For visual object recognition tasks, the illumination variations can cause distinct changes in object appearance and thus confuse the deep neural network based recognition models. Especially for some rare illumination conditions, collecting sufficient training samples could be time-consuming and expensive. To solve this problem, in this paper we propose a novel neural network architecture called Separating-Illumination Network (Sill-Net). Sill-Net learns to separate illumination features from images, and then during training we augment training samples with these separated illumination features in the feature space. Experimental results demonstrate that our approach outperforms current state-of-the-art methods in several object classification benchmarks.
Generalization Gap in Data Augmentation: Insights from Illumination
South China University of Technology（华南理工大学）；Hitachi Elevator (China) Co., Ltd.（日立电梯（中国）有限公司）；Hitachi Building Technology (Guangzhou) Co., Ltd.（日立楼宇科技（广州）有限公司）；Zhejiang Lab（之江实验室）
A core challenge in background subtraction (BGS) is handling videos with sudden illumination changes in consecutive frames. In this paper, we tackle the problem from a data point-of-view using data augmentation. Our method performs data augmentation that not only creates endless data on the fly, but also features semantic transformations of illumination which enhance the generalisation of the model. It successfully simulates flashes and shadows by applying the Euclidean distance transform over a binary mask that is randomly generated. Such data allows us to effectively train an illumination-in…
Mitigating Illumination-Induced Domain Shift in Night-Time Pedestrian Detection for Intelligent Vehicles using Annotation-Preserving Diffusion Augmentation
Fu Jen Catholic University（辅仁大学）；National Tsing Hua University（国立清华大学）；Tsinghua University（清华大学）
The performance of a convolutional neural network (CNN) based face recognition model largely relies on the richness of labelled training data. Collecting a training set with large variations of a face identity under different poses and illumination changes, however, is very expensive, making the diversity of within-class face images a critical issue in practice. In this paper, we propose a 3D model-assisted domain-transferred face augmentation network (DotFAN) that can generate a series of variants of an input face based on the knowledge distilled from existing rich face datasets collected fro…
At the heart of the success of deep learning is the quality of the data. Through data augmentation, one can train models with better generalization capabilities and thus achieve greater results in their field of interest. In this work, we explore how to augment a varied set of image datasets through relighting so as to improve the ability of existing models to be invariant to illumination changes, namely for learned descriptors. We develop a tool, based on an encoder-decoder network, that is able to quickly generate multiple variations of the illumination of various input scenes whilst also al…
Escola Politècnica Superior, Universitat de Girona（赫罗纳大学高等理工学院）
Fully automatic detection of skin lesions in dermatoscopic images can facilitate early diagnosis and repression of malignant melanoma and non-melanoma skin cancer. Although convolutional neural networks are a powerful solution, they are limited by the illumination spectrum of annotated dermatoscopic screening images, where color is an important discriminative feature. In this paper, we propose an adaptive color augmentation technique to amplify data expression and model performance, while regulating color difference and saturation to minimize the risks of using synthetic data. Through deep vis…
Object detection and semantic segmentation are two of the most widely adopted deep learning algorithms in agricultural applications. One of the major sources of variability in image quality acquired in the outdoors for such tasks is changing lighting condition that can alter the appearance of the objects or the contents of the entire image. While transfer learning and data augmentation to some extent reduce the need for large amount of data to train deep neural networks, the large variety of cultivars and the lack of shared datasets in agriculture makes wide-scale field deployments difficult. …
Self-supervised learning of depth has been a highly studied topic of research as it alleviates the requirement of having ground truth annotations for predicting depth. Depth is learnt as an intermediate solution to the task of view synthesis, utilising warped photometric consistency. Although it gives good results when trained using stereo data, the predicted depth is still sensitive to noise, illumination changes and specular reflections. Also, occlusion can be tackled better by learning depth from a single camera. We propose ADAA, utilising depth augmentation as depth supervision for learnin…
Graduate School of Automotive Engineering（汽车工程研究生院）；Seoul National University of Science and Technology（首尔国立科技大学）；Department of Mechanics and Automotive Engineering（力学与汽车工程系）
Visual surveillance aims to stably detect a foreground object using a continuous image acquired from a fixed camera. Recent deep learning methods based on supervised learning show superior performance compared to classical background subtraction algorithms. However, there is still a room for improvement in static foreground, dynamic background, hard shadow, illumination changes, camouflage, etc. In addition, most of the deep learning-based methods operates well on environments similar to training. If the testing environments are different from training ones, their performance degrades. As a re…
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）
SMFormer: Empowering Self-supervised Stereo Matching via Foundation Models and Data Augmentation
Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）；Hong Kong Generative AI Research and Development Center, The Hong Kong University of Science and Technology（香港科技大学香港生成式人工智能研发中心）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；School of Electronics and Communication Engineering, the Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University（中山大学深圳校区电子与通信工程学院）
How Important are Data Augmentations to Close the Domain Gap for Object Detection in Orbit?
