检索结果-内蒙古大学图书馆

RCCNet: An Efficient Convolutional Neural Network for Histological Routine Colon Cancer Nuclei Classification

学校读者我要写书评

暂无评论

RCCNet: An Efficient Convolutional Neural Network for Histol...

International Conference on Control, Automation, Robotics and vision

作者： S H Shabbeer Basha Soumen Ghosh Kancharagunta Kishan Babu Shiv Ram Dubey Viswanath Pulabaigari Snehasis Mukherjee Computer Vision and Machine Learning Groups Indian Institute of Information Technology Sri City Andhra Pradesh India

Efficient and precise classification of histological cell nuclei is of utmost importance due to its potential applications in the field of medical image analysis. It would facilitate the medical practitioners to better understand and explore various factors for cancer treatment. The classification of histological cell nuclei is a challenging task due to the cellular heterogeneity. This paper proposes an efficient Convolutional Neural Network (CNN) based architecture for classification of histological routine colon cancer nuclei named as RCCNet. The main objective of this network is to keep the CNN model as simple as possible. The proposed RCCNet model consists of 1, 512, 868 learnable parameters which are significantly less compared to the popular CNN models such as AlexNet, CIFAR-VGG, GoogLeNet, and WRN. The experiments are conducted over publicly available routine colon cancer histological dataset "CRCHistoPhenotypes". The results of the proposed RCCNet model are compared with five state-of-the-art CNN models in terms of the accuracy, weighted average F1 score and training time. The proposed method has achieved a classification accuracy of 80.61% and 0.7887 weighted average F1 score. The proposed RCCNet is more efficient and generalized in terms of the training time and data over-fitting, respectively.

关键词： Cancer computer architecture Colon Biomedical imaging Task analysis Training Image analysis

Determining Mice Sex from Chest X-rays using Deep learning

学校读者我要写书评

暂无评论

Determining Mice Sex from Chest X-rays using Deep Learning

International Conference on Cyberspace (CYBER)

作者： Abiodun Ajiboye Kola Babalola Institute of Computer Vision and Machine Learning Lagos Nigeria European Molecular Biology Laboratory European Bioinformatics Institute Cambridgshire UK

ISBN: (纸本)9781665444095;9781665444101

This Following on from work by Babalola et al. It is shown that the sex of mice can be determined from x-ray images of the chest region alone using convolutional neural networks. The anatomical differences that may be responsible for this is further sinvestigated, as it may be useful in determining phenotype changes caused by knocking out genes - hence in understanding genotype-phenotype effects. Our results indicate that the cervical vertebrae may play an important role in the ability of our convolutional neural network to classify the sex of mice correctly using only x-rays of the chest region.

关键词： Deep learning Conferences Mice Convolutional neural networks X-ray imaging Biomedical imaging

The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Mirza, Muhammad Jehanzeb Micorek, Jakub Possegger, Horst Bischof, Horst Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Austria

Domain adaptation is crucial to adapt a learned model to new scenarios, such as domain shifts or changing data distributions. Current approaches usually require a large amount of labeled or unlabeled data from the shifted domain. This can be a hurdle in fields which require continuous dynamic adaptation or suffer from scarcity of data, e.g. autonomous driving in challenging weather conditions. To address this problem of continuous adaptation to distribution shifts, we propose Dynamic Unsupervised Adaptation (DUA). By continuously adapting the statistics of the batch normalization layers we modify the feature representations of the model. We show that by sequentially adapting a model with only a fraction of unlabeled data, a strong performance gain can be achieved. With even less than 1% of unlabeled data from the target domain, DUA already achieves competitive results to strong baselines. In addition, the computational overhead is minimal in contrast to previous approaches. Our approach is simple, yet effective and can be applied to any architecture which uses batch normalization. We show the utility of DUA by evaluating it on a variety of domain adaptation datasets and tasks including object recognition, digit recognition and object detection. © 2021, CC BY.

关键词： Object recognition

RCCNet: An efficient convolutional neural network for histological routine colon cancer nuclei classification

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Basha, S.H. Shabbeer Ghosh, Soumen Babu, Kancharagunta Kishan Dubey, Shiv Ram Pulabaigari, Viswanath Mukherjee, Snehasis Computer Vision and Machine Learning Groups Indian Institute of Information Technology Sri CityAndhra Pradesh517646 India

关键词： Convolution

Constrained parametric min-cuts for automatic object segmentation

学校读者我要写书评

暂无评论

Constrained parametric min-cuts for automatic object segment...

Conference on computer vision and Pattern Recognition (CVPR)

作者： Joao Carreira Cristian Sminchisescu Computer Vision and Machine Learning Group Institute for Numerical Simulation Faculty of Mathematics and Natural Sciences University of Bonn Germany

We present a novel framework for generating and ranking plausible objects hypotheses in an image using bottom-up processes and mid-level cues. The object hypotheses are represented as figure-ground segmentations, and are extracted automatically, without prior knowledge about properties of individual object classes, by solving a sequence of constrained parametric min-cut problems (CPMC) on a regular image grid. We then learn to rank the object hypotheses by training a continuous model to predict how plausible the segments are, given their mid-level region properties. We show that this algorithm significantly outperforms the state of the art for low-level segmentation in the VOC09 segmentation dataset. It achieves the same average best segmentation covering as the best performing technique to date, 0.61 when using just the top 7 ranked segments, instead of the full hierarchy in. Our method achieves 0.78 average best covering using 154 segments. In a companion paper, we also show that the algorithm achieves state-of-the art results when used in a segmentation-based recognition pipeline.

