Related papers: Unfolding Once is Enough: A Deployment-Friendly Tr…

Underwater Image Enhancement (UIE) is essential for robust visual perception in marine applications. However, existing methods predominantly rely on uniform mapping tailored to average dataset distributions, leading to over-processing…

Implicit neural representations (INRs) have emerged as powerful tools for encoding signals, yet dominant MLP-based designs often suffer from slow convergence, overfitting to noise, and poor extrapolation. We introduce FUTON (Fourier Tensor…

In this paper, we present Uformer, an effective and efficient Transformer-based architecture for image restoration, in which we build a hierarchical encoder-decoder network using the Transformer block. In Uformer, there are two core…

Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation. With an isotropic architecture that chains a series of transformer blocks, DiTs demonstrate competitive performance…

Vision Transformers and U-Net architectures have been widely adopted in the implementation of Diffusion Models. However, each architecture presents specific challenges while realizing them on-device. Vision Transformers require positional…

U-Net is widely used in medical image segmentation due to its simple and flexible architecture design. To address the challenges of scale and complexity in medical tasks, several variants of U-Net have been proposed. In particular, methods…

Recently, diffusion-based video generation models have achieved significant success. However, existing models often suffer from issues like weak consistency and declining image quality over time. To overcome these challenges, inspired by…

Hyperspectral single image super-resolution (SISR) is a challenging task due to the difficulty of restoring fine spatial details while preserving spectral fidelity across a wide range of wavelengths, which limits the performance of…

As an important area in computer vision, object tracking has formed two separate communities that respectively study Single Object Tracking (SOT) and Multiple Object Tracking (MOT). However, current methods in one tracking scenario are not…

Single-Image-Super-Resolution (SISR) is a classical computer vision problem that has benefited from the recent advancements in deep learning methods, especially the advancements of convolutional neural networks (CNN). Although…

Miniaturized autonomous unmanned aerial vehicles (UAVs) are gaining popularity due to their small size, enabling new tasks such as indoor navigation or people monitoring. Nonetheless, their size and simple electronics pose severe challenges…

Owing to the success of transformer models, recent works study their applicability in 3D medical segmentation tasks. Within the transformer models, the self-attention mechanism is one of the main building blocks that strives to capture…

Solid results from Transformers have made them prevailing architectures in various natural language and vision tasks. As a default component in Transformers, Layer Normalization (LN) normalizes activations within each token to boost the…

The recent 3D medical ViTs (e.g., SwinUNETR) achieve the state-of-the-art performances on several 3D volumetric data benchmarks, including 3D medical image segmentation. Hierarchical transformers (e.g., Swin Transformers) reintroduced…

Scene Text Image Super-Resolution (STISR) aims to restore high-resolution details in low-resolution text images, which is crucial for both human readability and machine recognition. Existing methods, however, often depend on external…

Network densification is a promising cellular deployment technique that leverages spatial reuse to enhance coverage and throughput. Recent work has identified that at some point ultra-densification will no longer be able to deliver…

Quantization is essential to simplify DNN inference in edge applications. Existing uniform and non-uniform quantization methods, however, exhibit an inherent conflict between the representing range and representing resolution, and thereby…

Single Image Super-Resolution (SISR) is a fundamental computer vision task that aims to reconstruct a high-resolution (HR) image from a low-resolution (LR) input. Transformer-based methods have achieved remarkable performance by modeling…

Photonic computing has emerged as a promising substrate for accelerating the dense linear-algebra operations at the heart of AI, yet adoption for large Transformer models remains in its infancy. We identify two bottlenecks: (1) costly…

Deploying large-scale transformer models on edge devices presents significant challenges due to strict constraints on memory, compute, and latency. In this work, we propose a lightweight yet effective multi-stage optimization pipeline…