Related papers: Seeing What You Miss: Vision-Language Pre-training…

Vision-and-Language (V+L) pre-training models have achieved tremendous success in recent years on various multi-modal benchmarks. However, the majority of existing models require pre-training on a large set of parallel image-text data,…

Vision-language pre-training (VLP) methods are blossoming recently, and its crucial goal is to jointly learn visual and textual features via a transformer-based architecture, demonstrating promising improvements on a variety of…

Multi-modal Large Language Models (MLLMs) have introduced a novel dimension to document understanding, i.e., they endow large language models with visual comprehension capabilities; however, how to design a suitable image-text pre-training…

We present a simplified, task-agnostic multi-modal pre-training approach that can accept either video or text input, or both for a variety of end tasks. Existing pre-training are task-specific by adopting either a single cross-modal encoder…

Contrastive cross-modal models such as CLIP and CLAP aid various vision-language (VL) and audio-language (AL) tasks. However, there has been limited investigation of and improvement in their language encoder, which is the central component…

Autoregressive vision-language models (VLMs) can handle many tasks within a single model, yet the representations that enable this capability remain opaque. We find that VLMs align conceptually equivalent inputs into a shared task vector,…

Multimodal representation learning, exemplified by multimodal contrastive learning (MMCL) using image-text pairs, aims to learn powerful representations by aligning cues across modalities. This approach relies on the core assumption that…

We present SWIM (See What I Mean), a novel training strategy that aligns vision and language representations to enable fine-grained object understanding solely from textual prompts. Unlike existing approaches that require explicit visual…

Multimodal representation learning has shown promising improvements on various vision-language tasks. Most existing methods excel at building global-level alignment between vision and language while lacking effective fine-grained image-text…

Previous vision-language pre-training models mainly construct multi-modal inputs with tokens and objects (pixels) followed by performing cross-modality interaction between them. We argue that the input of only tokens and object features…

Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they often fail on tasks that require fine-grained visual perception, even when the required information is still present…

Foundation models have recently gained tremendous popularity in medical image analysis. State-of-the-art methods leverage either paired image-text data via vision-language pre-training or unpaired image data via self-supervised pre-training…

Vision-and-language models (VLMs) have been increasingly explored in the medical domain, particularly following the success of CLIP in general domain. However, unlike the relatively straightforward pairing of 2D images and text, curating…

Self-supervised Multi-modal Contrastive Learning (SMCL) remarkably advances modern Vision-Language Pre-training (VLP) models by aligning visual and linguistic modalities. Due to noises in web-harvested text-image pairs, however, scaling up…

Recent advances in language modeling have witnessed the rise of highly desirable emergent capabilities, such as reasoning and in-context learning. However, vision models have yet to exhibit comparable progress in these areas. In this paper,…

Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks without explicitly preserving the cross-modal semantic geometry inherited from pretraining and…

Visual Question Answering (VQA) is a multi-discipline research task. To produce the right answer, it requires an understanding of the visual content of images, the natural language questions, as well as commonsense reasoning over the…

Pretraining general-purpose visual features has become a crucial part of tackling many computer vision tasks. While one can learn such features on the extensively-annotated ImageNet dataset, recent approaches have looked at ways to allow…

Recently, vision-language joint representation learning has proven to be highly effective in various scenarios. In this paper, we specifically adapt vision-language joint learning for scene text detection, a task that intrinsically involves…

Vision-language models (VLMs), serve as foundation models for multi-modal applications such as image captioning and text-to-image generation. Recent studies have highlighted limitations in VLM text encoders, particularly in areas like…