English
Related papers

Related papers: Tiny-VBF: Resource-Efficient Vision Transformer ba…

200 papers

Objective: Transformers, born to remedy the inadequate receptive fields of CNNs, have drawn explosive attention recently. However, the daunting computational complexity of global representation learning, together with rigid window…

Computer Vision and Pattern Recognition · Computer Science 2023-04-20 Xian Lin , Li Yu , Kwang-Ting Cheng , Zengqiang Yan

Transformers, the de-facto standard for language modeling, have been recently applied for vision tasks. This paper introduces sparse queries for vision transformers to exploit the intrinsic spatial redundancy of natural images and save…

Computer Vision and Pattern Recognition · Computer Science 2023-01-11 Lin Song , Songyang Zhang , Songtao Liu , Zeming Li , Xuming He , Hongbin Sun , Jian Sun , Nanning Zheng

Recent advances in fMRI-based visual decoding have enabled compelling reconstructions of perceived images. However, most approaches rely on subject-specific training, limiting scalability and practical deployment. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Chenqian Le , Yilin Zhao , Nikasadat Emami , Kushagra Yadav , Xujin "Chris" Liu , Xupeng Chen , Yao Wang

We present TinyBEV, a unified, camera only Bird's Eye View (BEV) framework that distills the full-stack capabilities of a large planning-oriented teacher (UniAD [19]) into a compact, real-time student model. Unlike prior efficient camera…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Reeshad Khan , John Gauch

Objective: Ultrasound elastography is gaining traction as an accessible and useful diagnostic tool for such things as cancer detection and differentiation and thyroid disease diagnostics. Unfortunately, state of the art shear wave imaging…

Machine Learning · Computer Science 2019-07-31 Micha Feigin , Daniel Freedman , Brian W. Anthony

The transformer architectures with attention mechanisms have obtained success in Nature Language Processing (NLP), and Vision Transformers (ViTs) have recently extended the application domains to various vision tasks. While achieving high…

Machine Learning · Computer Science 2022-02-21 Mengshu Sun , Haoyu Ma , Guoliang Kang , Yifan Jiang , Tianlong Chen , Xiaolong Ma , Zhangyang Wang , Yanzhi Wang

Plane Wave imaging enables many applications that require high frame rates, including localisation microscopy, shear wave elastography, and ultra-sensitive Doppler. To alleviate the degradation of image quality with respect to conventional…

Signal Processing · Electrical Eng. & Systems 2021-12-24 Nishith Chennakeshava , Ben Luijten , Massimo Mischi , Yonina C. Eldar , Ruud J. G. van Sloun

In the field of computer vision, visible light images often exhibit low contrast in low-light conditions, presenting a significant challenge. While infrared imagery provides a potential solution, its utilization entails high costs and…

Computer Vision and Pattern Recognition · Computer Science 2024-04-30 Yijia Chen , Pinghua Chen , Xiangxin Zhou , Yingtie Lei , Ziyang Zhou , Mingxian Li

Millimeter wave (mmWave) communication, utilizing beamforming techniques to address the inherent path loss limitation, is considered as one of the key technologies to support ever increasing high throughput and low latency demands of…

Networking and Internet Architecture · Computer Science 2026-02-17 Muhammad Baqer Mollah , Honggang Wang , Mohammad Ataul Karim , Hua Fang

We present TVF (Time-Varying Filtering), a low-latency speech enhancement model with 1 million parameters. Combining the interpretability of Digital Signal Processing (DSP) with the adaptability of deep learning, TVF bridges the gap between…

Sound · Computer Science 2026-03-04 Riccardo Rota , Kiril Ratmanski , Jozef Coldenhoff , Milos Cernak

Millimeter Wave (mmWave) communications with full-duplex (FD) have the potential of increasing the spectral efficiency, relative to those with half-duplex. However, the residual self-interference (SI) from FD and high pathloss inherent to…

Signal Processing · Electrical Eng. & Systems 2020-04-20 Shaocheng Huang , Yu Ye , Ming Xiao

Advances in latent diffusion models (LDMs) have revolutionized high-resolution image generation, but the design space of the autoencoder that is central to these systems remains underexplored. In this paper, we introduce LiteVAE, a new…

Machine Learning · Computer Science 2025-01-22 Seyedmorteza Sadat , Jakob Buhmann , Derek Bradley , Otmar Hilliges , Romann M. Weber

Miniature imaging systems are essential for space-constrained applications but are limited by memory and power constraints. While machine learning can reduce data size by extracting key features, its high energy demands often exceed the…

Hardware Architecture · Computer Science 2025-12-02 Yuyang Li , Swasthik Muloor , Jack Laudati , Nickolas Dematteis , Yidam Park , Hana Kim , Nathan Chang , Inhee Lee

The rapid development of coherent short-wavelength light sources in the extreme ultraviolet (EUV) and soft X-ray (SXR) regimes has created a growing need for advanced optoelectronic detection capabilities, particularly for…

Instrumentation and Detectors · Physics 2026-05-26 Ivan Ryger , Terry Brown , Dina S. Eissa , Chen-Ting Liao

Adaptive beamforming can lead to substantial improvement in resolution and contrast of ultrasound images over standard delay and sum beamforming. Here we introduce the adaptive time-channel (ATC) beamformer, a data-driven approach that…

Signal Processing · Electrical Eng. & Systems 2021-10-19 Avner Shultzman , Oded Drori , Yonina C. Eldar

Visual prompting has recently emerged as an efficient strategy to adapt vision models using lightweight, learnable parameters injected into the input space. However, prior work mainly targets large Vision Transformers and high-resolution…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Salim Khazem

Vision Transformer (ViT) models have made breakthroughs in image embedding extraction, which provide state-of-the-art performance in tasks such as zero-shot image classification. However, the models suffer from a high computational burden.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Takahiro Naruko , Hiroaki Akutsu

Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Linxiang Su

Structured illumination microscopy (SIM) is an important super-resolution based microscopy technique that breaks the diffraction limit and enhances optical microscopy systems. With the development of biology and medical engineering, there…

Image and Video Processing · Electrical Eng. & Systems 2021-11-18 Xi Cheng , Jun Li , Qiang Dai , Zhenyong Fu , Jian Yang

Most change detection models based on vision transformers currently follow a "pretraining then fine-tuning" strategy. This involves initializing the model weights using large scale classification datasets, which can be either natural images…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Yang Zhao , Yuxiang Zhang , Yanni Dong , Bo Du