Institute of Robotics and Mechatronics, German Aerospace Center (DLR)（德国航空航天中心机器人与机电一体化研究所）；Department of Informatics, Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院信息学系）；Department of Computer Science, Technical University of Munich (TUM)（慕尼黑工业大学计算机科学系）
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 …
National Technical University of Athens（雅典国立技术大学）；Queen Mary University of London（伦敦玛丽女王大学）
Automatic Facial Expression Recognition (FER) has attracted increasing attention in the last 20 years since facial expressions play a central role in human communication. Most FER methodologies utilize Deep Neural Networks (DNNs) that are powerful tools when it comes to data analysis. However, despite their power, these networks are prone to overfitting, as they often tend to memorize the training data. What is more, there are not currently a lot of in-the-wild (i.e. in unconstrained environment) large databases for FER. To alleviate this issue, a number of data augmentation techniques have be…
Image retrieval methods for place recognition learn global image descriptors that are used for fetching geo-tagged images at inference time. Recent works have suggested employing weak and self-supervision for mining hard positives and hard negatives in order to improve localization accuracy and robustness to visibility changes (e.g. in illumination or view point). However, generating hard positives, which is essential for obtaining robustness, is still limited to hard-coded or global augmentations. In this work we propose an adversarial method to guide the creation of hard positives for traini…
University of Milano – Bicocca（米兰比可卡大学）；Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；University of Florence（佛罗伦萨大学）
Several recent works on self-supervised learning are trained by mapping different augmentations of the same image to the same feature representation. The data augmentations used are of crucial importance to the quality of learned feature representations. In this paper, we analyze how the color jitter traditionally used in data augmentation negatively impacts the quality of the color features in learned feature representations. To address this problem, we propose a more realistic, physics-based color data augmentation - which we call Planckian Jitter - that creates realistic variations in chrom…
Technical University of Munich（慕尼黑工业大学）；Toyota Research Institute（丰田研究院）；Siemens Corporate Technology（西门子公司技术部）
We present a novel approach to tackle domain adaptation between synthetic and real data. Instead, of employing "blind" domain randomization, i.e., augmenting synthetic renderings with random backgrounds or changing illumination and colorization, we leverage the task network as its own adversarial guide toward useful augmentations that maximize the uncertainty of the output. To this end, we design a min-max optimization scheme where a given task competes against a special deception network to minimize the task error subject to the specific constraints enforced by the deceiver. The deception net…
In this paper, we propose a data augmentation framework for Optical Character Recognition (OCR). The proposed framework is able to synthesize new viewing angles and illumination scenarios, effectively enriching any available OCR dataset. Its modular structure allows to be modified to match individual user requirements. The framework enables to comfortably scale the enlargement factor of the available dataset. Furthermore, the proposed method is not restricted to single frame OCR but can also be applied to video OCR. We demonstrate the performance of our framework by augmenting a 15% subset of …
Mutual Information guided Visual Contrastive Learning
Antiquus S. Hippocampus, Natalia Cerebro & Amelie P. Amygdale Department of Computer Science Cranberry-Lemon University Pittsburgh, PA 15213, USA（计算机科学系，Cranberry-Lemon大学）；Ji Q. Ren & Yevgeny LeNet Department of Computational Neuroscience University of the Witwatersrand Joburg, South Africa（计算神经科学系，乌特雷赫大学）
Optical flow is the motion of a pixel between at least two consecutive video frames and can be estimated through an end-to-end trainable convolutional neural network. To this end, large training datasets are required to improve the accuracy of optical flow estimation. Our paper presents OmniFlow: a new synthetic omnidirectional human optical flow dataset. Based on a rendering engine we create a naturalistic 3D indoor environment with textured rooms, characters, actions, objects, illumination and motion blur where all components of the environment are shuffled during the data capturing process.…
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 …
University of Agder（阿格德尔大学）；Institute of Marine Research（海洋研究所）
Our understanding and ability to effectively monitor and manage coastal ecosystems are severely limited by observation methods. Automatic recognition of species in natural environment is a promising tool which would revolutionize video and image analysis for a wide range of applications in marine ecology. However, classifying fish from images captured by underwater cameras is in general very challenging due to noise and illumination variations in water. Previous classification methods in the literature relies on filtering the images to separate the fish from the background or sharpening the im…
Background subtraction is a basic task in computer vision and video processing often applied as a pre-processing step for object tracking, people recognition, etc. Recently, a number of successful background-subtraction algorithms have been proposed, however nearly all of the top-performing ones are supervised. Crucially, their success relies upon the availability of some annotated frames of the test video during training. Consequently, their performance on completely "unseen" videos is undocumented in the literature. In this work, we propose a new, supervised, background-subtraction algorithm…
