Out-of-distribution (OOD) detection can be used in deep learning-based applications to reject outlier samples from being unreliably classified by deep neural networks. Learning to classify between OOD and in-distribution samples is difficult because data comprising the former is extremely diverse. It has been observed that an auxiliary OOD dataset is most effective in training a "rejection" network when its samples are semantically similar to in-distribution images. We first deduce that OOD images are perceived by a deep neural network to be semantically similar to in-distribution samples when they share a common background, as deep networks are observed to incorrectly classify such images with high confidence. We then propose a simple yet effective Key In-distribution feature Replacement BY inpainting (KIRBY) procedure that constructs a surrogate OOD dataset by replacing class-discriminative features of in-distribution samples with marginal background features. The procedure can be implemented using off-the-shelf vision algorithms, where each step within the algorithm is shown to make the surrogate data increasingly similar to in-distribution data. Design choices in each step are studied extensively, and an exhaustive comparison with state-of-the-art algorithms demonstrates KIRBY's competitiveness on various benchmarks.
Centro de Informática, Universidade Federal de Pernambuco（伯南布哥联邦大学信息中心）；Montreal Institute for Learning Algorithms (MILA)（蒙特利尔学习算法研究所（MILA））；Université de Montréal (UdeM)（蒙特利尔大学（UdeM））
Current out-of-distribution detection approaches usually present special requirements (e.g., collecting outlier data and hyperparameter validation) and produce side effects (e.g., classification accuracy drop and slow/inefficient inferences). Recently, entropic out-of-distribution detection has been proposed as a seamless approach (i.e., a solution that avoids all previously mentioned drawbacks). The entropic out-of-distribution detection solution uses the IsoMax loss for training and the entropic score for out-of-distribution detection. The IsoMax loss works as a drop-in replacement of the So…
A Data-Driven Approach to Support Clinical Renal Replacement Therapy
Department of Applied Science and Technology（应用科学与技术系）；Department of Inf. Eng., Computer Science and Mathematics（信息工程、计算机科学与数学系）；University of L'Aquila（拉奎拉大学）；Dipartimento di Scienze della Salute（健康科学系）；University of Florence（佛罗伦萨大学）
We propose a novel framework for Alzheimer's disease (AD) detection using brain MRIs. The framework starts with a data augmentation method called Brain-Aware Replacements (BAR), which leverages a standard brain parcellation to replace medically-relevant 3D brain regions in an anchor MRI from a randomly picked MRI to create synthetic samples. Ground truth "hard" labels are also linearly mixed depending on the replacement ratio in order to create "soft" labels. BAR produces a great variety of realistic-looking synthetic MRIs with higher local variability compared to other mix-based methods, such…
Universidade Federal de Pernambuco（伯南布哥联邦大学）；Montreal Institute for Learning Algorithms, University of Montreal（蒙特利尔大学蒙特利尔学习算法研究所）
Building robust deterministic neural networks remains a challenge. On the one hand, some approaches improve out-of-distribution detection at the cost of reducing classification accuracy in some situations. On the other hand, some methods simultaneously increase classification accuracy, uncertainty estimation, and out-of-distribution detection at the expense of reducing the inference efficiency. In this paper, we propose training deterministic neural networks using our DisMax loss, which works as a drop-in replacement for the usual SoftMax loss (i.e., the combination of the linear output layer,…
Centro de Informática, Universidade Federal de Pernambuco（伯南布哥联邦大学信息中心）；Montreal Institute for Learning Algorithms, University of Montreal（蒙特利尔大学蒙特利尔学习算法研究所）；Northwestern University（西北大学）
Out-of-distribution (OOD) detection approaches usually present special requirements (e.g., hyperparameter validation, collection of outlier data) and produce side effects (e.g., classification accuracy drop, slower energy-inefficient inferences). We argue that these issues are a consequence of the SoftMax loss anisotropy and disagreement with the maximum entropy principle. Thus, we propose the IsoMax loss and the entropic score. The seamless drop-in replacement of the SoftMax loss by IsoMax loss requires neither additional data collection nor hyperparameter validation. The trained models do no…
In this work, we focus on the problem of distinguishing a human written news article from a news article that is created by manipulating entities in a human written news article (e.g., replacing entities with factually incorrect entities). Such manipulated articles can mislead the reader by posing as a human written news article. We propose a neural network based detector that detects manipulated news articles by reasoning about the facts mentioned in the article. Our proposed detector exploits factual knowledge via graph convolutional neural network along with the textual information in the n…
