Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However, in practice, random data augmentation, such as random image cropping, is low-efficiency and might introduce many uncontrolled background noises. In this paper, we propose Weakly Supervised Data Augmentation Network (WS-DAN) to explore the potential of data augmentation. Specifically, for each training image, we first generate attention maps to represent the object's discriminative parts by weakly supervised learning. Next, we augment the image guided by these attention maps, including attention cropping and attention dropping. The proposed WS-DAN improves the classification accuracy in two folds. In the first stage, images can be seen better since more discriminative parts' features will be extracted. In the second stage, attention regions provide accurate location of object, which ensures our model to look at the object closer and further improve the performance. Comprehensive experiments in common fine-grained visual classification datasets show that our WS-DAN surpasses the state-of-the-art methods, which demonstrates its effectiveness.
Feature Augmentation for Self-supervised Contrastive Learning: A Closer Look
Shenzhen Institute of Advanced Technology, CAS（中国科学院深圳先进技术研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Sangfor Technologies Inc.（深信服科技股份有限公司）
UBTECH Sydney Artificial Intelligence Centre, The University of Sydney（悉尼大学优必选悉尼人工智能中心）；The University of Sydney（悉尼大学）
Deep learning-based computer vision is usually data-hungry. Many researchers attempt to augment datasets with synthesized data to improve model robustness. However, the augmentation of popular pedestrian datasets, such as Caltech and Citypersons, can be extremely challenging because real pedestrians are commonly in low quality. Due to the factors like occlusions, blurs, and low-resolution, it is significantly difficult for existing augmentation approaches, which generally synthesize data using 3D engines or generative adversarial networks (GANs), to generate realistic-looking pedestrians. Alte…
The recently proposed panoptic segmentation task presents a significant challenge of image understanding with computer vision by unifying semantic segmentation and instance segmentation tasks. In this paper we present an efficient and novel panoptic data augmentation (PanDA) method which operates exclusively in pixel space, requires no additional data or training, and is computationally cheap to implement. By retraining original state-of-the-art models on PanDA augmented datasets generated with a single frozen set of parameters, we show robust performance gains in panoptic segmentation, instan…
In contrastive self-supervised learning, the common way to learn discriminative representation is to pull different augmented "views" of the same image closer while pushing all other images further apart, which has been proven to be effective. However, it is unavoidable to construct undesirable views containing different semantic concepts during the augmentation procedure. It would damage the semantic consistency of representation to pull these augmentations closer in the feature space indiscriminately. In this study, we introduce feature-level augmentation and propose a novel semantics-consis…
University of Oxford（牛津大学）；Naver Labs Europe（Naver欧洲实验室）
Traditional approaches for learning 3D object categories use either synthetic data or manual supervision. In this paper, we propose a method which does not require manual annotations and is instead cued by observing objects from a moving vantage point. Our system builds on two innovations: a Siamese viewpoint factorization network that robustly aligns different videos together without explicitly comparing 3D shapes; and a 3D shape completion network that can extract the full shape of an object from partial observations. We also demonstrate the benefits of configuring networks to perform probab…
Linköping University（林雪平大学）；Sectra AB（斯凯特拉公司）；Center for Medical Image Science and Visualization（医学影像科学与可视化中心）
Domain shift is a significant problem in histopathology. There can be large differences in data characteristics of whole-slide images between medical centers and scanners, making generalization of deep learning to unseen data difficult. To gain a better understanding of the problem, we present a study on convolutional neural networks trained for tumor classification of H&E stained whole-slide images. We analyze how augmentation and normalization strategies affect performance and learned representations, and what features a trained model respond to. Most centrally, we present a novel measure fo…
State Key Laboratory of Intelligent Technology and Systems（智能技术与系统国家重点实验室）；Tsinghua University（清华大学）；University of Chinese Academy of Sciences（中国科学院大学）
