The increased use of convolutional neural networks for face recognition in science, governance, and broader society has created an acute need for methods that can show how these 'black box' decisions are made. To be interpretable and useful to humans, such a method should convey a model's learned classification strategy in a way that is robust to random initializations or spurious correlations in input data. To this end, we applied the decompositional pixel-wise attribution method of layer-wise relevance propagation (LRP) to resolve the decisions of several classes of VGG-16 models trained for face recognition. We then quantified how these relevance measures vary with and generalize across key model parameters, such as the pretraining dataset (ImageNet or VGGFace), the finetuning task (gender or identity classification), and random initializations of model weights. Using relevance-based image masking, we find that relevance maps for face classification prove generally stable across random initializations, and can generalize across finetuning tasks. However, there is markedly less generalization across pretraining datasets, indicating that ImageNet- and VGGFace-trained models sample face information differently even as they achieve comparably high classification performance. Fine-grained analyses of relevance maps across models revealed asymmetries in generalization that point to specific benefits of choice parameters, and suggest that it may be possible to find an underlying set of important face image pixels that drive decisions across convolutional neural networks and tasks. Finally, we evaluated model decision weighting against human measures of similarity, providing a novel framework for interpreting face recognition decisions across human and machine.
Center for Machine Vision and Signal Analysis, University of Oulu（奥卢大学机器视觉与信号分析中心）；Xi’an Jiaotong University（西安交通大学）；Northwestern Polytechnical University（西北工业大学）
Face anti-spoofing (FAS) plays a vital role in securing face recognition systems from the presentation attacks (PAs). As more and more realistic PAs with novel types spring up, it is necessary to develop robust algorithms for detecting unknown attacks even in unseen scenarios. However, deep models supervised by traditional binary loss (e.g., `0' for bonafide vs. `1' for PAs) are weak in describing intrinsic and discriminative spoofing patterns. Recently, pixel-wise supervision has been proposed for the FAS task, intending to provide more fine-grained pixel/patch-level cues. In this paper, we f…
Face recognition has evolved as a prominent biometric authentication modality. However, vulnerability to presentation attacks curtails its reliable deployment. Automatic detection of presentation attacks is essential for secure use of face recognition technology in unattended scenarios. In this work, we introduce a Convolutional Neural Network (CNN) based framework for presentation attack detection, with deep pixel-wise supervision. The framework uses only frame level information making it suitable for deployment in smart devices with minimal computational and time overhead. We demonstrate the…
Hyperspectral image (HSI) classification is the most vibrant area of research in the hyperspectral community due to the rich spectral information contained in HSI can greatly aid in identifying objects of interest. However, inherent non-linearity between materials and the corresponding spectral profiles brings two major challenges in HSI classification: interclass similarity and intraclass variability. Many advanced deep learning methods have attempted to address these issues from the perspective of a region/patch-based approach, instead of a pixel-based alternate. However, the patch-based app…
University of Ljubljana（卢布尔雅那大学）；KTH Royal Institute of Technology（瑞典皇家理工学院）
Object detection and segmentation represents the basis for many tasks in computer and machine vision. In biometric recognition systems the detection of the region-of-interest (ROI) is one of the most crucial steps in the overall processing pipeline, significantly impacting the performance of the entire recognition system. Existing approaches to ear detection, for example, are commonly susceptible to the presence of severe occlusions, ear accessories or variable illumination conditions and often deteriorate in their performance if applied on ear images captured in unconstrained settings. To add…
Southern University of Science and Technology（南方科技大学）；Shanghai Jiao Tong University（上海交通大学）
This paper presents a method to explain how the information of each input variable is gradually discarded during the forward propagation in a deep neural network (DNN), which provides new perspectives to explain DNNs. We define two types of entropy-based metrics, i.e. (1) the discarding of pixel-wise information used in the forward propagation, and (2) the uncertainty of the input reconstruction, to measure input information contained by a specific layer from two perspectives. Unlike previous attribution metrics, the proposed metrics ensure the fairness of comparisons between different layers …
