English
Related papers

Related papers: Generating Hard Examples for Pixel-wise Classifica…

200 papers

Annotating images for semantic segmentation requires intense manual labor and is a time-consuming and expensive task especially for domains with a scarcity of experts, such as Forensic Anthropology. We leverage the evolving nature of images…

Computer Vision and Pattern Recognition · Computer Science 2021-05-24 Sara Mousavi , Zhenning Yang , Kelley Cross , Dawnie Steadman , Audris Mockus

While capable of segregating visual data, humans take time to examine a single piece, let alone thousands or millions of samples. The deep learning models efficiently process sizeable information with the help of modern-day computing.…

Computer Vision and Pattern Recognition · Computer Science 2022-09-28 Alankrit Mishra , Nikhil Raj , Garima Bajwa

Adversarial classification is the task of performing robust classification in the presence of a strategic attacker. Originating from information hiding and multimedia forensics, adversarial classification recently received a lot of…

Cryptography and Security · Computer Science 2018-03-12 Pascal Schöttle , Alexander Schlögl , Cecilia Pasquini , Rainer Böhme

Fully supervised deep neural networks for segmentation usually require a massive amount of pixel-level labels which are manually expensive to create. In this work, we develop a multi-task learning method to relax this constraint. We regard…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Rihuan Ke , Aurélie Bugeau , Nicolas Papadakis , Mark Kirkland , Peter Schuetz , Carola-Bibiane Schönlieb

Riding on the waves of deep neural networks, deep metric learning has also achieved promising results in various tasks using triplet network or Siamese network. Though the basic goal of making images from the same category closer than the…

Computer Vision and Pattern Recognition · Computer Science 2017-08-02 Yuhui Yuan , Kuiyuan Yang , Chao Zhang

The \emph{receptive fields} of deep learning classification models determine the regions of the input data that have the most significance for providing correct decisions. The primary way to learn such receptive fields is to train the…

Machine Learning · Computer Science 2020-07-06 Ehsan Yaghoubi , Diana Borza , Aruna Kumar , Hugo Proença

We propose a new approach to interactive full-image semantic segmentation which enables quickly collecting training data for new datasets with previously unseen semantic classes (A demo is available at https://youtu.be/yUk8D5gEX-o). We…

Computer Vision and Pattern Recognition · Computer Science 2020-07-17 Mykhaylo Andriluka , Stefano Pellegrini , Stefan Popov , Vittorio Ferrari

Several image pattern recognition tasks rely on superpixel generation as a fundamental step. Image analysis based on superpixels facilitates domain-specific applications, also speeding up the overall processing time of the task. Recent…

Computer Vision and Pattern Recognition · Computer Science 2018-02-19 Marcelo Santos , Luciano Oliveira

The success of state-of-the-art deep neural networks heavily relies on the presence of large-scale labelled datasets, which are extremely expensive and time-consuming to annotate. This paper focuses on tackling semi-supervised part…

Computer Vision and Pattern Recognition · Computer Science 2022-11-08 Yu Yang , Xiaotian Cheng , Hakan Bilen , Xiangyang Ji

Semantic segmentation of electron microscopy (EM) images of biological samples remains a challenge in the life sciences. EM data captures details of biological structures, sometimes with such complexity that even human observers can find it…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Sheida Rahnamai Kordasiabi , Damian Dalle Nogare , Florian Jug

The latent class model is a widely used mixture model for multivariate discrete data. Besides the existence of qualitatively heterogeneous latent classes, real data often exhibit additional quantitative heterogeneity nested within each…

Methodology · Statistics 2025-01-23 Zhongyuan Lyu , Ling Chen , Yuqi Gu

Most of the approaches for indoor RGBD semantic la- beling focus on using pixels or superpixels to train a classi- fier. In this paper, we implement a higher level segmentation using a hierarchy of superpixels to obtain a better segmen-…

Computer Vision and Pattern Recognition · Computer Science 2018-01-30 Steven Hickson , Irfan Essa , Henrik Christensen

Crucial to the success of training a depth-based 3D hand pose estimator (HPE) is the availability of comprehensive datasets covering diverse camera perspectives, shapes, and pose variations. However, collecting such annotated datasets is…

Computer Vision and Pattern Recognition · Computer Science 2018-05-14 Seungryul Baek , Kwang In Kim , Tae-Kyun Kim

Mechanical exfoliation of graphene and its identification by optical inspection is one of the milestones in condensed matter physics that sparked the field of 2D materials. Finding regions of interest from the entire sample space and…

Materials Science · Physics 2022-09-19 Woon Hyung Cho , Jiseon Shin , Young Duck Kim , George J. Jung

Histopathology image analysis plays a critical role in cancer diagnosis and treatment. To automatically segment the cancerous regions, fully supervised segmentation algorithms require labor-intensive and time-consuming labeling at the pixel…

Image and Video Processing · Electrical Eng. & Systems 2019-08-29 Gang Xu , Zhigang Song , Zhuo Sun , Calvin Ku , Zhe Yang , Cancheng Liu , Shuhao Wang , Jianpeng Ma , Wei Xu

Generative Adversarial Networks (GANs) have significantly advanced image synthesis, however, the synthesis quality drops significantly given a limited amount of training data. To improve the data efficiency of GAN training, prior work…

Computer Vision and Pattern Recognition · Computer Science 2021-06-09 Ceyuan Yang , Yujun Shen , Yinghao Xu , Bolei Zhou

Many active learning and search approaches are intractable for large-scale industrial settings with billions of unlabeled examples. Existing approaches search globally for the optimal examples to label, scaling linearly or even…

In recent years, large amount of high spatial-resolution remote sensing (HRRS) images are available for land-cover mapping. However, due to the complex information brought by the increased spatial resolution and the data disturbances caused…

Computer Vision and Pattern Recognition · Computer Science 2022-04-25 Xin-Yi Tong , Gui-Song Xia , Qikai Lu , Huanfeng Shen , Shengyang Li , Shucheng You , Liangpei Zhang

Semantic segmentation is a fundamental topic in computer vision. Several deep learning methods have been proposed for semantic segmentation with outstanding results. However, these models require a lot of densely annotated images. To…

Computer Vision and Pattern Recognition · Computer Science 2022-10-12 Jhony H. Giraldo , Vincenzo Scarrica , Antonino Staiano , Francesco Camastra , Thierry Bouwmans

Learning segmentation from noisy labels is an important task for medical image analysis due to the difficulty in acquiring highquality annotations. Most existing methods neglect the pixel correlation and structural prior in segmentation,…

Computer Vision and Pattern Recognition · Computer Science 2021-07-22 Shuailin Li , Zhitong Gao , Xuming He