Tremendous efforts have been made on instance segmentation but the mask quality is still not satisfactory. The boundaries of predicted instance masks are usually imprecise due to the low spatial resolution of feature maps and the imbalance problem caused by the extremely low proportion of boundary pixels. To address these issues, we propose a conceptually simple yet effective post-processing refinement framework to improve the boundary quality based on the results of any instance segmentation model, termed BPR. Following the idea of looking closer to segment boundaries better, we extract and r…
Multimedia Systems Department Gdańsk University of Technology（格但斯克工业大学多媒体系统系）；Gdańsk University of Technology（格但斯克工业大学）；Electronics, Telecommunications and Informatics Faculty, Gdańsk University of Technology（格但斯克工业大学电子、电信与信息学院）
While recent computer vision algorithms achieve impressive performance on many benchmarks, they lack robustness - presented with an image from a different distribution, (e.g. weather or lighting conditions not considered during training), they may produce an erroneous prediction. Therefore, it is desired that such a model will be able to reliably predict its confidence measure. In this work, uncertainty estimation for the task of semantic segmentation is evaluated under a varying level of domain shift: in a cross-dataset setting and when adapting a model trained on data from the simulation. It…
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）
The training of Generative Adversarial Networks (GANs) requires a large amount of data, stimulating the development of new augmentation methods to alleviate the challenge. Oftentimes, these methods either fail to produce enough new data or expand the dataset beyond the original manifold. In this paper, we propose a new augmentation method that guarantees to keep the new data within the original data manifold thanks to the optimal transport theory. The proposed algorithm finds cliques in the nearest-neighbors graph and, at each sampling iteration, randomly draws one clique to compute the Wasser…
Learnable keypoint detectors and descriptors are beginning to outperform classical hand-crafted feature extraction methods. Recent studies on self-supervised learning of visual representations have driven the increasing performance of learnable models based on deep networks. By leveraging traditional data augmentations and homography transformations, these networks learn to detect corners under adverse conditions such as extreme illumination changes. However, their generalization capabilities are limited to corner-like features detected a priori by classical methods or synthetically generated …
University of Western Ontario（西安大略大学）；University of Waterloo（滑铁卢大学）
CNNs have made a tremendous impact on the field of computer vision in the last several years. The main component of any CNN architecture is the convolution operation, which is translation invariant by design. However, location in itself can be an important cue. For example, a salient object is more likely to be closer to the center of the image, the sky in the top part of an image, etc. To include the location cue for feature learning, we propose to augment the color image, the usual input to CNNs, with one or more channels that carry location information. We test two approaches for adding loc…
The identification of lesion within medical image data is necessary for diagnosis, treatment and prognosis. Segmentation and classification approaches are mainly based on supervised learning with well-paired image-level or voxel-level labels. However, labeling the lesion in medical images is laborious requiring highly specialized knowledge. We propose a medical image synthesis model named abnormal-to-normal translation generative adversarial network (ANT-GAN) to generate a normal-looking medical image based on its abnormal-looking counterpart without the need for paired training data. Unlike t…
Recent work indicates that, besides being a challenge in producing perceptually pleasing images, low light proves more difficult for machine cognition than previously thought. In our work, we take a closer look at object detection in low light. First, to support the development and evaluation of new methods in this domain, we present a high-quality large-scale Night Object Detection (NOD) dataset showing dynamic scenes captured on the streets at night. Next, we directly link the lighting conditions to perceptual difficulty and identify what makes low light problematic for machine cognition. Ac…
Seoul National University of Science and Technology（首尔科学技术大学）
