Related papers: CanViT: Toward Active-Vision Foundation Models

Although convolutional neural networks (CNNs) showed remarkable results in many vision tasks, they are still strained by simple yet challenging visual reasoning problems. Inspired by the recent success of the Transformer network in computer…

Vision transformers (ViT) usually extract features via forwarding all the tokens in the self-attention layers from top to toe. In this paper, we introduce dynamic token-pass vision transformers (DoViT) for semantic segmentation, which can…

We present Recurrent Vision Transformers (RVTs), a novel backbone for object detection with event cameras. Event cameras provide visual information with sub-millisecond latency at a high-dynamic range and with strong robustness against…

Large vision-language models (VLMs) have advanced multimodal tasks such as video question answering (QA). However, VLMs face the challenge of selecting frames effectively and efficiently, as standard uniform sampling is expensive and…

Vision transformer (ViT) has been widely applied in many areas due to its self-attention mechanism that help obtain the global receptive field since the first layer. It even achieves surprising performance exceeding CNN in some vision…

Learning efficient and expressive visual representation has long been the pursuit of computer vision research. While Vision Transformers (ViTs) gradually replace traditional Convolutional Neural Networks (CNNs) as more scalable vision…

In recent years, large-scale visual backbones have demonstrated remarkable capabilities in learning general-purpose features from images via extensive pre-training. Concurrently, many efficient architectures have emerged that have…

Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to convolutional neural network (CNN)-based models. However, ViTs are mainly designed for image classification that generate single-scale…

Transformers have recently gained significant attention in the computer vision community. However, the lack of scalability of self-attention mechanisms with respect to image size has limited their wide adoption in state-of-the-art vision…

In this work, we introduce Dual Attention Vision Transformers (DaViT), a simple yet effective vision transformer architecture that is able to capture global context while maintaining computational efficiency. We propose approaching the…

Prediction, decision-making, and motion planning are essential for autonomous driving. In most contemporary works, they are considered as individual modules or combined into a multi-task learning paradigm with a shared backbone but separate…

Masked Image Modeling (MIM) is a new self-supervised vision pre-training paradigm using a Vision Transformer (ViT). Previous works can be pixel-based or token-based, using original pixels or discrete visual tokens from parametric tokenizer…

Vision Transformer (ViT) has achieved excellent performance and demonstrated its promising potential in various computer vision tasks. The wide deployment of ViT in real-world tasks requires a thorough understanding of the societal impact…

Recent works have demonstrated that transformer can achieve promising performance in computer vision, by exploiting the relationship among image patches with self-attention. While they only consider the attention in a single feature layer,…

Many vision-language tasks can be reduced to the problem of sequence prediction for natural language output. In particular, recent advances in image captioning use deep reinforcement learning (RL) to alleviate the "exposure bias" during…

Robotic manipulation in complex scenes demands precise perception of task-relevant details, yet fixed or suboptimal viewpoints often impair fine-grained perception and induce occlusions, constraining imitation-learned policies. We present…

Due to its deficiency in prior knowledge (inductive bias), Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. Moreover, the growing layers and parameters in ViT models impede their applicability to…

Low-level vision involves a wide spectrum of tasks, including image restoration, enhancement, stylization, and feature extraction, which differ significantly in both task formulation and output domains. To address the challenge of unified…

Recently, masked image modeling (MIM) has become a promising direction for visual pre-training. In the context of vision transformers, MIM learns effective visual representation by aligning the token-level features with a pre-defined space…

Facial Beauty Prediction (FBP) has made significant strides with the application of deep learning, yet state-of-the-art models often exhibit critical limitations, including architectural constraints, inherent demographic biases, and a lack…