SEDDI（SEDDI 公司）；Universidad Carlos III de Madrid（马德里卡洛斯三世大学）；Universidad Rey Juan Carlos（胡安·卡洛斯国王大学）
We present a deep learning-based method for propagating spatially-varying visual material attributes (e.g. texture maps or image stylizations) to larger samples of the same or similar materials. For training, we leverage images of the material taken under multiple illuminations and a dedicated data augmentation policy, making the transfer robust to novel illumination conditions and affine deformations. Our model relies on a supervised image-to-image translation framework and is agnostic to the transferred domain; we showcase a semantic segmentation, a normal map, and a stylization. Following a…
It is well known that deep learning approaches to face recognition and facial landmark detection suffer from biases in modern training datasets. In this work, we propose to use synthetic face images to reduce the negative effects of dataset biases on these tasks. Using a 3D morphable face model, we generate large amounts of synthetic face images with full control over facial shape and color, pose, illumination, and background. With a series of experiments, we extensively test the effects of priming deep nets by pre-training them with synthetic faces. We observe the following positive effects f…
University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）；College of Computing and Informatics（计算与信息学院）
Recently, there has been a remarkable increase in the interest towards skeleton-based action recognition within the research community, owing to its various advantageous features, including computational efficiency, representative features, and illumination invariance. Despite this, researchers continue to explore and investigate the most optimal way to represent human actions through skeleton representation and the extracted features. As a result, the growth and availability of human action recognition datasets have risen substantially. In addition, deep learning-based algorithms have gained …
Pose variation is one of the key challenges in face recognition. Conventional techniques mainly focus on face frontalization or face augmentation in image space. However, transforming face images in image space is not guaranteed to preserve the lossless identity features of the original image. Moreover, these methods suffer from more computational costs and memory requirements due to the additional models. We argue that it is more desirable to perform feature transformation in hierarchical feature space rather than image space, which can take advantage of different feature levels and benefit f…
Australian Centre for Field Robotics（澳大利亚野外机器人中心）；University of Sydney（悉尼大学）
Hyperspectral imaging sensors are becoming increasingly popular in robotics applications such as agriculture and mining, and allow per-pixel thematic classification of materials in a scene based on their unique spectral signatures. Recently, convolutional neural networks have shown remarkable performance for classification tasks, but require substantial amounts of labelled training data. This data must sufficiently cover the variability expected to be encountered in the environment. For hyperspectral data, one of the main variations encountered outdoors is due to incident illumination, which c…
Baze University（巴泽大学）；The University of the West of England（西英格兰大学）
Deep networks have achieved huge successes in application domains like object and face recognition. The performance gain is attributed to different facets of the network architecture such as: depth of the convolutional layers, activation function, pooling, batch normalization, forward and back propagation and many more. However, very little emphasis is made on the preprocessors. Therefore, in this paper, the network's preprocessing module is varied across different preprocessing approaches while keeping constant other facets of the network architecture, to investigate the contribution preproce…
University of Maryland, College Park（马里兰大学帕克分校）；Fudan University（复旦大学）；New York University（纽约大学）
Adversarial training is the industry standard for producing models that are robust to small adversarial perturbations. However, machine learning practitioners need models that are robust to other kinds of changes that occur naturally, such as changes in the style or illumination of input images. Such changes in input distribution have been effectively modeled as shifts in the mean and variance of deep image features. We adapt adversarial training by directly perturbing feature statistics, rather than image pixels, to produce models that are robust to various unseen distributional shifts. We ex…
A challenge of skeleton-based action recognition is the difficulty to classify actions with similar motions and object-related actions. Visual clues from other streams help in that regard. RGB data are sensible to illumination conditions, thus unusable in the dark. To alleviate this issue and still benefit from a visual stream, we propose a modular network (FUSION) combining skeleton and infrared data. A 2D convolutional neural network (CNN) is used as a pose module to extract features from skeleton data. A 3D CNN is used as an infrared module to extract visual cues from videos. Both feature v…
NEC Labs America（NEC美国实验室）；UC Merced（加州大学默塞德分校）；Dalian University of Technology（大连理工大学）；UC San Diego（加州大学圣迭戈分校）
Despite rapid advances in face recognition, there remains a clear gap between the performance of still image-based face recognition and video-based face recognition, due to the vast difference in visual quality between the domains and the difficulty of curating diverse large-scale video datasets. This paper addresses both of those challenges, through an image to video feature-level domain adaptation approach, to learn discriminative video frame representations. The framework utilizes large-scale unlabeled video data to reduce the gap between different domains while transferring discriminative …
