Playing to distraction: towards a robust training of CNN classifiers through visual explanation techniques
Andalusian Research Institute in Data Science and Computational Intelligence（安达卢西亚数据科学与计算智能研究所）；University of Granada（格拉纳达大学）；HAT.tec GmbH（HAT.tec有限公司）；Universität der Bundeswehr（联邦国防军大学）；University of Groningen（格罗宁根大学）；Universidad de Oviedo（奥维耶多大学）
David Morales, Estefania Talavera, Beatriz Remeseiro
The field of deep learning is evolving in different directions, with still the need for more efficient training strategies. In this work, we present a novel and robust training scheme that integrates visual explanation techniques in the learning process. Unlike the attention mechanisms that focus on the relevant parts of images, we aim to improve the robustness of the model by making it pay attention to other regions as well. Broadly speaking, the idea is to distract the classifier in the learning process to force it to focus not only on relevant regions but also on those that, a priori, are not so informative for the discrimination of the class. We tested the proposed approach by embedding it into the learning process of a convolutional neural network for the analysis and classification of two well-known datasets, namely Stanford cars and FGVC-Aircraft. Furthermore, we evaluated our model on a real-case scenario for the classification of egocentric images, allowing us to obtain relevant information about peoples' lifestyles. In particular, we work on the challenging EgoFoodPlaces dataset, achieving state-of-the-art results with a lower level of complexity. The obtained results indicate the suitability of our proposed training scheme for image classification, improving the robustness of the final model.
Central Electronics Engineering Research Institute (CSIR-CEERI)（中央电子工程研究所）
As the proportion of road accidents increases each year, driver distraction continues to be an important risk component in road traffic injuries and deaths. The distractions caused by the increasing use of mobile phones and other wireless devices pose a potential risk to road safety. Our current study aims to aid the already existing techniques in driver posture recognition by improving the performance in the driver distraction classification problem. We present an approach using a genetic algorithm-based ensemble of six independent deep neural architectures, namely, AlexNet, VGG-16, Efficient…
In this work we propose a novel technique to quantify how distracting watermarks are on an image. We begin with watermark detection using a two-tower CNN model composed of a binary classification task and a semantic segmentation prediction. With this model, we demonstrate significant improvement in image precision while maintaining per-pixel accuracy, especially for our real-world dataset with sparse positive examples. We fit a nonlinear function to represent detected watermarks by a single score correlated with human perception based on their size, location, and visual obstructiveness. Finall…
Beijing Advanced Innovation Center for Big Data and Brain Computing（北京大数据与脑计算高精尖创新中心）；Beihang University（北京航空航天大学）
Recently, Human Attribute Recognition (HAR) has become a hot topic due to its scientific challenges and application potentials, where localizing attributes is a crucial stage but not well handled. In this paper, we propose a novel deep learning approach to HAR, namely Distraction-aware HAR (Da-HAR). It enhances deep CNN feature learning by improving attribute localization through a coarse-to-fine attention mechanism. At the coarse step, a self-mask block is built to roughly discriminate and reduce distractions, while at the fine step, a masked attention branch is applied to further eliminate i…
University of Arizona（亚利桑那大学）；Cornell University（康奈尔大学）
To help prevent motor vehicle accidents, there has been significant interest in finding an automated method to recognize signs of driver distraction, such as talking to passengers, fixing hair and makeup, eating and drinking, and using a mobile phone. In this paper, we present an automated supervised learning method called Drive-Net for driver distraction detection. Drive-Net uses a combination of a convolutional neural network (CNN) and a random decision forest for classifying images of a driver. We compare the performance of our proposed Drive-Net to two other popular machine-learning approa…
Cornell University（康奈尔大学）；CuraCloud Corporation（库拉克劳德公司）；UNC Charlotte（北卡罗来纳大学夏洛特分校）；University at Albany, State University at New York（纽约州立大学奥尔巴尼分校）
Computerized automatic methods have been employed to boost the productivity as well as objectiveness of hand bone age assessment. These approaches make predictions according to the whole X-ray images, which include other objects that may introduce distractions. Instead, our framework is inspired by the clinical workflow (Tanner-Whitehouse) of hand bone age assessment, which focuses on the key components of the hand. The proposed framework is composed of two components: a Mask R-CNN subnet of pixelwise hand segmentation and a residual attention network for hand bone age assessment. The Mask R-C…
