Related papers: PicT: A Slim Weakly Supervised Vision Transformer …

Deep learning models are increasingly utilized on resource-constrained edge devices for real-time data analytics. Recently, Vision Transformer and their variants have shown exceptional performance in various computer vision tasks. However,…

Current methods for medical image segmentation primarily focus on extracting contextual feature information from the perspective of the whole image. While these methods have shown effective performance, none of them take into account the…

We present a novel deep learning framework named the Iteratively Optimized Patch Label Inference Network (IOPLIN) for automatically detecting various pavement distresses that are not solely limited to specific ones, such as cracks and…

Multi-scale representations are crucial for semantic segmentation. The community has witnessed the flourish of semantic segmentation convolutional neural networks (CNN) exploiting multi-scale contextual information. Motivated by that the…

Recent advances in Vision Transformers (ViTs) have significantly enhanced medical image segmentation by facilitating the learning of global relationships. However, these methods face a notable challenge in capturing diverse local and global…

Vision Transformer (ViT)-based sparse multi-view 3D object detectors have achieved remarkable accuracy but still suffer from high inference latency due to heavy token processing. To accelerate these models, token compression has been widely…

Vision transformer (ViT) has achieved competitive accuracy on a variety of computer vision applications, but its computational cost impedes the deployment on resource-limited mobile devices. We explore the sparsity in ViT and observe that…

Attention-based vision models, such as Vision Transformer (ViT) and its variants, have shown promising performance in various computer vision tasks. However, these emerging architectures suffer from large model sizes and high computational…

Vision Transformers (ViTs) have recently become the state-of-the-art across many computer vision tasks. In contrast to convolutional networks (CNNs), ViTs enable global information sharing even within shallow layers of a network, i.e.,…

Recent progress in vision-language pretraining has enabled significant improvements to many downstream computer vision applications, such as classification, retrieval, segmentation and depth prediction. However, a fundamental capability…

Under high-intensity rail operations, rail tracks endure considerable stresses resulting in various defects such as corrugation and spellings. Failure to effectively detect defects and provide maintenance in time would compromise service…

Surface cracks are a common sight on public infrastructure nowadays. Recent work has been addressing this problem by supporting structural maintenance measures using machine learning methods. Those methods are used to segment surface cracks…

Automating pavement maintenance suggestions is challenging,especially for actionable recommendations such as patching location,depth and priority.It is common practice among State agencies to manually inspect road segments of interest and…

Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions. Despite having…

Automated pavement distress detection via road images is still a challenging issue among pavement researchers and computer-vision community. In recent years, advancement in deep learning has enabled researchers to develop robust tools for…

Shortcut learning is common but harmful to deep learning models, leading to degenerated feature representations and consequently jeopardizing the model's generalizability and interpretability. However, shortcut learning in the widely used…

Since Transformer has found widespread use in NLP, the potential of Transformer in CV has been realized and has inspired many new approaches. However, the computation required for replacing word tokens with image patches for Transformer…

Rapid building damage assessment is critical for post-disaster response. Damage classification models built on satellite imagery provide a scalable means of obtaining situational awareness. However, label noise and severe class imbalance in…

Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…

Diffusion Transformer (DiT) has emerged as the new trend of generative diffusion models on image generation. In view of extremely slow convergence in typical DiT, recent breakthroughs have been driven by mask strategy that significantly…