关键词： Object segmentation Image segmentation machine learning Art Humans machine learning algorithms computer vision Numerical simulation Mathematics Predictive models

SAILOR: Scaling Anchors via Insights into Latent Object Representation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Malić, Dušan Fruhwirth-Reisinger, Christian Possegger, Horst Bischof, Horst Institute of Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Austria

LiDAR 3D object detection models are inevitably biased towards their training dataset. The detector clearly exhibits this bias when employed on a target dataset, particularly towards object sizes. However, object sizes vary heavily between domains due to, for instance, different labeling policies or geographical locations. State-of-the-art unsupervised domain adaptation approaches outsource methods to overcome the object size bias. Mainstream size adaptation approaches exploit target domain statistics, contradicting the original unsupervised assumption. Our novel unsupervised anchor calibration method addresses this limitation. Given a model trained on the source data, we estimate the optimal target anchors in a completely unsupervised manner. The main idea stems from an intuitive observation: by varying the anchor sizes for the target domain, we inevitably introduce noise or even remove valuable object cues. The latent object representation, perturbed by the anchor size, is closest to the learned source features only under the optimal target anchors. We leverage this observation for anchor size optimization. Our experimental results show that, without any retraining, we achieve competitive results even compared to state-of-the-art weakly-supervised size adaptation approaches. In addition, our anchor calibration can be combined with such existing methods, making them completely unsupervised. © 2022, CC BY.

关键词： Anchors

Object recognition as ranking holistic figure-ground hypotheses

学校读者我要写书评

暂无评论

Object recognition as ranking holistic figure-ground hypothe...

Conference on computer vision and Pattern Recognition (CVPR)

作者： Fuxin Li Joao Carreira Cristian Sminchisescu Computer Vision and Machine Learning Group Institute for Numerical Simulation Faculty of Mathematics and Natural Sciences University of Bonn Germany

We present an approach to visual object-class recognition and segmentation based on a pipeline that combines multiple, holistic figure-ground hypotheses generated in a bottom-up, object independent process. Decisions are performed based on continuous estimates of the spatial overlap between image segment hypotheses and each putative class. We differ from existing approaches not only in our seemingly unreasonable assumption that good object-level segments can be obtained in a feed-forward fashion, but also in framing recognition as a regression problem. Instead of focusing on a one-vs-all winning margin that can scramble ordering inside the non-maximum (non-winning) set, learning produces a globally consistent ranking with close ties to segment quality, hence to the extent entire object or part hypotheses spatially overlap with the ground truth. We demonstrate results beyond the current state of the art for image classification, object detection and semantic segmentation, in a number of challenging datasets including Caltech-101, ETHZ-Shape and PASCAL VOC 2009.

关键词： Object recognition Image segmentation Shape machine learning Object detection Space exploration computer vision Numerical simulation Mathematics Pipelines

An information-rich sampling technique over spatio-temporal CNN for classification of human actions in videos

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shabbeer Basha, S.H. Pulabaigari, Viswanath Mukherjee, Snehasis Computer Vision and Machine Learning Groups Indian Institute of Information Technology Sri City Andhra Pradesh517646 India

We propose a novel scheme for human action recognition in videos, using a 3-dimensional Convolutional Neural Network (3D CNN) based classifier. Traditionally in deep learning based human activity recognition approaches, either a few random frames or every kth frame of the video is considered for training the 3D CNN, where k is a small positive integer, like 4, 5, or 6. This kind of sampling reduces the volume of the input data, which speeds-up training of the network and also avoids over-fitting to some extent, thus enhancing the performance of the 3D CNN model. In the proposed video sampling technique, consecutive k frames of a video are aggregated into a single frame by computing a Gaussianweighted summation of the k frames. The resulting frame (aggregated frame) preserves the information in a better way than the conventional approaches and experimentally shown to perform better. In this paper, a 3D CNN architecture is proposed to extract the spatio-temporal features and follows Long Short-Term Memory (LSTM) to recognize the human actions. The proposed 3D CNN architecture is capable of handling the videos where the camera is placed at a distance from the performer. Experiments are performed with KTH and WEIZMANN human actions datasets, whereby it is shown to produce comparable results with the state-of-the-art techniques. Copyright © 2020, The Authors. All rights reserved.

关键词： Long short-term memory

AutoFCL: Automatically tuning fully connected layers for handling small dataset

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shabbeer Basha, S.H. Vinakota, Sravan Kumar Dubey, Shiv Ram Pulabaigari, Viswanath Mukherjee, Snehasis Computer Vision and Machine Learning Groups Indian Institute of Information Technology Sri City Andhra Pradesh517646 India

Deep Convolutional Neural Networks (CNN) have evolved as popular machine learning models for image classification during the past few years, due to their ability to learn the problem-specific features directly from the input images. The success of deep learning models solicits architecture engineering rather than hand-engineering the features. However, designing state-of-the-art CNN for a given task remains a non-trivial and challenging task, especially when training data size is less. To address this phenomena, transfer learning has been used as a popularly adopted technique. While transferring the learned knowledge from one task to another, fine-tuning with the target-dependent Fully Connected (FC) layers generally produces better results over the target task. In this paper, the proposed AutoFCL model attempts to learn the structure of FC layers of a CNN automatically using Bayesian optimization. To evaluate the performance of the proposed AutoFCL, we utilize five pre-trained CNN models such as VGG-16, ResNet, DenseNet, MobileNet, and NASNetMobile. The experiments are conducted on three benchmark datasets, namely CalTech-101, Oxford-102 Flowers, and UC Merced Land Use datasets. Fine-tuning the newly learned (target-dependent) FC layers leads to state-of-the-art performance, according to the experiments carried out in this research. The proposed AutoFCL method outperforms the existing methods over CalTech-101 and Oxford-102 Flowers datasets by achieving the accuracy of 94.38% and 98.89%, respectively. However, our method achieves comparable performance on the UC Merced Land Use dataset with 96.83% accuracy. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks