Related papers: DLIP: Distilling Language-Image Pre-training

We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than…

For visual recognition, knowledge distillation typically involves transferring knowledge from a large, well-trained teacher model to a smaller student model. In this paper, we introduce an effective method to distill knowledge from an…

Prompt learning as a parameter-efficient method that has been widely adopted to adapt Vision-Language Models (VLMs) to downstream tasks. While hard-prompt design requires domain expertise and iterative optimization, soft-prompt methods rely…

We present Fast Language-Image Pre-training (FLIP), a simple and more efficient method for training CLIP. Our method randomly masks out and removes a large portion of image patches during training. Masking allows us to learn from more…

Vision-language pre-training (VLP) on large-scale image-text pairs has recently witnessed rapid progress for learning cross-modal representations. Existing pre-training methods either directly concatenate image representation and text…

Recent advancements in deep learning have significantly improved performance on computer vision tasks. Previous image classification methods primarily modify model architectures or add features, and they optimize models using cross-entropy…

In this work, we propose a method that leverages CLIP feature distillation, achieving efficient 3D segmentation through language guidance. Unlike previous methods that rely on multi-scale CLIP features and are limited by processing speed…

This work explores knowledge distillation (KD) for visually-rich document (VRD) applications such as document layout analysis (DLA) and document image classification (DIC). While VRD research is dependent on increasingly sophisticated and…

Despite recent advances in Vision-Language Models (VLMs), they may over-rely on visual language priors existing in their training data rather than true visual reasoning. To investigate this, we introduce ViLP, a benchmark featuring…

This paper examines the robustness of a multi-modal computer vision model, CLIP (Contrastive Language-Image Pretraining), in the context of unsupervised learning. The main objective is twofold: first, to evaluate the robustness of CLIP, and…

Pre-trained language-vision models have shown remarkable performance on the visual question answering (VQA) task. However, most pre-trained models are trained by only considering monolingual learning, especially the resource-rich language…

Contrastive Language-Image Pre-training (CLIP) models excel in integrating semantic information between images and text through contrastive learning techniques. It has achieved remarkable performance in various multimodal tasks. However,…

Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts…

Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory…

Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We observe a regional-to-global perception gap: the same MLLM…

Vision-Language Action (VLA) models significantly advance robotic manipulation by leveraging the strong perception capabilities of pretrained vision-language models (VLMs). By integrating action modules into these pretrained models, VLA…

Large-scale image-text contrastive pre-training models, such as CLIP, have been demonstrated to effectively learn high-quality multimodal representations. However, there is limited research on learning video-text representations for general…

Large-scale vision-language models (VLMs) have shown a strong zero-shot generalization capability on unseen-domain data. However, adapting pre-trained VLMs to a sequence of downstream tasks often leads to the forgetting of previously…

Transformer-based architectures have become the de-facto standard models for diverse vision tasks owing to their superior performance. As the size of the models continues to scale up, model distillation becomes extremely important in…

Despite the success of Vision-Language Models (VLMs) like CLIP in aligning vision and language, their proficiency in detailed, fine-grained visual comprehension remains a key challenge. We present CLIP-IN, a novel framework that bolsters…