中文
相关论文

相关论文: DRKF: Distilled Rotated Kernel Fusion for Efficien…

200 篇论文

The detection of moving infrared dim-small targets has been a challenging and prevalent research topic. The current state-of-the-art methods are mainly based on ConvLSTM to aggregate information from adjacent frames to facilitate the…

计算机视觉与模式识别 · 计算机科学 2024-07-11 Dengyan Luo , Yanping Xiang , Hu Wang , Luping Ji , Shuai Li , Mao Ye

Optical coherence tomography (OCT) is a prevalent, interferometric, high-resolution imaging method with broad biomedical applications. Nonetheless, OCT images suffer from an artifact, called speckle which degrades the image quality. Digital…

Image fusion aims to integrate complementary information from multiple input images acquired through various sources to synthesize a new fused image. Existing methods usually employ distinct constraint designs tailored to specific scenes,…

计算机视觉与模式识别 · 计算机科学 2024-11-05 Bing Cao , Xingxin Xu , Pengfei Zhu , Qilong Wang , Qinghua Hu

The challenge in fine-grained visual categorization lies in how to explore the subtle differences between different subclasses and achieve accurate discrimination. Previous research has relied on large-scale annotated data and pre-trained…

计算机视觉与模式识别 · 计算机科学 2024-05-16 Tianxu Wu , Shuo Ye , Shuhuang Chen , Qinmu Peng , Xinge You

Recognition of handwritten words continues to be an important problem in document analysis and recognition. Existing approaches extract hand-engineered features from word images--which can perform poorly with new data sets. Recently, deep…

计算机视觉与模式识别 · 计算机科学 2016-12-06 Gang Chen , Yawei Li , Sargur N. Srihari

Random feature (RF) has been widely used for node consistency in decentralized kernel ridge regression (KRR). Currently, the consistency is guaranteed by imposing constraints on coefficients of features, necessitating that the random…

机器学习 · 计算机科学 2024-09-23 Ruikai Yang , Fan He , Mingzhen He , Jie Yang , Xiaolin Huang

Joint image filters are used to transfer structural details from a guidance picture used as a prior to a target image, in tasks such as enhancing spatial resolution and suppressing noise. Previous methods based on convolutional neural…

计算机视觉与模式识别 · 计算机科学 2020-10-22 Beomjun Kim , Jean Ponce , Bumsub Ham

The enhancement of 3D object detection is pivotal for precise environmental perception and improved task execution capabilities in autonomous driving. LiDAR point clouds, offering accurate depth information, serve as a crucial information…

计算机视觉与模式识别 · 计算机科学 2024-03-12 Leichao Cui , Xiuxian Li , Min Meng , Guangyu Jia

Distributed learning frameworks often rely on exchanging model parameters across workers, instead of revealing their raw data. A prime example is federated learning that exchanges the gradients or weights of each neural network model. Under…

机器学习 · 计算机科学 2020-11-05 Hyowoon Seo , Jihong Park , Seungeun Oh , Mehdi Bennis , Seong-Lyun Kim

Modern perception increasingly relies on fisheye, panoramic, and other wide field-of-view (FoV) cameras, yet most pipelines still apply planar CNNs designed for pinhole imagery on 2D grids, where pixel-space neighborhoods misrepresent…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Mukai Yu , Mosam Dabhi , Liuyue Xie , Sebastian Scherer , László A. Jeni

Multi-source data classification is a critical yet challenging task for remote sensing image interpretation. Existing methods lack adaptability to diverse land cover types when modeling frequency domain features. To this end, we propose a…

图像与视频处理 · 电气工程与系统科学 2025-07-08 Yikang Zhao , Feng Gao , Xuepeng Jin , Junyu Dong , Qian Du

Purpose: To develop an algorithm for robust partial Fourier (PF) reconstruction applicable to diffusion-weighted (DW) images with non-smooth phase variations. Methods: Based on an unrolled proximal splitting algorithm, a neural network…

图像与视频处理 · 电气工程与系统科学 2022-01-11 Fasil Gadjimuradov , Thomas Benkert , Marcel Dominik Nickel , Andreas Maier

Although Convolutional Neural Networks (CNNs) have achieved promising results in image classification, they still are vulnerable to affine transformations including rotation, translation, flip and shuffle. The drawback motivates us to…

计算机视觉与模式识别 · 计算机科学 2023-12-14 Zijie Tan , Guanfang Dong , Chenqiu Zhao , Anup Basu

In recent years, Convolutional Neural Networks (CNNs) have enabled ubiquitous image processing applications. As such, CNNs require fast runtime (forward propagation) to process high-resolution visual streams in real time. This is still a…

计算机视觉与模式识别 · 计算机科学 2022-03-23 Jinlin Xiang , Shane Colburn , Arka Majumdar , Eli Shlizerman

Generalizable NeRF aims to synthesize novel views for unseen scenes. Common practices involve constructing variance-based cost volumes for geometry reconstruction and encoding 3D descriptors for decoding novel views. However, existing…

计算机视觉与模式识别 · 计算机科学 2024-04-29 Tianqi Liu , Xinyi Ye , Min Shi , Zihao Huang , Zhiyu Pan , Zhan Peng , Zhiguo Cao

Novel view synthesis from a single image requires inferring occluded regions of objects and scenes whilst simultaneously maintaining semantic and physical consistency with the input. Existing approaches condition neural radiance fields…

计算机视觉与模式识别 · 计算机科学 2023-02-21 Jiatao Gu , Alex Trevithick , Kai-En Lin , Josh Susskind , Christian Theobalt , Lingjie Liu , Ravi Ramamoorthi

Occluded person re-identification aims to retrieve holistic images based on occluded ones. Existing methods often rely on aligning visible body parts, applying occlusion augmentation, or complementing missing semantics using holistic…

计算机视觉与模式识别 · 计算机科学 2025-07-14 Yufei Zheng , Wenjun Wang , Wenjun Gan , Jiawei Liu

Transformers are successfully applied to computer vision due to their powerful modeling capacity with self-attention. However, the excellent performance of transformers heavily depends on enormous training images. Thus, a data-efficient…

计算机视觉与模式识别 · 计算机科学 2022-04-29 Xianing Chen , Qiong Cao , Yujie Zhong , Jing Zhang , Shenghua Gao , Dacheng Tao

Dynamic convolution enhances model capacity by adaptively combining multiple kernels, yet faces critical trade-offs: prior works either (1) incur significant parameter overhead by scaling kernel numbers linearly, (2) compromise inference…

计算机视觉与模式识别 · 计算机科学 2025-11-18 Haiduo Huang , Yadong Zhang , Yinghui Xu , Pengju Ren

We hypothesize that a key bottleneck in generalizable robot manipulation is not solely data scale or policy capacity, but a structural mismatch between current visual backbones and the physical requirements of closed-loop control. While…

机器人学 · 计算机科学 2026-02-13 Yu Deng , Yufeng Jin , Xiaogang Jia , Jiahong Xue , Gerhard Neumann , Georgia Chalvatzaki