Related papers: CLIMP: Contrastive Language-Image Mamba Pretrainin…

Recent Mamba-based architectures for video understanding demonstrate promising computational efficiency and competitive performance, yet struggle with overfitting issues that hinder their scalability. To overcome this challenge, we…

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

Leveraging pre-trained 2D image representations in behavior cloning policies has achieved great success and has become a standard approach for robotic manipulation. However, such representations fail to capture the 3D spatial information…

Large-scale Pre-Training Vision-Language Model such as CLIP has demonstrated outstanding performance in zero-shot classification, e.g. achieving 76.3% top-1 accuracy on ImageNet without seeing any example, which leads to potential benefits…

Recent research has shown that CLIP models struggle with visual reasoning tasks that require grounding compositionality, understanding spatial relationships, or capturing fine-grained details. One natural hypothesis is that the CLIP vision…

Contrastive Language-Image Pre-training (CLIP) excels in global alignment with language but exhibits limited sensitivity to spatial information, leading to strong performance in zero-shot classification tasks but underperformance in tasks…

Recent vision-language models (VLMs) such as CLIP, OpenCLIP, EVA02-CLIP and SigLIP achieve strong zero-shot performance, but it is unclear how reliably they respond to controlled linguistic perturbations. We introduce Language-Guided…

Spatial understanding remains a key challenge in vision-language models. Yet it is still unclear whether such understanding is truly acquired, and if so, through what mechanisms. We present a controllable 1D image-text testbed to probe how…

Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. While recent studies reveal their vulnerability to adversarial attacks, research to date has primarily focused on…

CLIP (Contrastive Language-Image Pretraining) has become a popular choice for various downstream tasks. However, recent studies have questioned its ability to represent compositional concepts effectively. These works suggest that CLIP often…

Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. Various architectures, from vision transformers (ViTs) to convolutional networks (ResNets) have been trained with CLIP to…

The tremendous success of CLIP (Radford et al., 2021) has promoted the research and application of contrastive learning for vision-language pretraining. In this work, we construct a large-scale dataset of image-text pairs in Chinese, where…

We introduce Quantized Language-Image Pretraining (QLIP), a visual tokenization method that combines state-of-the-art reconstruction quality with state-of-the-art zero-shot image understanding. QLIP trains a…

Vision-language models, such as contrastive language-image pre-training (CLIP), have demonstrated impressive results in natural image domains. However, these models often struggle when applied to specialized domains like remote sensing, and…

Recent work has shown that self-supervised pre-training leads to improvements over supervised learning on challenging visual recognition tasks. CLIP, an exciting new approach to learning with language supervision, demonstrates promising…

Contrastive Language-Image Pre-training (CLIP) has become a cornerstone in vision-language representation learning, powering diverse downstream tasks and serving as the default vision backbone in multimodal large language models (MLLMs).…

Contrastive Language-Image Pre-training (CLIP) provides a foundation model by integrating natural language into visual concepts, enabling zero-shot recognition on downstream tasks. It is usually expected that satisfactory overall accuracy…

Recent advancements in Contrastive Language-Image Pre-training (CLIP) have demonstrated notable success in self-supervised representation learning across various tasks. However, the existing CLIP-like approaches often demand extensive GPU…

With the flourishing of social media platforms, vision-language pre-training (VLP) recently has received great attention and many remarkable progresses have been achieved. The success of VLP largely benefits from the information…

Recently, vision-language models like CLIP have advanced the state of the art in a variety of multi-modal tasks including image captioning and caption evaluation. Many approaches leverage CLIP for cross-modal retrieval to condition…