This work addresses the task of electric vehicle (EV) charging inlet detection for autonomous EV charging robots. Recently, automated EV charging systems have received huge attention to improve users' experience and to efficiently utilize charging infrastructures and parking lots. However, most related works have focused on system design, robot control, planning, and manipulation. Towards robust EV charging inlet detection, we propose a new dataset (EVCI dataset) and a novel data augmentation method that is based on image-to-image translation where typical image-to-image translation methods sy…
Charles Sturt University（查尔斯特大学）；TerraCipher Pty Ltd（TerraCipher私人有限公司）；Food Agility CRC Ltd（食品敏捷合作研究中心有限公司）
You Only Look Once (YOLO) is a single-stage object detection model popular for real-time object detection, accuracy, and speed. This paper investigates the YOLOv5 model to identify cattle in the yards. The current solution to cattle identification includes radio-frequency identification (RFID) tags. The problem occurs when the RFID tag is lost or damaged. A biometric solution identifies the cattle and helps to assign the lost or damaged tag or replace the RFID-based system. Muzzle patterns in cattle are unique biometric solutions like a fingerprint in humans. This paper aims to present our rec…
CLIP-Guided Data Augmentation for Night-Time Image Dehazing
Hangzhou Dianzi University（杭州电子科技大学）；Jinan University（济南大学）；Hefei University of Technology（合肥工业大学）；Wuhan University（武汉大学）；The University of Tokyo（东京大学）
Politecnico di Torino（都灵理工大学）；Italian Institute of Technology（意大利理工学院）；MPI for Informatics（马克斯·普朗克信息学研究所）；University of Tübingen（蒂宾根大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Being able to segment unseen classes not observed during training is an important technical challenge in deep learning, because of its potential to reduce the expensive annotation required for semantic segmentation. Prior zero-label semantic segmentation works approach this task by learning visual-semantic embeddings or generative models. However, they are prone to overfitting on the seen classes because there is no training signal for them. In this paper, we study the challenging generalized zero-label semantic segmentation task where the model has to segment both seen and unseen classes at t…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Beijing University of Posts and Telecommunications（北京邮电大学）；Zhejiang Lab（之江实验室）；University of Chinese Academy of Sciences（中国科学院大学）；University of Science and Technology Beijing（北京科技大学）
Limited by the locality of convolutional neural networks, most existing local features description methods only learn local descriptors with local information and lack awareness of global and surrounding spatial context. In this work, we focus on making local descriptors "look wider to describe better" by learning local Descriptors with More Than just Local information (MTLDesc). Specifically, we resort to context augmentation and spatial attention mechanisms to make our MTLDesc obtain non-local awareness. First, Adaptive Global Context Augmented Module and Diverse Local Context Augmented Modu…
Deepfake media is becoming widespread nowadays because of the easily available tools and mobile apps which can generate realistic looking deepfake videos/images without requiring any technical knowledge. With further advances in this field of technology in the near future, the quantity and quality of deepfake media is also expected to flourish, while making deepfake media a likely new practical tool to spread mis/disinformation. Because of these concerns, the deepfake media detection tools are becoming a necessity. In this study, we propose a novel hybrid transformer network utilizing early fe…
EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classification
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学现代软件技术国家重点实验室）；Department of Computer Science and Technology, Nanjing University（南京大学计算机科学与技术系）；School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）；School of Electronic Science and Engineering, Nanjing University（南京大学电子科学与工程学院）
本文提出无需调参的自适应数据增强框架 EntAugment，依据模型 softmax 输出的信息熵逐样本调整增强幅度，并结合 EntLoss 正则化，在图像分类中以低额外成本取得优于现有 DA 方法的性能。
Looking through the past: better knowledge retention for generative replay in continual learning
IDEAS NCBR；Gdańsk University of Technology（格但斯克工业大学）；Warsaw University of Technology（华沙工业大学）；Jagiellonian University（雅盖隆大学）；Tooploox；Computer Vision Center（计算机视觉中心）；Universitat Autònoma Barcelona（巴塞罗那自治大学）