Biometric based authentication is currently playing an essential role over conventional authentication system; however, the risk of presentation attacks subsequently rising. Our research aims at identifying the areas where presentation attack can be prevented even though adequate biometric image samples of users are limited. Our work focusses on generating photorealistic synthetic images from the real image sets by implementing Deep Convolution Generative Adversarial Net (DCGAN). We have implemented the temporal and spatial augmentation during the fake image generation. Our work detects the pr…
LGBP-OrgaNet: Learnable Gaussian Band Pass Fusion of CNN and Transformer Features for Robust Organoid Segmentation and Tracking
School of Optoelectronic Science and Engineering（光电科学与工程学院）；Translational Chinese Medicine Key Laboratory of Sichuan, Sichuan-Chongqing Joint Key Laboratory of innovation of New Drugs of Traditional, Chinese Medicine Sichuan Institute for Translational Chinese Medicine（四川 translational 中医关键实验室，四川-重庆联合新药创新中药关键实验室，四川 translational 中医研究所）；Sichuan Cancer Hospital and Institute（四川癌症医院与研究所）
CUNY City College（纽约市立大学城市学院）；CUNY Graduate Center（纽约市立大学研究生中心）
In this paper, we propose a recursive framework to recognize facial expressions from images in real scenes. Unlike traditional approaches that typically focus on developing and refining algorithms for improving recognition performance on an existing dataset, we integrate three important components in a recursive manner: facial dataset generation, facial expression recognition model building, and interactive interfaces for testing and new data collection. To start with, we first create a candid-images-for-facial-expression (CIFE) dataset. We then apply a convolutional neural network (CNN) to CI…
Recent research has shown that map raw pixels from a single front-facing camera directly to steering commands are surprisingly powerful. This paper presents a convolutional neural network (CNN) to playing the CarRacing-v0 using imitation learning in OpenAI Gym. The dataset is generated by playing the game manually in Gym and used a data augmentation method to expand the dataset to 4 times larger than before. Also, we read the true speed, four ABS sensors, steering wheel position, and gyroscope for each image and designed a mixed model by combining the sensor input and image input. After traini…
National Research Council of Italy（意大利国家研究委员会）；University Paris-Est Creteil（巴黎东部克雷泰伊大学）
In the last three years, the world has been facing a global crisis caused by Covid-19 pandemic. Medical imaging has been playing a crucial role in the fighting against this disease and saving the human lives. Indeed, CT-scans has proved their efficiency in diagnosing, detecting, and following-up the Covid-19 infection. In this paper, we propose a new Transformer-CNN based approach for Covid-19 infection segmentation from the CT slices. The proposed D-TrAttUnet architecture has an Encoder-Decoder structure, where compound Transformer-CNN encoder and Dual-Decoders are proposed. The Transformer-C…
Queen Mary University of London（伦敦玛丽女王大学）；Vision Semantics Ltd.（Vision Semantics有限公司）
The objective learning formulation is essential for the success of convolutional neural networks. In this work, we analyse thoroughly the standard learning objective functions for multi-class classification CNNs: softmax regression (SR) for single-label scenario and logistic regression (LR) for multi-label scenario. Our analyses lead to an inspiration of exploiting LR for single-label classification learning, and then the disclosing of the negative class distraction problem in LR. To address this problem, we develop two novel LR based objective functions that not only generalise the convention…
This paper presents a novel keypoints-based attention mechanism for visual recognition in still images. Deep Convolutional Neural Networks (CNNs) for recognizing images with distinctive classes have shown great success, but their performance in discriminating fine-grained changes is not at the same level. We address this by proposing an end-to-end CNN model, which learns meaningful features linking fine-grained changes using our novel attention mechanism. It captures the spatial structures in images by identifying semantic regions (SRs) and their spatial distributions, and is proved to be the …
Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；National University of Singapore（新加坡国立大学）；School of Software Technology, Zhejiang University（浙江大学软件学院）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新区（滨江）区块链研究院）；Bangsheng Technology Co., Ltd.（邦盛科技股份有限公司）；Robotics Institute, School of Computer Science, Carnegie Mellon University（卡内基梅隆大学计算机学院机器人研究所）
NSFlow: End-to-End Differentiable Neuro-Symbolic Optical Flow for Visual Odometry
State Key Laboratory of Intelligent Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology（华中科技大学机械科学与工程学院智能制造装备与技术国家重点实验室）
