Related papers: Image-Specific Adaptation of Transformer Encoders …

Traditional deep learning methods in medical imaging often focus solely on segmentation or classification, limiting their ability to leverage shared information. Multi-task learning (MTL) addresses this by combining both tasks through…

Neural fields excel in computer vision and robotics due to their ability to understand the 3D visual world such as inferring semantics, geometry, and dynamics. Given the capabilities of neural fields in densely representing a 3D scene from…

We present an Encoder-Decoder Attention Transformer, EDAFormer, which consists of the Embedding-Free Transformer (EFT) encoder and the all-attention decoder leveraging our Embedding-Free Attention (EFA) structure. The proposed EFA is a…

Medical image segmentation plays a crucial role in advancing healthcare systems for disease diagnosis and treatment planning. The u-shaped architecture, popularly known as U-Net, has proven highly successful for various medical image…

Recently, transformer-based models have demonstrated remarkable performance on audio-visual segmentation (AVS) tasks. However, their expensive computational cost makes real-time inference impractical. By characterizing attention maps of the…

Human fashion understanding is one crucial computer vision task since it has comprehensive information for real-world applications. This focus on joint human fashion segmentation and attribute recognition. Contrary to the previous works…

In computer vision, it has achieved great transfer learning performance via adapting large-scale pretrained vision models (e.g., vision transformers) to downstream tasks. Common approaches for model adaptation either update all model…

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have…

The traditional SegNet architecture commonly encounters significant information loss during the sampling process, which detrimentally affects its accuracy in image semantic segmentation tasks. To counter this challenge, we introduce an…

We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a…

This paper introduces a novel transformer-based network architecture, FlowFormer, along with the Masked Cost Volume AutoEncoding (MCVA) for pretraining it to tackle the problem of optical flow estimation. FlowFormer tokenizes the 4D…

To address the challenges of table structure recognition, we propose a novel Split-Merge-based top-down model optimized for large, densely populated tables. Our approach formulates row and column splitting as sequence labeling tasks,…

With the rapid development of deep learning, CNN-based U-shaped networks have succeeded in medical image segmentation and are widely applied for various tasks. However, their limitations in capturing global features hinder their performance…

In this paper, we propose an encoder-decoder neural architecture (called Channelformer) to achieve improved channel estimation for orthogonal frequency-division multiplexing (OFDM) waveforms in downlink scenarios. The self-attention…

Transformers have revolutionized deep learning based computer vision with improved performance as well as robustness to natural corruptions and adversarial attacks. Transformers are used predominantly for 2D vision tasks, including image…

The primary challenge in accelerating image super-resolution lies in reducing computation while maintaining performance and adaptability. Motivated by the observation that high-frequency regions (e.g., edges and textures) are most critical…

This paper proposes a method for generating images of customized objects specified by users. The method is based on a general framework that bypasses the lengthy optimization required by previous approaches, which often employ a per-object…

The optimal training of a vision transformer for brain encoding depends on three factors: model size, data size, and computational resources. This study investigates these three pillars, focusing on the effects of data scaling, model…

Recently, visual encoding based on functional magnetic resonance imaging (fMRI) have realized many achievements with the rapid development of deep network computation. Visual encoding model is aimed at predicting brain activity in response…

Image segmentation plays an important role in vision understanding. Recently, the emerging vision foundation models continuously achieved superior performance on various tasks. Following such success, in this paper, we prove that the…