A Vision Transformer (ViT) is a simple neural architecture amenable to serve several computer vision tasks. It has limited built-in architectural priors, in contrast to more recent architectures that incorporate priors either about the input data or of specific tasks. Recent works show that ViTs benefit from self-supervised pre-training, in particular BerT-like pre-training like BeiT. In this paper, we revisit the supervised training of ViTs. Our procedure builds upon and simplifies a recipe introduced for training ResNet-50. It includes a new simple data-augmentation procedure with only 3 aug…
Rectified Decoupled Dataset Distillation: A Closer Look for Fair and Comprehensive Evaluation
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
We propose a Three-Player Generative Adversarial Network to improve classification networks. In addition to the game played between the discriminator and generator, a competition is introduced between the generator and the classifier. The generator's objective is to synthesize samples that are both realistic and hard to label for the classifier. Even though we make no assumptions on the type of augmentations to learn, we find that the model is able to synthesize realistically looking examples that are hard for the classification model. Furthermore, the classifier becomes more robust when train…
Pontifical Catholic University of Rio de Janeiro（里约热内卢天主教大学）
In several application areas, such as medical diagnosis, spam filtering, fraud detection, and seismic data analysis, it is very usual to find relevant classification tasks where some class occurrences are rare. This is the so called class imbalance problem, which is a challenge in machine learning. In this work, we propose the SeismoFlow a flow-based generative model to create synthetic samples, aiming to address the class imbalance. Inspired by the Glow model, it uses interpolation on the learned latent space to produce synthetic samples for one rare class. We apply our approach to the develo…
Are nuclear masks all you need for improved out-of-domain generalisation? A closer look at cancer classification in histopathology
University of Oslo（奥斯陆大学）；Otto-von-Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）；Singapore Institute of Technology（新加坡科技学院）；Oslo University Hospital（奥斯陆大学医院）；UiT The Arctic University of Norway（挪威北极大学）
ONERA, The French Aerospace Lab（法国航空航天实验室（ONERA））；Univ. Bretagne-Sud（南布列塔尼大学）
This work addresses the scarcity of annotated hyperspectral data required to train deep neural networks. Especially, we investigate generative adversarial networks and their application to the synthesis of consistent labeled spectra. By training such networks on public datasets, we show that these models are not only able to capture the underlying distribution, but also to generate genuine-looking and physically plausible spectra. Moreover, we experimentally validate that the synthetic samples can be used as an effective data augmentation strategy. We validate our approach on several public hy…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Tübingen（图宾根大学）；Amazon（亚马逊）
In recent years, deep generative models have gained significance due to their ability to synthesize natural-looking images with applications ranging from virtual reality to data augmentation for training computer vision models. While existing models are able to faithfully learn the image distribution of the training set, they often lack controllability as they operate in 2D pixel space and do not model the physical image formation process. In this work, we investigate the importance of 3D reasoning for photorealistic rendering. We present an approach for learning light transport in static and …
Looking Beyond the Scale: Do Surgical Skill Models Learn Transferable Representations Across Assessment Rubrics?
National Center for Tumor Diseases (NCT)（国家肿瘤疾病中心）；DKFZ（德国癌症研究中心）；Faculty of Medicine and University Hospital Carl Gustav Carus（卡尔·古斯塔夫·卡鲁斯医学院及大学医院）；TUD Dresden University of Technology（德累斯顿工业大学）；Helmholtz-Zentrum Dresden-Rossendorf (HZDR)（德累斯顿-罗森多夫亥姆霍兹中心）；BMFTR Research Hub 6G-Life（BMFTR 6G生活研究中心）；Deutsches Krebsforschungszentrum (DKFZ)（德国癌症研究中心）；The Centre for Tactile Internet with Human-in-the-Loop (CeTI)（人在回路触觉互联网中心）
ETH Zurich（苏黎世联邦理工学院）；University of Zurich（苏黎世大学）；Stanford University（斯坦福大学）；Stanford Stroke Center（斯坦福中风中心）；Institute for Biomedical Engineering（生物医学工程研究所）
We show that high quality, diverse and realistic-looking diffusion-weighted magnetic resonance images can be synthesized using deep generative models. Based on professional neuroradiologists' evaluations and diverse metrics with respect to quality and diversity of the generated synthetic brain images, we present two networks, the Introspective Variational Autoencoder and the Style-Based GAN, that qualify for data augmentation in the medical field, where information is saved in a dispatched and inhomogeneous way and access to it is in many aspects restricted.
