improving visual representations for vision language (VL) tasks and develops an improved object detection model to provide object-centric representations of images. Compared to the most widely used…

LiDAR-based 3D object detection has become an essential part of automated driving due to its ability to localize and classify objects precisely in 3D. However, object detectors face a critical challenge when dealing with unknown foreground…

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…

Despite the success of large-scale pretrained Vision-Language Models (VLMs) especially CLIP in various open-vocabulary tasks, their application to semantic segmentation remains challenging, producing noisy segmentation maps with…

With the rapid advancement of Multimodal Large Language Models (MLLMs), a variety of benchmarks have been introduced to evaluate their capabilities. While most evaluations have focused on complex tasks such as scientific comprehension and…

We present a novel vision-language prompt learning approach for few-shot out-of-distribution (OOD) detection. Few-shot OOD detection aims to detect OOD images from classes that are unseen during training using only a few labeled…

In rapidly evolving field of vision-language models (VLMs), contrastive language-image pre-training (CLIP) has made significant strides, becoming foundation for various downstream tasks. However, relying on one-to-one (image, text)…

Leveraging the effective visual-text alignment and static generalizability from CLIP, recent video learners adopt CLIP initialization with further regularization or recombination for generalization in open-vocabulary action recognition…

Image classification plays a pivotal role across diverse applications, yet challenges persist when models are deployed in real-world scenarios. Notably, these models falter in detecting unfamiliar classes that were not incorporated during…

Grounding natural language to the physical world is a ubiquitous topic with a wide range of applications in computer vision and robotics. Recently, 2D vision-language models such as CLIP have been widely popularized, due to their impressive…

Contrastive learning has emerged as an efficient framework to learn multimodal representations. CLIP, a seminal work in this area, achieved impressive results by training on paired image-text data using the contrastive loss. Recent work…

In the field of vision-language contrastive learning, models such as CLIP capitalize on matched image-caption pairs as positive examples and leverage within-batch non-matching pairs as negatives. This approach has led to remarkable outcomes…