Intent classification is a major task in spoken language understanding (SLU). Since most models are built with pre-collected in-domain (IND) training utterances, their ability to detect unsupported out-of-domain (OOD) utterances has a critical effect in practical use. Recent works have shown that using extra data and labels can improve the OOD detection performance, yet it could be costly to collect such data. This paper proposes to train a model with only IND data while supporting both IND intent classification and OOD detection. Our method designs a novel domain-regularized module (DRM) to r…
JR East Information Systems（东日本旅客铁道信息系统）；PARC, A Xerox Company（施乐帕克研究中心）
Although training data is essential for machine learning, railway companies are facing difficulties in gathering adequate images of defective equipment due to their proactive replacement of would be defective equipment. Nevertheless, proactive replacement is indispensable for safe and undisturbed operation of public transport. In this research, we have developed a model using CycleGAN to generate artificial images of defective equipment instead of real images. By adopting these generated images as training data, we verified that these images are indistinguishable from real images and they play…
LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection
Baidu Inc.（百度公司）；The University of Adelaide（阿德莱德大学）；Beihang University（北京航空航天大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Australian National University（澳大利亚国立大学）
We present a learned, spatially-varying steganography system that allows detecting when and how images have been altered by cropping, splicing or inpainting after publication. The system comprises a learned encoder that imperceptibly hides distinct positional signatures in every local image region before publication, and an accompanying learned decoder that extracts the steganographic signatures to determine, for each local image region, its 2D positional coordinates within the originally-published image. Crop and replacement edits become detectable by the inconsistencies they cause in the hid…
Carnegie Mellon University（卡内基梅隆大学）；Mila-University of Montreal（蒙特利尔大学米拉研究院）；Polytechnique Montreal（蒙特利尔综合理工大学）；Element AI（元素人工智能公司）
We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry. We achieve this by inferring the depth of facial keypoints of an input image in an unsupervised manner, without using any form of ground-truth depth information. We show how it is possible to use these depths as intermediate computations within a new backpropable loss to predict the parameters of a 3D affine transformation matrix that maps inferred 3D keypoints of an input face …
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Brigham and Women’s Hospital（布莱根妇女医院）；Santa Clara University（圣克拉拉大学）
Identifying the design of a failed implant is a key step in preoperative planning of revision total joint arthroplasty. Manual identification of the implant design from radiographic images is time consuming and prone to error. Failure to identify the implant design preoperatively can lead to increased operating room time, more complex surgery, increased blood loss, increased bone loss, increased recovery time, and overall increased healthcare costs. In this study, we present a novel, fully automatic and interpretable approach to identify the design of total hip replacement (THR) implants from …
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Brigham and Women’s Hospital（布莱根妇女医院）；Karolinska Institutet（卡罗林斯卡学院）；Danderyd Hospital（丹德吕德医院）
Plain radiography is widely used to detect mechanical loosening of total hip replacement (THR) implants. Currently, radiographs are assessed manually by medical professionals, which may be prone to poor inter and intra observer reliability and low accuracy. Furthermore, manual detection of mechanical loosening of THR implants requires experienced clinicians who might not always be readily available, potentially resulting in delayed diagnosis. In this study, we present a novel, fully automatic and interpretable approach to detect mechanical loosening of THR implants from plain radiographs using…
Huazhong University of Science and Technology（华中科技大学）
One major impediment in rapidly deploying object detection models for industrial applications is the lack of large annotated datasets. We currently have presented the Sacked Carton Dataset(SCD) that contains carton images from three scenarios, such as comprehensive pharmaceutical logistics company(CPLC), e-commerce logistics company(ECLC), fruit market(FM). However, due to domain shift, the model trained with one of the three scenarios in SCD has poor generalization ability when applied to the rest scenarios. To solve this problem, a novel image synthesis method is proposed to replace the fore…
National Robotics Engineering Center（国家机器人工程中心）；Carnegie Mellon University（卡内基梅隆大学）