The University of Tokyo（东京大学）；National Institute of Informatics（国立信息学研究所）；University of Cambridge（剑桥大学）；Cancer Research UK Cambridge Institute（英国癌症研究院剑桥研究所）；University of Milano-Bicocca（米兰比可卡大学）；Chubu University（中部大学）；Jikei University School of Medicine（东京慈惠会医科大学）；Kyushu University（九州大学）
Convolutional Neural Networks (CNNs) achieve excellent computer-assisted diagnosis with sufficient annotated training data. However, most medical imaging datasets are small and fragmented. In this context, Generative Adversarial Networks (GANs) can synthesize realistic/diverse additional training images to fill the data lack in the real image distribution; researchers have improved classification by augmenting data with noise-to-image (e.g., random noise samples to diverse pathological images) or image-to-image GANs (e.g., a benign image to a malignant one). Yet, no research has reported resul…
University of California, Davis（加州大学戴维斯分校）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
We are interested in representation learning in self-supervised, supervised, and semi-supervised settings. Some recent self-supervised learning methods like mean-shift (MSF) cluster images by pulling the embedding of a query image to be closer to its nearest neighbors (NNs). Since most NNs are close to the query by design, the averaging may not affect the embedding of the query much. On the other hand, far away NNs may not be semantically related to the query. We generalize the mean-shift idea by constraining the search space of NNs using another source of knowledge so that NNs are far from th…
We introduce a self-attending task generative adversarial network (SATGAN) and apply it to the problem of augmenting synthetic high contrast scientific imagery of resident space objects with realistic noise patterns and sensor characteristics learned from collected data. Augmenting these synthetic data is challenging due to the highly localized nature of semantic content in the data that must be preserved. Real collected images are used to train a network what a given class of sensor's images should look like. The trained network then acts as a filter on noiseless context images and outputs re…
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；University of Bern（伯尔尼大学）；University of California, Davis（加利福尼亚大学戴维斯分校）
Recently, contrastive learning has achieved great results in self-supervised learning, where the main idea is to push two augmentations of an image (positive pairs) closer compared to other random images (negative pairs). We argue that not all random images are equal. Hence, we introduce a self supervised learning algorithm where we use a soft similarity for the negative images rather than a binary distinction between positive and negative pairs. We iteratively distill a slowly evolving teacher model to the student model by capturing the similarity of a query image to some random images and tr…
Siemens Corporate Technology（西门子企业技术部）；University of Passau（帕绍大学）
With the increasing availability of large databases of 3D CAD models, depth-based recognition methods can be trained on an uncountable number of synthetically rendered images. However, discrepancies with the real data acquired from various depth sensors still noticeably impede progress. Previous works adopted unsupervised approaches to generate more realistic depth data, but they all require real scans for training, even if unlabeled. This still represents a strong requirement, especially when considering real-life/industrial settings where real training images are hard or impossible to acquir…
Technical University Munich（慕尼黑工业大学）；Helmholtz AI（亥姆霍兹人工智能研究院）
In computational pathology, we often face a scarcity of annotations and a large amount of unlabeled data. One method for dealing with this is semi-supervised learning which is commonly split into a self-supervised pretext task and a subsequent model fine-tuning. Here, we compress this two-stage training into one by introducing S5CL, a unified framework for fully-supervised, self-supervised, and semi-supervised learning. With three contrastive losses defined for labeled, unlabeled, and pseudo-labeled images, S5CL can learn feature representations that reflect the hierarchy of distance relations…
Semantic Positive Pairs for Enhancing Visual Representation Learning of Instance Discrimination Methods
Department of Computing Science University of Aberdeen, UK（计算科学系大学爱丁堡大学，英国）；Department of Computing Science & Interdisciplinary Centre for Data and AI University of Aberdeen, UK（计算科学系与数据和人工智能交叉研究中心大学爱丁堡大学，英国）
Uber ATG（优步先进技术集团）；University of Toronto（多伦多大学）；Princeton University（普林斯顿大学）
Modern autonomous driving systems rely heavily on deep learning models to process point cloud sensory data; meanwhile, deep models have been shown to be susceptible to adversarial attacks with visually imperceptible perturbations. Despite the fact that this poses a security concern for the self-driving industry, there has been very little exploration in terms of 3D perception, as most adversarial attacks have only been applied to 2D flat images. In this paper, we address this issue and present a method to generate universal 3D adversarial objects to fool LiDAR detectors. In particular, we demo…
NeuroSYS（NeuroSYS公司）；Wroclaw University of Science and Technology（弗罗茨瓦夫科技大学）
We introduce an effective strategy to generate an annotated synthetic dataset of microbiological images of Petri dishes that can be used to train deep learning models in a fully supervised fashion. The developed generator employs traditional computer vision algorithms together with a neural style transfer method for data augmentation. We show that the method is able to synthesize a dataset of realistic looking images that can be used to train a neural network model capable of localising, segmenting, and classifying five different microbial species. Our method requires significantly fewer resou…
We describe a method for 3D human pose estimation from transient images (i.e., a 3D spatio-temporal histogram of photons) acquired by an optical non-line-of-sight (NLOS) imaging system. Our method can perceive 3D human pose by `looking around corners' through the use of light indirectly reflected by the environment. We bring together a diverse set of technologies from NLOS imaging, human pose estimation and deep reinforcement learning to construct an end-to-end data processing pipeline that converts a raw stream of photon measurements into a full 3D human pose sequence estimate. Our contributi…
