English
Related papers

Related papers: Zero Shot Learning for Multi-Modal Real Time Image…

200 papers

Quantization is one of the most popular techniques for reducing computation time and shrinking model size. However, ensuring the accuracy of quantized models typically involves calibration using training data, which may be inaccessible due…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Burak Sevsay , Erdem Akagündüz

Objects classification generally relies on image acquisition and analysis. Real-time classification of high-speed moving objects is challenging, as both high temporal resolution in image acquisition and low computational complexity in…

Image and Video Processing · Electrical Eng. & Systems 2020-05-20 Zibang Zhang , Xiang Li , Manhong Yao , Shujun Zheng , Guoan Zheng , Jingang Zhong

Zero-shot learning enables the model to recognize unseen categories with the aid of auxiliary semantic information such as attributes. Current works proposed to detect attributes from local image regions and align extracted features with…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Junzhe Xu , Suling Duan , Chenwei Tang , Zhenan He , Jiancheng Lv

One of the key limitations in conventional deep learning based image reconstruction is the need for registered pairs of training images containing a set of high-quality groundtruth images. This paper addresses this limitation by proposing a…

Image and Video Processing · Electrical Eng. & Systems 2020-09-30 Weijie Gan , Yu Sun , Cihat Eldeniz , Jiaming Liu , Hongyu An , Ulugbek S. Kamilov

Zero-shot learning (ZSL) is a challenging task aiming at recognizing novel classes without any training instances. In this paper we present a simple but high-performance ZSL approach by generating pseudo feature representations (GPFR).…

Computer Vision and Pattern Recognition · Computer Science 2018-09-11 Jiang Lu , Jin Li , Ziang Yan , Changshui Zhang

Producing manual, pixel-accurate, image segmentation labels is tedious and time-consuming. This is often a rate-limiting factor when large amounts of labeled images are required, such as for training deep convolutional networks for…

Computer Vision and Pattern Recognition · Computer Science 2021-02-19 Luis C. Garcia-Peraza-Herrera , Lucas Fidon , Claudia D'Ettorre , Danail Stoyanov , Tom Vercauteren , Sebastien Ourselin

This study introduces a novel unsupervised medical image feature extraction method that employs spatial stratification techniques. An objective function based on weight is proposed to achieve the purpose of fast image recognition. The…

Image and Video Processing · Electrical Eng. & Systems 2024-06-28 Qishi Zhan , Dan Sun , Erdi Gao , Yuhan Ma , Yaxin Liang , Haowei Yang

Recent research leveraging large-scale pretrained diffusion models has demonstrated the potential of using diffusion features to establish semantic correspondences in images. Inspired by advancements in diffusion-based techniques, we…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Chengyu Zheng , Jin Huang , Honghua Chen , Mingqiang Wei

Zero-shot learning (ZSL) aims to infer novel classes without training samples by transferring knowledge from seen classes. Existing embedding-based approaches for ZSL typically employ attention mechanisms to locate attributes on an image.…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Lei Xiang , Yuan Zhou , Haoran Duan , Yang Long

Deep neural networks often struggle to learn robust representations in the presence of dataset biases, leading to suboptimal generalization on unbiased datasets. This limitation arises because the models heavily depend on peripheral and…

Machine Learning · Computer Science 2024-12-11 Carlo Alberto Barbano , Enzo Tartaglione , Marco Grangetto

Semantic segmentation models are limited in their ability to scale to large numbers of object classes. In this paper, we introduce the new task of zero-shot semantic segmentation: learning pixel-wise classifiers for never-seen object…

Computer Vision and Pattern Recognition · Computer Science 2019-11-19 Maxime Bucher , Tuan-Hung Vu , Matthieu Cord , Patrick Pérez

3D medical image registration is of great clinical importance. However, supervised learning methods require a large amount of accurately annotated corresponding control points (or morphing), which are very difficult to obtain. Unsupervised…

Computer Vision and Pattern Recognition · Computer Science 2020-05-11 Shengyu Zhao , Tingfung Lau , Ji Luo , Eric I-Chao Chang , Yan Xu

Diffeomorphic deformable image registration is one of the crucial tasks in medical image analysis, which aims to find a unique transformation while preserving the topology and invertibility of the transformation. Deep convolutional neural…

Image and Video Processing · Electrical Eng. & Systems 2022-02-09 Ameneh Sheikhjafari , Michelle Noga , Kumaradevan Punithakumar , Nilanjan Ray

Deep learning models perform best when tested on target (test) data domains whose distribution is similar to the set of source (train) domains. However, model generalization can be hindered when there is significant difference in the…

Computer Vision and Pattern Recognition · Computer Science 2020-08-19 Pulkit Khandelwal , Paul Yushkevich

Zero-shot point cloud segmentation aims to make deep models capable of recognizing novel objects in point cloud that are unseen in the training phase. Recent trends favor the pipeline which transfers knowledge from seen classes with labels…

Computer Vision and Pattern Recognition · Computer Science 2023-07-21 Yuhang Lu , Qi Jiang , Runnan Chen , Yuenan Hou , Xinge Zhu , Yuexin Ma

Image modality recognition is essential for efficient imaging workflows in current clinical environments, where multiple imaging modalities are used to better comprehend complex diseases. Emerging biomarkers from novel, rare modalities are…

Computer Vision and Pattern Recognition · Computer Science 2019-08-28 Santi Puch , Irina Sánchez , Matt Rowe

Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for privacy and safety. Existing machine unlearning methods…

Machine Learning · Computer Science 2026-05-21 Yujie Lin , Chengyi Yang , Zhishang Xiang , Yiping Song , Jinsong Su

We describe a point-set registration algorithm based on a novel free point transformer (FPT) network, designed for points extracted from multimodal biomedical images for registration tasks, such as those frequently encountered in…

Computer Vision and Pattern Recognition · Computer Science 2020-08-06 Zachary M. C. Baum , Yipeng Hu , Dean C. Barratt

Image registration techniques usually assume that the images to be registered are of a certain type (e.g. single- vs. multi-modal, 2D vs. 3D, rigid vs. deformable) and there lacks a general method that can work for data under all…

Image and Video Processing · Electrical Eng. & Systems 2025-01-28 Quang Luong Nhat Nguyen , Ruiming Cao , Laura Waller

Convolutional neural networks are able to learn realistic image priors from numerous training samples in low-level image generation and restoration. We show that, for high-level image recognition tasks, we can further reconstruct…

Computer Vision and Pattern Recognition · Computer Science 2021-01-22 Xiangyu He , Qinghao Hu , Peisong Wang , Jian Cheng