相关论文: Modulating early visual processing by language

When we experience a visual stimulus as beautiful, how much of that experience derives from perceptual computations we cannot describe versus conceptual knowledge we can readily translate into natural language? Disentangling perception from…

Linguistic knowledge is of great benefit to scene text recognition. However, how to effectively model linguistic rules in end-to-end deep networks remains a research challenge. In this paper, we argue that the limited capacity of language…

The analysis of vision-based deep neural networks (DNNs) is highly desirable but it is very challenging due to the difficulty of expressing formal specifications for vision tasks and the lack of efficient verification procedures. In this…

Pretrained vision-language models (VLMs) can make semantic and visual inferences across diverse settings, providing valuable common-sense priors for robotic control. However, effectively grounding this knowledge in robot behaviors remains…

Mainstream Multimodal Large Language Models (MLLMs) achieve visual understanding by using a vision projector to bridge well-pretrained vision encoders and large language models (LLMs). The inherent gap between visual and textual modalities…

Multimodal Large Language Models (MLLMs) have achieved notable gains in various tasks by incorporating Chain-of-Thought (CoT) reasoning in language spaces. Recent work extends this direction by leveraging external tools for visual editing,…

Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval…

Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…

Visual hallucinations in Large Language Models (LLMs), where the model generates responses that are inconsistent with the visual input, pose a significant challenge to their reliability, particularly in contexts where precise and…

Visual reasoning is a special visual question answering problem that is multi-step and compositional by nature, and also requires intensive text-vision interactions. We propose CMM: Cascaded Mutual Modulation as a novel end-to-end visual…

Language models demonstrate remarkable capacity to generalize representations learned in one modality to downstream tasks in other modalities. Can we trace this ability to individual neurons? We study the case where a frozen text…

Language models have recently advanced into the realm of reasoning, yet it is through multimodal reasoning that we can fully unlock the potential to achieve more comprehensive, human-like cognitive capabilities. This survey provides a…

Deep residual networks (ResNets) and their variants are widely used in many computer vision applications and natural language processing tasks. However, the theoretical principles for designing and training ResNets are still not fully…

Interpreting the learned features of vision models has posed a longstanding challenge in the field of machine learning. To address this issue, we propose a novel method that leverages the capabilities of language models to interpret the…

Referring image segmentation aims to segment an object referred to by natural language expression from an image. However, this task is challenging due to the distinct data properties between text and image, and the randomness introduced by…

Few-shot learning aims to learn representations that can tackle novel tasks given a small number of examples. Recent studies show that cross-modal learning can improve representations for few-shot classification. More specifically, language…

Humans learn to solve tasks of increasing complexity by building on top of previously acquired knowledge. Typically, there exists a natural progression in the tasks that we learn - most do not require completely independent solutions, but…

Neural module networks (NMN) have achieved success in image-grounded tasks such as Visual Question Answering (VQA) on synthetic images. However, very limited work on NMN has been studied in the video-grounded dialogue tasks. These tasks…

Recent multi-modal contrastive learning models have demonstrated the ability to learn an embedding space suitable for building strong vision classifiers, by leveraging the rich information in large-scale image-caption datasets. Our work…

Humans learn language via multi-modal knowledge. However, due to the text-only pre-training scheme, most existing pre-trained language models (PLMs) are hindered from the multi-modal information. To inject visual knowledge into PLMs,…