English
Related papers

Related papers: Probabilistic Pixel-Adaptive Refinement Networks

200 papers

Probabilistic atlases (PAs) have long been used in standard segmentation approaches and, more recently, in conjunction with Convolutional Neural Networks (CNNs). However, their use has been restricted to relatively standardized structures…

Computer Vision and Pattern Recognition · Computer Science 2019-09-19 Udaranga Wickramasinghe , Graham Knott , Pascal Fua

Inspired by "predictive coding" - a theory in neuroscience, we develop a bi-directional and dynamic neural network with local recurrent processing, namely predictive coding network (PCN). Unlike feedforward-only convolutional neural…

Computer Vision and Pattern Recognition · Computer Science 2018-10-29 Kuan Han , Haiguang Wen , Yizhen Zhang , Di Fu , Eugenio Culurciello , Zhongming Liu

We propose a novel locally adaptive learning estimator for enhancing the inter- and intra- discriminative capabilities of Deep Neural Networks, which can be used as improved loss layer for semantic image segmentation tasks. Most loss layers…

Computer Vision and Pattern Recognition · Computer Science 2018-04-17 Jinjiang Guo , Pengyuan Ren , Aiguo Gu , Jian Xu , Weixin Wu

This paper tackles the problem of motion deblurring of dynamic scenes. Although end-to-end fully convolutional designs have recently advanced the state-of-the-art in non-uniform motion deblurring, their performance-complexity trade-off is…

Computer Vision and Pattern Recognition · Computer Science 2024-02-12 Maitreya Suin , Kuldeep Purohit , A. N. Rajagopalan

Based on the predictive coding theory in neuroscience, we designed a bi-directional and recurrent neural net, namely deep predictive coding networks (PCN). It has feedforward, feedback, and recurrent connections. Feedback connections from a…

Computer Vision and Pattern Recognition · Computer Science 2018-07-31 Haiguang Wen , Kuan Han , Junxing Shi , Yizhen Zhang , Eugenio Culurciello , Zhongming Liu

Positional encodings are a common component of neural scene reconstruction methods, and provide a way to bias the learning of neural fields towards coarser or finer representations. Current neural surface reconstruction methods use a…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Thomas Walker , Octave Mariotti , Amir Vaxman , Hakan Bilen

In convolutional neural networks (CNNs), padding plays a pivotal role in preserving spatial dimensions throughout the layers. Traditional padding techniques do not explicitly distinguish between the actual image content and the padded…

Computer Vision and Pattern Recognition · Computer Science 2023-11-20 Juho Kim

We present data structures and algorithms for native implementations of discrete convolution operators over Adaptive Particle Representations (APR) of images on parallel computer architectures. The APR is a content-adaptive image…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Joel Jonsson , Bevan L. Cheeseman , Suryanarayana Maddu , Krzysztof Gonciarz , Ivo F. Sbalzarini

Convolutional layers are a major driving force behind the successes of deep learning. Pointwise convolution (PWC) is a 1x1 convolutional filter that is primarily used for parameter reduction. However, the PWC ignores the spatial information…

Computer Vision and Pattern Recognition · Computer Science 2020-02-07 Pratik Mazumder , Pravendra Singh , Vinay Namboodiri

We present highly efficient algorithms for performing forward and backward propagation of Convolutional Neural Network (CNN) for pixelwise classification on images. For pixelwise classification tasks, such as image segmentation and object…

Computer Vision and Pattern Recognition · Computer Science 2014-12-17 Hongsheng Li , Rui Zhao , Xiaogang Wang

We present a general learning-based solution for restoring images suffering from spatially-varying degradations. Prior approaches are typically degradation-specific and employ the same processing across different images and different pixels…

Computer Vision and Pattern Recognition · Computer Science 2021-08-20 Kuldeep Purohit , Maitreya Suin , A. N. Rajagopalan , Vishnu Naresh Boddeti

Generative image codecs aim to optimize perceptual quality, producing realistic and detailed reconstructions. However, they often overlook a key property of human vision: our tendency to focus on particular aspects of a visual scene (e.g.,…

Image and Video Processing · Electrical Eng. & Systems 2026-04-02 Lucas Relic , Roberto Azevedo , Yang Zhang , Stephan Mandt , Markus Gross , Christopher Schroers

The deployment of Machine Learning models intraoperatively for tissue characterisation can assist decision making and guide safe tumour resections. For image classification models, pixel attribution methods are popular to infer…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Alfie Roddan , Chi Xu , Serine Ajlouni , Irini Kakaletri , Patra Charalampaki , Stamatia Giannarou

In this paper we propose the use of image pixel position coordinate system to improve image classification accuracy in various applications. Specifically, we hypothesize that the use of pixel coordinates will lead to (a) Resolution…

Computer Vision and Pattern Recognition · Computer Science 2018-02-08 Avinash Kori , Ganapathy Krishnamurthi , Balaji Srinivasan

While initially devised for image categorization, convolutional neural networks (CNNs) are being increasingly used for the pixelwise semantic labeling of images. However, the proper nature of the most common CNN architectures makes them…

Computer Vision and Pattern Recognition · Computer Science 2017-04-24 Emmanuel Maggiori , Guillaume Charpiat , Yuliya Tarabalka , Pierre Alliez

Applying feature dependent network weights have been proved to be effective in many fields. However, in practice, restricted by the enormous size of model parameters and memory footprints, scalable and versatile dynamic convolutions with…

Computer Vision and Pattern Recognition · Computer Science 2021-08-19 Ze Wang , Zichen Miao , Jun Hu , Qiang Qiu

Deep learning vision models are typically tailored for specific modalities and often rely on domain-specific assumptions, such as the grid structures used by nearly all existing vision models. In this work, we propose a self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Mahmoud Khalil , Ahmad Khalil , Alioune Ngom

Pixelwise semantic image labeling is an important, yet challenging, task with many applications. Typical approaches to tackle this problem involve either the training of deep networks on vast amounts of images to directly infer the labels…

Computer Vision and Pattern Recognition · Computer Science 2017-12-12 Yu-Hui Huang , Xu Jia , Stamatios Georgoulis , Tinne Tuytelaars , Luc Van Gool

Predicting salient regions in natural images requires the detection of objects that are present in a scene. To develop robust representations for this challenging task, high-level visual features at multiple spatial scales must be extracted…

Computer Vision and Pattern Recognition · Computer Science 2024-04-08 Alexander Kroner , Mario Senden , Kurt Driessens , Rainer Goebel

This paper tackles the problem of motion deblurring of dynamic scenes. Although end-to-end fully convolutional designs have recently advanced the state-of-the-art in non-uniform motion deblurring, their performance-complexity trade-off is…

Computer Vision and Pattern Recognition · Computer Science 2020-04-14 Maitreya Suin , Kuldeep Purohit , A. N. Rajagopalan