As object detectors rapidly improve, attention has expanded past image-only networks to include a range of 3D and multimodal frameworks, especially ones that incorporate LiDAR. However, due to cost, logistics, and even some safety considerations, stereo can be an appealing alternative. Towards understanding the efficacy of stereo as a replacement for monocular input or LiDAR in object detectors, we show that multimodal learning with traditional disparity algorithms can improve image-based results without increasing the number of parameters, and that learning over stereo error can impart simila…
Isfahan University of Technology（伊斯法罕理工大学）；University of Michigan（密歇根大学）
Colonoscopy video frames might be contaminated by bright spots with unsaturated values known as specular reflection. Detection and removal of such reflections could enhance the quality of colonoscopy images and facilitate diagnosis procedure. In this paper we propose a novel two-phase method for this purpose, consisting of detection and removal phases. In the detection phase, we employ both HSV and RGB color space information for segmentation of specular reflections. We first train a non-linear SVM for selecting a color space based on image statistical features extracted from each channel of t…
Knowledge Distillation (KD) is a well-known training paradigm in deep neural networks where knowledge acquired by a large teacher model is transferred to a small student. KD has proven to be an effective technique to significantly improve the student's performance for various tasks including object detection. As such, KD techniques mostly rely on guidance at the intermediate feature level, which is typically implemented by minimizing an lp-norm distance between teacher and student activations during training. In this paper, we propose a replacement for the pixel-wise independent lp-norm based …
Modern convolutional neural networks (CNNs)-based face detectors have achieved tremendous strides due to large annotated datasets. However, misaligned results with high detection confidence but low localization accuracy restrict the further improvement of detection performance. In this paper, the authors first predict high confidence detection results on the training set itself. Surprisingly, a considerable part of them exist in the same misalignment problem. Then, the authors carefully examine these cases and point out that annotation misalignment is the main reason. Later, a comprehensive di…
University of Modena and Reggio Emilia（摩德纳和雷焦艾米利亚大学）；GoatAI S.r.l.（GoatAI 有限责任公司）；Technical University of Munich（慕尼黑工业大学）
Deep learning-based methods for video pedestrian detection and tracking require large volumes of training data to achieve good performance. However, data acquisition in crowded public environments raises data privacy concerns -- we are not allowed to simply record and store data without the explicit consent of all participants. Furthermore, the annotation of such data for computer vision applications usually requires a substantial amount of manual effort, especially in the video domain. Labeling instances of pedestrians in highly crowded scenarios can be challenging even for human annotators a…
University of Paderborn（帕德博恩大学）；IIIT-Allahabad（印度信息技术学院阿拉哈巴德分校）
Facial Key Points (FKPs) Detection is an important and challenging problem in the fields of computer vision and machine learning. It involves predicting the co-ordinates of the FKPs, e.g. nose tip, center of eyes, etc, for a given face. In this paper, we propose a LeNet adapted Deep CNN model - NaimishNet, to operate on facial key points data and compare our model's performance against existing state of the art approaches.
In this paper, we studied the problem of localizing a generic set of keypoints across multiple quadruped or four-legged animal species from images. Due to the lack of large scale animal keypoint dataset with ground truth annotations, we developed a novel dataset, AwA Pose, for keypoint detection of quadruped animals from images. Our dataset contains significantly more keypoints per animal and has much more diverse animals than the existing datasets for animal keypoint detection. We benchmarked the dataset with a state-of-the-art deep learning model for different keypoint detection tasks, inclu…
Xiamen University（厦门大学）；PKU-Wuhan Institute for Artificial Intelligence（北京大学-武汉人工智能研究院）
Frame prediction based on AutoEncoder plays a significant role in unsupervised video anomaly detection. Ideally, the models trained on the normal data could generate larger prediction errors of anomalies. However, the correlation between appearance and motion information is underutilized, which makes the models lack an understanding of normal patterns. Moreover, the models do not work well due to the uncontrollable generalizability of deep AutoEncoder. To tackle these problems, we propose a multi-level memory-augmented appearance-motion correspondence framework. The latent correspondence betwe…
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Freiburg（弗莱堡大学）；Max-Planck-Institute for Informatics（马克斯·普朗克信息学研究所）
In this paper, we introduce a contrastive learning framework for keypoint detection (CoKe). Keypoint detection differs from other visual tasks where contrastive learning has been applied because the input is a set of images in which multiple keypoints are annotated. This requires the contrastive learning to be extended such that the keypoints are represented and detected independently, which enables the contrastive loss to make the keypoint features different from each other and from the background. Our approach has two benefits: It enables us to exploit contrastive learning for keypoint detec…
