相关论文: TIPSv2: Advancing Vision-Language Pretraining with…

In this paper, we focus on enhancing a diffusion-based text-to-video (T2V) model during the post-training phase by distilling a highly capable consistency model from a pretrained T2V model. Our proposed method, T2V-Turbo-v2, introduces a…

Masked image modeling (MIM) has become a prevalent pre-training setup for vision foundation models and attains promising performance. Despite its success, existing MIM methods discard the decoder network during downstream applications,…

Knowledge distillation transfers knowledge from large teacher models to smaller students for efficient inference. While existing methods primarily focus on distillation strategies, they often overlook the importance of enhancing teacher…

The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…

Text embedding models are widely used for semantic similarity tasks, including information retrieval, clustering, and classification. General-purpose models are typically trained with single- or multi-stage processes using contrastive loss…

Recent approaches have shown that large-scale vision-language models such as CLIP can improve semantic segmentation performance. These methods typically aim for pixel-level vision-language alignment, but often rely on low resolution image…

Current foundation models for 3D shapes excel at global tasks (retrieval, classification) but transfer poorly to local part-level reasoning. Recent approaches leverage vision and language foundation models to directly solve dense tasks…

The creation of high-quality human-labeled image-caption datasets presents a significant bottleneck in the development of Visual-Language Models (VLMs). In this work, we investigate an approach that leverages the strengths of Large Language…

Recent advancements in diffusion models have showcased their impressive capacity to generate visually striking images. Nevertheless, ensuring a close match between the generated image and the given prompt remains a persistent challenge. In…

Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher, with the teacher being conditioned on privileged information unavailable to the student. Such…

Text spotting, a task involving the extraction of textual information from image or video sequences, faces challenges in cross-domain adaption, such as image-to-image and image-to-video generalization. In this paper, we introduce a new…

Vision-language pre-training (VLP) has attracted increasing attention recently. With a large amount of image-text pairs, VLP models trained with contrastive loss have achieved impressive performance in various tasks, especially the…

Fine-grained vision-language understanding requires precise alignment between visual content and linguistic descriptions, a capability that remains limited in current models, particularly in non-English settings. While models like CLIP…

On-policy knowledge distillation has proven effective for language models, yet its application to vision-language models (VLMs) remains underexplored. We observe that standard on-policy distillation can improve a student's output quality…

Semi-supervised semantic segmentation (SSS) aims at learning rich visual knowledge from cheap unlabeled images to enhance semantic segmentation capability. Among recent works, UniMatch improves its precedents tremendously by amplifying the…

Visual language data such as plots, charts, and infographics are ubiquitous in the human world. However, state-of-the-art vision-language models do not perform well on these data. We propose MatCha (Math reasoning and Chart derendering…

Speculative decoding (SD) accelerates large language model inference by employing a faster draft model for generating multiple tokens, which are then verified in parallel by the larger target model, resulting in the text generated according…

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…

Masked image modeling (MIM) learns representations with remarkably good fine-tuning performances, overshadowing previous prevalent pre-training approaches such as image classification, instance contrastive learning, and image-text…

This paper studies the problem of pre-training for small models, which is essential for many mobile devices. Current state-of-the-art methods on this problem transfer the representational knowledge of a large network (as a Teacher) into a…