English
Related papers

Related papers: LDA-AQU: Adaptive Query-guided Upsampling via Loca…

200 papers

The space of task-agnostic feature upsampling has emerged as a promising area of research to efficiently create denser features from pre-trained visual backbones. These methods act as a shortcut to achieve dense features for a fraction of…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Matthew Walmer , Saksham Suri , Anirud Aggarwal , Abhinav Shrivastava

Feature upsampling is a fundamental and indispensable ingredient of almost all current network structures for dense prediction tasks. Recently, a popular similarity-based feature upsampling pipeline has been proposed, which utilizes a…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Minghao Zhou , Hong Wang , Yefeng Zheng , Deyu Meng

This paper presents an unsupervised deep-learning framework named Local Deep-Feature Alignment (LDFA) for dimension reduction. We construct neighbourhood for each data sample and learn a local Stacked Contractive Auto-encoder (SCAE) from…

Computer Vision and Pattern Recognition · Computer Science 2019-04-23 Jian Zhang , Jun Yu , Dacheng Tao

Attention mechanisms have significantly advanced visual models by capturing global context effectively. However, their reliance on large-scale datasets and substantial computational resources poses challenges in data-scarce and…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Chenghao Li , Chaoning Zhang , Boheng Zeng , Yi Lu , Pengbo Shi , Qingzi Chen , Jirui Liu , Lingyun Zhu , Yang Yang , Heng Tao Shen

Local quantum annealing (LQA), an iterative algorithm, is designed to solve combinatorial optimization problems. It draws inspiration from QA, which utilizes adiabatic time evolution to determine the global minimum of a given objective…

Quantum Physics · Physics 2025-01-07 Shunta Arai , Satoshi Takabe

Convolutional layers are an integral part of many deep neural network solutions in computer vision. Recent work shows that replacing the standard convolution operation with mechanisms based on self-attention leads to improved performance on…

Computer Vision and Pattern Recognition · Computer Science 2020-12-21 Souvik Kundu , Hesham Mostafa , Sharath Nittur Sridhar , Sairam Sundaresan

Medical image segmentation methods downsample images for feature extraction and then upsample them to restore resolution for pixel-level predictions. In such a schema, upsample technique is vital in restoring information for better…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Yijiang Li , Wentian Cai , Ying Gao , Chengming Li , Xiping Hu

Self-attention mechanism has been a key factor in the recent progress of Vision Transformer (ViT), which enables adaptive feature extraction from global contexts. However, existing self-attention methods either adopt sparse global attention…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Xuran Pan , Tianzhu Ye , Zhuofan Xia , Shiji Song , Gao Huang

Question answering (QA) has recently shown impressive results for answering questions from customized domains. Yet, a common challenge is to adapt QA models to an unseen target domain. In this paper, we propose a novel self-supervised…

Computation and Language · Computer Science 2022-10-21 Zhenrui Yue , Huimin Zeng , Bernhard Kratzwald , Stefan Feuerriegel , Dong Wang

Medical image segmentation has seen significant improvements with transformer models, which excel in grasping far-reaching contexts and global contextual information. However, the increasing computational demands of these models,…

Computer Vision and Pattern Recognition · Computer Science 2023-09-04 Reza Azad , Leon Niggemeier , Michael Huttemann , Amirhossein Kazerouni , Ehsan Khodapanah Aghdam , Yury Velichko , Ulas Bagci , Dorit Merhof

Point set is arguably the most direct approximation of an object or scene surface, yet its practical acquisition often suffers from the shortcoming of being noisy, sparse, and possibly incomplete, which restricts its use for a high-quality…

Computer Vision and Pattern Recognition · Computer Science 2020-09-11 Jiehong Lin , Xian Shi , Yuan Gao , Ke Chen , Kui Jia

Monocular depth estimation (MDE) has attracted intense study due to its low cost and critical functions for robotic tasks such as localization, mapping and obstacle detection. Supervised approaches have led to great success with the advance…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Shao-Yuan Lo , Wei Wang , Jim Thomas , Jingjing Zheng , Vishal M. Patel , Cheng-Hao Kuo

Most recent works on optical flow use convex upsampling as the last step to obtain high-resolution flow. In this work, we show and discuss several issues and limitations of this currently widely adopted convex upsampling approach. We…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Alexander Gielisse , Nergis Tömen , Jan van Gemert

Facial action unit (AU) detection and face alignment are two highly correlated tasks since facial landmarks can provide precise AU locations to facilitate the extraction of meaningful local features for AU detection. Most existing AU…

Computer Vision and Pattern Recognition · Computer Science 2018-11-20 Zhiwen Shao , Zhilei Liu , Jianfei Cai , Lizhuang Ma

Multi-scale deformable attention (MSDA) is a flexible and powerful feature extraction mechanism for visual tasks, but its random-access grid sampling strategy poses significant optimization challenges, especially on domain-specific…

Performance · Computer Science 2025-05-21 Chenghuan Huang , Zhigeng Xu , Chong Sun , Chen Li , Ziyang Ma

Convolutional networks have been the paradigm of choice in many computer vision applications. The convolution operation however has a significant weakness in that it only operates on a local neighborhood, thus missing global information.…

Computer Vision and Pattern Recognition · Computer Science 2020-09-11 Irwan Bello , Barret Zoph , Ashish Vaswani , Jonathon Shlens , Quoc V. Le

Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities. These models have recently shown promising results for modeling discrete sequences, but they are non-trivial…

Computation and Language · Computer Science 2018-06-19 Matthias Sperber , Jan Niehues , Graham Neubig , Sebastian Stüker , Alex Waibel

We show that learning affinity in upsampling provides an effective and efficient approach to exploit pairwise interactions in deep networks. Second-order features are commonly used in dense prediction to build adjacent relations with a…

Computer Vision and Pattern Recognition · Computer Science 2020-12-01 Yutong Dai , Hao Lu , Chunhua Shen

We propose Frequency-Guided Attention (FGA), a lightweight upsampling module for single image super-resolution. Conventional upsamplers, such as Sub-Pixel Convolution, are efficient but frequently fail to reconstruct high-frequency details…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Daejune Choi , Youchan No , Jinhyung Lee , Duksu Kim

Many successful learning targets such as minimizing dice loss and cross-entropy loss have enabled unprecedented breakthroughs in segmentation tasks. Beyond these semantic metrics, this paper aims to introduce location supervision into…

Computer Vision and Pattern Recognition · Computer Science 2019-11-15 Xiangyu He , Zitao Mo , Qiang Chen , Anda Cheng , Peisong Wang , Jian Cheng
‹ Prev 1 2 3 10 Next ›