scholarly journals MICRA-Net: MICRoscopy Analysis Neural Network to solve detection, classification, and segmentation from a single simple auxiliary task

2020 ◽  
Author(s):  
Flavie Lavoie-Cardinal ◽  
Anthony Bilodeau ◽  
Constantin Delmas ◽  
Martin Parent ◽  
Paul De Koninck ◽  
...  
Keyword(s):  
Neural Network ◽  
Quantitative Analysis ◽  
High Throughput ◽  
State Of The Art ◽  
Feature Maps ◽  
Annotation Process ◽  
Expert Annotation ◽  
Microscopy Analysis ◽  
Weakly Supervised ◽  
Microscopy Images

Abstract High throughput quantitative analysis of microscopy images presents a challenge due to the complexity of the image content and the difficulty to retrieve precisely annotated datasets. In this paper we introduce a weakly-supervised MICRoscopy Analysis neural network (MICRA-Net) that can be trained on a simple main classification task using image-level annotations to solve multiple more complex auxiliary tasks, such as segmentation, detection, and enumeration. MICRA-Net relies on the latent information embedded within a trained model to achieve performances similar to state-of-the-art fully-supervised learning. This learnt information is extracted from the network using gradient class activation maps, which are combined to generate precise feature maps of the biological structures of interest. We demonstrate how MICRA-Net significantly alleviates the expert annotation process on various microscopy datasets and can be used for high-throughput quantitative analysis of microscopy images.

scholarly journals MICRA-Net: MICRoscopy Analysis Neural Network to solve detection, classification, and segmentation from a single simple auxiliary task

2021 ◽  
Author(s):  
Anthony Bilodeau ◽  
Constantin V.L. Delmas ◽  
Martin Parent ◽  
Paul De Koninck ◽  
Audrey Durand ◽  
...  
Keyword(s):  
Neural Network ◽  
Quantitative Analysis ◽  
High Throughput ◽  
Semantic Segmentation ◽  
Feature Maps ◽  
Expert Annotation ◽  
Microscopy Analysis ◽  
Weakly Supervised ◽  
Segmentation Task ◽  
Microscopy Images

High throughput quantitative analysis of microscopy images presents a challenge due to the complexity of the image content and the difficulty to retrieve precisely annotated datasets. In this paper we introduce a weakly-supervised MICRoscopy Analysis neural network (MICRA-Net) that can be trained on a simple main classification task using image-level annotations to solve multiple the more complex auxiliary semantic segmentation task and other associated tasks such as detection or enumeration. MICRA-Net relies on the latent information embedded within a trained model to achieve performances similar to state-of-the-art fully-supervised learning. This learnt information is extracted from the network using gradient class activation maps, which are combined to generate detailed feature maps of the biological structures of interest. We demonstrate how MICRA-Net significantly alleviates the Expert annotation process on various microscopy datasets and can be used for high-throughput quantitative analysis of microscopy images.

scholarly journals PedNet: A Spatio-Temporal Deep Convolutional Neural Network for Pedestrian Segmentation

2018 ◽  
Vol 4 (9) ◽  
pp. 107 ◽  
Author(s):  
Mohib Ullah ◽  
Ahmed Mohammed ◽  
Faouzi Alaya Cheikh
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Performance Metrics ◽  
State Of The Art ◽  
Temporal Information ◽  
Feature Maps ◽  
Current Frame ◽  
Low Level ◽  
Art Methods ◽  
Spatio Temporal

Articulation modeling, feature extraction, and classification are the important components of pedestrian segmentation. Usually, these components are modeled independently from each other and then combined in a sequential way. However, this approach is prone to poor segmentation if any individual component is weakly designed. To cope with this problem, we proposed a spatio-temporal convolutional neural network named PedNet which exploits temporal information for spatial segmentation. The backbone of the PedNet consists of an encoder–decoder network for downsampling and upsampling the feature maps, respectively. The input to the network is a set of three frames and the output is a binary mask of the segmented regions in the middle frame. Irrespective of classical deep models where the convolution layers are followed by a fully connected layer for classification, PedNet is a Fully Convolutional Network (FCN). It is trained end-to-end and the segmentation is achieved without the need of any pre- or post-processing. The main characteristic of PedNet is its unique design where it performs segmentation on a frame-by-frame basis but it uses the temporal information from the previous and the future frame for segmenting the pedestrian in the current frame. Moreover, to combine the low-level features with the high-level semantic information learned by the deeper layers, we used long-skip connections from the encoder to decoder network and concatenate the output of low-level layers with the higher level layers. This approach helps to get segmentation map with sharp boundaries. To show the potential benefits of temporal information, we also visualized different layers of the network. The visualization showed that the network learned different information from the consecutive frames and then combined the information optimally to segment the middle frame. We evaluated our approach on eight challenging datasets where humans are involved in different activities with severe articulation (football, road crossing, surveillance). The most common CamVid dataset which is used for calculating the performance of the segmentation algorithm is evaluated against seven state-of-the-art methods. The performance is shown on precision/recall, F 1 , F 2 , and mIoU. The qualitative and quantitative results show that PedNet achieves promising results against state-of-the-art methods with substantial improvement in terms of all the performance metrics.

