Related papers: Centroid-centered Modeling for Efficient Vision Tr…
Vision Transformers (ViTs) are widely adopted in medical imaging tasks, and some existing efforts have been directed towards vision-language training for Chest X-rays (CXRs). However, we envision that there still exists a potential for…
For medical image semantic segmentation (MISS), Vision Transformers have emerged as strong alternatives to convolutional neural networks thanks to their inherent ability to capture long-range correlations. However, existing research uses…
This paper investigates two techniques for developing efficient self-supervised vision transformers (EsViT) for visual representation learning. First, we show through a comprehensive empirical study that multi-stage architectures with…
We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. Our method leverages global context self-attention modules, joint with standard local…
Pre-trained vision models (PVMs) are fundamental to modern robotics, yet their optimal configuration remains unclear. Through systematic evaluation, we find that while DINO and iBOT outperform MAE across visuomotor control and perception…
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…
We address the task of weakly-supervised few-shot image classification and segmentation, by leveraging a Vision Transformer (ViT) pretrained with self-supervision. Our proposed method takes token representations from the self-supervised ViT…
In stereo matching, CNNs have traditionally served as the predominant architectures. Although Transformer-based stereo models have been studied recently, their performance still lags behind CNN-based stereo models due to the inherent data…
Cell-level dense prediction is central to computational pathology, but remains challenging due to fine-grained histological structures, strong domain shifts, and costly dense annotations. Existing ViT-based pathology foundation models rely…
This work proposes a semantic segmentation network that produces high-quality uncertainty estimates in a single forward pass. We exploit general representations from foundation models and unlabelled datasets through a Masked Image Modeling…
Vision Transformer (ViT) has shown its advantages over the convolutional neural network (CNN) with its ability to capture global long-range dependencies for visual representation learning. Besides ViT, contrastive learning is another…
Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…
Although vision Transformers have achieved excellent performance as backbone models in many vision tasks, most of them intend to capture global relations of all tokens in an image or a window, which disrupts the inherent spatial and local…
We propose a deep network that can be trained to tackle image reconstruction and classification problems that involve detection of multiple object instances, without any supervision regarding their whereabouts. The network learns to extract…
Generative transformers have experienced rapid popularity growth in the computer vision community in synthesizing high-fidelity and high-resolution images. The best generative transformer models so far, however, still treat an image naively…
In digital pathology, whole slide images (WSIs) are widely used for applications such as cancer diagnosis and prognosis prediction. Visual transformer models have recently emerged as a promising method for encoding large regions of WSIs…
Vision Transformers (ViTs) emerge to achieve impressive performance on many data-abundant computer vision tasks by capturing long-range dependencies among local features. However, under few-shot learning (FSL) settings on small datasets…
CutMix is a vital augmentation strategy that determines the performance and generalization ability of vision transformers (ViTs). However, the inconsistency between the mixed images and the corresponding labels harms its efficacy. Existing…
Recent vision transformer based video models mostly follow the ``image pre-training then finetuning" paradigm and have achieved great success on multiple video benchmarks. However, full finetuning such a video model could be computationally…
This paper presents a novel approach to address the challenges of understanding the prediction process and debugging prediction errors in Vision Transformers (ViT), which have demonstrated superior performance in various computer vision…