Related papers: SDTP: Semantic-aware Decoupled Transformer Pyramid…

Transformers are the mainstream of NLP applications and are becoming increasingly popular in other domains such as Computer Vision. Despite the improvements in model quality, the enormous computation costs make Transformers difficult at…

Knowledge distillation (KD) in transformers often faces challenges due to misalignment in the number of attention heads between teacher and student models. Existing methods either require identical head counts or introduce projectors to…

Graph Transformers (GTs) have recently achieved significant success in the graph domain by effectively capturing both long-range dependencies and graph inductive biases. However, these methods face two primary challenges: (1) multi-view…

To improve the prediction of cancer survival using whole-slide images and transcriptomics data, it is crucial to capture both modality-shared and modality-specific information. However, multimodal frameworks often entangle these…

Medical image recognition serves as a key way to aid in clinical diagnosis, enabling more accurate and timely identification of diseases and abnormalities. Vision transformer-based approaches have proven effective in handling various…

Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works…

Feature interactions across space and scales underpin modern visual recognition systems because they introduce beneficial visual contexts. Conventionally, spatial contexts are passively hidden in the CNN's increasing receptive fields or…

Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks. In this work, we revisit the design…

Image restoration is a long-standing task that seeks to recover the latent sharp image from its deteriorated counterpart. Due to the robust capacity of self-attention to capture long-range dependencies, transformer-based methods or some…

Dense prediction in medical volume provides enriched guidance for clinical analysis. CNN backbones have met bottleneck due to lack of long-range dependencies and global context modeling power. Recent works proposed to combine vision…

Semantic segmentation in cataract surgery has a wide range of applications contributing to surgical outcome enhancement and clinical risk reduction. However, the varying issues in segmenting the different relevant structures in these…

Mechanistic interpretability improves the safety, reliability, and robustness of large AI models. This study examined individual attention heads in vision transformers (ViTs) fine tuned on distorted 2D spectrogram images containing non…

Semantic segmentation is a challenging problem due to difficulties in modeling context in complex scenes and class confusions along boundaries. Most literature either focuses on context modeling or boundary refinement, which is less…

Saliency Prediction aims to predict the attention distribution of human eyes given an RGB image. Most of the recent state-of-the-art methods are based on deep image feature representations from traditional CNNs. However, the traditional…

Semantic segmentation is a fundamental task in multimedia processing, which can be used for analyzing, understanding, editing contents of images and videos, among others. To accelerate the analysis of multimedia data, existing segmentation…

Holistic scene understanding includes semantic segmentation, surface normal estimation, object boundary detection, depth estimation, etc. The key aspect of this problem is to learn representation effectively, as each subtask builds upon not…

The self-attention mechanism, a cornerstone of Transformer-based state-of-the-art deep learning architectures, is largely heuristic-driven and fundamentally challenging to interpret. Establishing a robust theoretical foundation to explain…

Traffic sign detection is a vital task in the visual system of self-driving cars and the automated driving system. Recently, novel Transformer-based models have achieved encouraging results for various computer vision tasks. We still…

Deep image prior (DIP) proposed in recent research has revealed the inherent trait of convolutional neural networks (CNN) for capturing substantial low-level image statistics priors. This framework efficiently addresses the inverse problems…

Semantic segmentation is one of the core tasks in the field of computer vision, and its goal is to accurately classify each pixel in an image. The traditional Unet model achieves efficient feature extraction and fusion through an…