Imam Khomeini International University（伊玛目霍梅尼国际大学）；University of Alicante（阿利坎特大学）；Institute for Research in Fundamental Sciences (IPM)（基础科学研究所（IPM））
Facial biometrics has been recently received tremendous attention as a convenient replacement for traditional authentication systems. Consequently, detecting malicious attempts has found great significance, leading to extensive studies in face anti-spoofing~(FAS),i.e., face presentation attack detection. Deep feature learning and techniques, as opposed to hand-crafted features, have promised a dramatic increase in the FAS systems' accuracy, tackling the key challenges of materializing the real-world application of such systems. Hence, a new research area dealing with the development of more ge…
UBTECH Sydney AI Centre（优必选悉尼人工智能中心）；The University of Sydney（悉尼大学）
Modern two-stage object detectors generally require excessively large models for their detection heads to achieve high accuracy. To address this problem, we propose that the model parameters of two-stage detection heads can be condensed and reduced by concentrating on object key parts. To this end, we first introduce an automatic object key part discovery task to make neural networks discover representative sub-parts in each foreground object. With these discovered key parts, we then decompose the object appearance modeling into a key part modeling process and a global modeling process for det…
The Chinese University of Hong Kong（香港中文大学）；Zhejiang University（浙江大学）；The University of Hong Kong（香港大学）；Shanghai AI Laboratory（上海人工智能实验室）
Current image-based keypoint detection methods for animal (including human) bodies and faces are generally divided into full-supervised and few-shot class-agnostic approaches. The former typically relies on laborious and time-consuming manual annotations, posing considerable challenges in expanding keypoint detection to a broader range of keypoint categories and animal species. The latter, though less dependent on extensive manual input, still requires necessary support images with annotation for reference during testing. To realize zero-shot keypoint detection without any prior annotation, we…
Vision-Learning-Mining Lab, University of Texas at Arlington（德克萨斯大学阿灵顿分校视觉-学习-挖掘实验室）；Heracleia - Human Centered Computing Lab, University of Texas at Arlington（德克萨斯大学阿灵顿分校Heracleia - 以人为本计算实验室）
Hand keypoints detection and pose estimation has numerous applications in computer vision, but it is still an unsolved problem in many aspects. An application of hand keypoints detection is in performing cognitive assessments of a subject by observing the performance of that subject in physical tasks involving rapid finger motion. As a part of this work, we introduce a novel hand key-points benchmark dataset that consists of hand gestures recorded specifically for cognitive behavior monitoring. We explore the state of the art methods in hand keypoint detection and we provide quantitative evalu…
Imperial College London（帝国理工学院）；Computer Vision Center（计算机视觉中心）；Arraiy, Inc.（Arraiy公司）
We introduce a novel approach for keypoint detection task that combines handcrafted and learned CNN filters within a shallow multi-scale architecture. Handcrafted filters provide anchor structures for learned filters, which localize, score and rank repeatable features. Scale-space representation is used within the network to extract keypoints at different levels. We design a loss function to detect robust features that exist across a range of scales and to maximize the repeatability score. Our Key.Net model is trained on data synthetically created from ImageNet and evaluated on HPatches benchm…
Pohang University of Science and Technology (POSTECH)（浦项科技大学）
Detecting robust keypoints from an image is an integral part of many computer vision problems, and the characteristic orientation and scale of keypoints play an important role for keypoint description and matching. Existing learning-based methods for keypoint detection rely on standard translation-equivariant CNNs but often fail to detect reliable keypoints against geometric variations. To learn to detect robust oriented keypoints, we introduce a self-supervised learning framework using rotation-equivariant CNNs. We propose a dense orientation alignment loss by an image pair generated by synth…
Monocular 3D object detection is well-known to be a challenging vision task due to the loss of depth information; attempts to recover depth using separate image-only approaches lead to unstable and noisy depth estimates, harming 3D detections. In this paper, we propose a novel keypoint-based approach for 3D object detection and localization from a single RGB image. We build our multi-branch model around 2D keypoint detection in images and complement it with a conceptually simple geometric reasoning method. Our network performs in an end-to-end manner, simultaneously and interdependently estima…