scholarly journals Regularized Instance Embedding for Deep Multi-Instance Learning

2019 ◽  
Vol 10 (1) ◽  
pp. 64
Author(s):  
Yi Lin ◽  
Honggang Zhang
Keyword(s):  
Neural Network ◽  
Big Data ◽  
Supervised Learning ◽  
Regularization Method ◽  
Gradient Descent ◽  
State Of The Art ◽  
Stochastic Gradient Descent ◽  
Learning Framework ◽  
Weakly Supervised ◽  
The Cost

In the era of Big Data, multi-instance learning, as a weakly supervised learning framework, has various applications since it is helpful to reduce the cost of the data-labeling process. Due to this weakly supervised setting, learning effective instance representation/embedding is challenging. To address this issue, we propose an instance-embedding regularizer that can boost the performance of both instance- and bag-embedding learning in a unified fashion. Specifically, the crux of the instance-embedding regularizer is to maximize correlation between instance-embedding and underlying instance-label similarities. The embedding-learning framework was implemented using a neural network and optimized in an end-to-end manner using stochastic gradient descent. In experiments, various applications were studied, and the results show that the proposed instance-embedding-regularization method is highly effective, having state-of-the-art performance.

scholarly journals A Multibranch Object Detection Method for Traffic Scenes

2019 ◽  
Vol 2019 ◽  
pp. 1-16
Author(s):  
Jiangfan Feng ◽  
Fanjie Wang ◽  
Siqin Feng ◽  
Yongrong Peng
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Detection Method ◽  
State Of The Art ◽  
Recall Rate ◽  
Small Scale ◽  
Feature Maps ◽  
Time Requirements ◽  
Speed Up

The performance of convolutional neural network- (CNN-) based object detection has achieved incredible success. Howbeit, existing CNN-based algorithms suffer from a problem that small-scale objects are difficult to detect because it may have lost its response when the feature map has reached a certain depth, and it is common that the scale of objects (such as cars, buses, and pedestrians) contained in traffic images and videos varies greatly. In this paper, we present a 32-layer multibranch convolutional neural network named MBNet for fast detecting objects in traffic scenes. Our model utilizes three detection branches, in which feature maps with a size of 16 × 16, 32 × 32, and 64 × 64 are used, respectively, to optimize the detection for large-, medium-, and small-scale objects. By means of a multitask loss function, our model can be trained end-to-end. The experimental results show that our model achieves state-of-the-art performance in terms of precision and recall rate, and the detection speed (up to 33 fps) is fast, which can meet the real-time requirements of industry.

scholarly journals ThriftyNets: Convolutional Neural Networks with Tiny Parameter Budget

IoT ◽  
2021 ◽  
Vol 2 (2) ◽  
pp. 222-235
Author(s):  
Guillaume Coiffier ◽  
Ghouthi Boukli Hacene ◽  
Vincent Gripon
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Spatial Resolution ◽  
Network Architecture ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Feature Maps ◽  
Neural Network Architecture

Deep Neural Networks are state-of-the-art in a large number of challenges in machine learning. However, to reach the best performance they require a huge pool of parameters. Indeed, typical deep convolutional architectures present an increasing number of feature maps as we go deeper in the network, whereas spatial resolution of inputs is decreased through downsampling operations. This means that most of the parameters lay in the final layers, while a large portion of the computations are performed by a small fraction of the total parameters in the first layers. In an effort to use every parameter of a network at its maximum, we propose a new convolutional neural network architecture, called ThriftyNet. In ThriftyNet, only one convolutional layer is defined and used recursively, leading to a maximal parameter factorization. In complement, normalization, non-linearities, downsamplings and shortcut ensure sufficient expressivity of the model. ThriftyNet achieves competitive performance on a tiny parameters budget, exceeding 91% accuracy on CIFAR-10 with less than 40 k parameters in total, 74.3% on CIFAR-100 with less than 600 k parameters, and 67.1% On ImageNet ILSVRC 2012 with no more than 4.15 M parameters. However, the proposed method typically requires more computations than existing counterparts.

A High-Efficiency FPGA-Based Accelerator for Binarized Neural Network

2019 ◽  
Vol 28 (supp01) ◽  
pp. 1940004 ◽  
Author(s):  
Peng Guo ◽  
Hong Ma ◽  
Ruizhi Chen ◽  
Donglin Wang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Mobile Devices ◽  
High Efficiency ◽  
State Of The Art ◽  
Memory Bandwidth ◽  
Feature Maps ◽  
Schedule Scheme ◽  
Memory Footprint ◽  
Compute Structure

Although the convolutional neural network (CNN) has exhibited outstanding performance in various applications, the deployment of CNN on embedded and mobile devices is limited by the massive computations and memory footprint. To address these challenges, Courbariaux and co-workers put forward binarized neural network (BNN) which quantizes both the weights and activations to [Formula: see text]1. From the perspective of hardware, BNN can greatly simplify the computation and reduce the storage. In this work, we first present the algorithm optimizations to further binarize the first layer and the padding bits of BNN; then we propose a fully binarized CNN accelerator. With the Shuffle–Compute structure and the memory-aware computation schedule scheme, the proposed design can boost the performance for feature maps of different sizes and make full use of the memory bandwidth. To evaluate our design, we implement the accelerator on the Zynq ZC702 board, and the experiments on the SVHN and CIFAR-10 datasets show the state-of-the-art performance efficiency and resource efficiency.

scholarly journals Answering Binary Causal Questions Through Large-Scale Text Mining: An Evaluation Using Cause-Effect Pairs from Human Experts

2019 ◽  
Author(s):  
Oktie Hassanzadeh ◽  
Debarun Bhattacharjya ◽  
Mark Feblowitz ◽  
Kavitha Srinivas ◽  
Michael Perrone ◽  
...  
Keyword(s):  
Neural Network ◽  
Decision Making ◽  
Large Scale ◽  
State Of The Art ◽  
Language Models ◽  
Training Set ◽  
Supervised Methods ◽  
Weakly Supervised ◽  
Answering Questions ◽  
Large Corpus

In this paper, we study the problem of answering questions of type "Could X cause Y?" where X and Y are general phrases without any constraints. Answering such questions will assist with various decision analysis tasks such as verifying and extending presumed causal associations used for decision making. Our goal is to analyze the ability of an AI agent built using state-of-the-art unsupervised methods in answering causal questions derived from collections of cause-effect pairs from human experts. We focus only on unsupervised and weakly supervised methods due to the difficulty of creating a large enough training set with a reasonable quality and coverage. The methods we examine rely on a large corpus of text derived from news articles, and include methods ranging from large-scale application of classic NLP techniques and statistical analysis to the use of neural network based phrase embeddings and state-of-the-art neural language models.

scholarly journals Learning Visual Words for Weakly-Supervised Semantic Segmentation

2021 ◽  
Author(s):  
Lixiang Ru ◽  
Bo Du ◽  
Chen Wu
Keyword(s):  
State Of The Art ◽  
Local Maximum ◽  
Semantic Segmentation ◽  
Input Image ◽  
Feature Maps ◽  
Visual Words ◽  
Fine Grained ◽  
Spatial Pyramid Pooling ◽  
Weakly Supervised ◽  
Spatial Pyramid

Current weakly-supervised semantic segmentation (WSSS) methods with image-level labels mainly adopt class activation maps (CAM) to generate the initial pseudo labels. However, CAM usually only identifies the most discriminative object extents, which is attributed to the fact that the network doesn't need to discover the integral object to recognize image-level labels. In this work, to tackle this problem, we proposed to simultaneously learn the image-level labels and local visual word labels. Specifically, in each forward propagation, the feature maps of the input image will be encoded to visual words with a learnable codebook. By enforcing the network to classify the encoded fine-grained visual words, the generated CAM could cover more semantic regions. Besides, we also proposed a hybrid spatial pyramid pooling module that could preserve local maximum and global average values of feature maps, so that more object details and less background were considered. Based on the proposed methods, we conducted experiments on the PASCAL VOC 2012 dataset. Our proposed method achieved 67.2% mIoU on the val set and 67.3% mIoU on the test set, which outperformed recent state-of-the-art methods.

scholarly journals MILDMS: Multiple Instance Learning via DD Constraint and Multiple Part Similarity

Symmetry ◽  
2019 ◽  
Vol 11 (9) ◽  
pp. 1080
Author(s):  
Chao Wen ◽  
Zhan Li ◽  
Jian Qu ◽  
Qingchen Fan ◽  
Aiping Li
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Subject Area ◽  
Multiple Instance Learning ◽  
Combination Method ◽  
Learning Problem ◽  
Label Information ◽  
Weakly Supervised ◽  
Instance Space ◽  
Diverse Density

As a subject area of symmetry, multiple instance learning (MIL) is a special form of a weakly supervised learning problem where the label is related to the bag, not the instances contained in it. The difficulty of MIL lies in the incomplete label information of instances. To resolve this problem, in this paper, we propose a novel diverse density (DD) and multiple part similarity combination method for multiple instance learning, named MILDMS. First, we model the target concepts optimization with a DD function constraint on positive and negative instance space, which can greatly improve the robustness to label noise problem. Next, we combine the positive and negative instances in the bag (generated by hand-crafted and convolutional neural network features) with multiple part similarities to construct an MIL kernel. We evaluate the proposed approach on the MUSK dataset, whose results MUSK1 (91.9%) and MUSK2 (92.2%) show our method is comparable to other MIL algorithms. To further demonstrate generality, we also present experimental results on the PASCAL VOC 2007 and 2012 (46.5% and 42.2%) and COREL (78.6%) that significantly outperforms the state-of-the-art algorithms including deep MIL and other non-deep MIL algorithms.

Sign in / Sign up

Export Citation Format

Share Document