Variational autoencoders (VAEs), that are built upon deep neural networks have emerged as popular generative models in computer vision. Most of the work towards improving variational autoencoders has focused mainly on making the approximations to the posterior flexible and accurate, leading to tremendous progress. However, there have been limited efforts to replace pixel-wise reconstruction, which have known shortcomings. In this work, we use real-valued non-volume preserving transformations (real NVP) to exactly compute the conditional likelihood of the data given the latent distribution. We …
Tel Aviv University（特拉维夫大学）；Sheba Medical Center（示巴医疗中心）；Bar-Ilan University（巴伊兰大学）
In this work we propose a method for anatomical data augmentation that is based on using slices of computed tomography (CT) examinations that are adjacent to labeled slices as another resource of labeled data for training the network. The extended labeled data is used to train a U-net network for a pixel-wise classification into different hepatic lesions and normal liver tissues. Our dataset contains CT examinations from 140 patients with 333 CT images annotated by an expert radiologist. We tested our approach and compared it to the conventional training process. Results indicate superiority o…
The Chinese University of Hong Kong（香港中文大学）；MEGVII Technology（旷视科技）；SmartMore（思谋科技）
Multi-object tracking (MOT) requires detecting and associating objects through frames. Unlike tracking via detected bounding boxes or tracking objects as points, we propose tracking objects as pixel-wise distributions. We instantiate this idea on a transformer-based architecture, P3AFormer, with pixel-wise propagation, prediction, and association. P3AFormer propagates pixel-wise features guided by flow information to pass messages between frames. Furthermore, P3AFormer adopts a meta-architecture to produce multi-scale object feature maps. During inference, a pixel-wise association procedure is…
Indian Institute of Technology Kanpur（印度理工学院坎普尔分校）
In this paper, we tackle the problem of explanations in a deep-learning based model for recommendations by leveraging the technique of layer-wise relevance propagation. We use a Deep Convolutional Neural Network to extract relevant features from the input images before identifying similarity between the images in feature space. Relationships between the images are identified by the model and layer-wise relevance propagation is used to infer pixel-level details of the images that may have significantly informed the model's choice. We evaluate our method on an Amazon products dataset and demonst…
University of Science and Technology of China（中国科学技术大学）
Contrastive learning (CL) is a form of self-supervised learning and has been widely used for various tasks. Different from widely studied instance-level contrastive learning, pixel-wise contrastive learning mainly helps with pixel-wise tasks such as medical landmark detection. The counterpart to an instance in instance-level CL is a pixel, along with its neighboring context, in pixel-wise CL. Aiming to build better feature representation, there is a vast literature about designing instance augmentation strategies for instance-level CL; but there is little similar work on pixel augmentation for…
City University of Hong Kong（香港城市大学）；SenseTime Research（商汤科技研究院）
We investigate the generalization of semi-supervised learning (SSL) to diverse pixel-wise tasks. Although SSL methods have achieved impressive results in image classification, the performances of applying them to pixel-wise tasks are unsatisfactory due to their need for dense outputs. In addition, existing pixel-wise SSL approaches are only suitable for certain tasks as they usually require to use task-specific properties. In this paper, we present a new SSL framework, named Guided Collaborative Training (GCT), for pixel-wise tasks, with two main technical contributions. First, GCT addresses t…
We address the problem of contour detection via per-pixel classifications of edge point. To facilitate the process, the proposed approach leverages with DenseNet, an efficient implementation of multiscale convolutional neural networks (CNNs), to extract an informative feature vector for each pixel and uses an SVM classifier to accomplish contour detection. In the experiment of contour detection, we look into the effectiveness of combining per-pixel features from different CNN layers and verify their performance on BSDS500.
Convolutional Neural Networks (CNN) have become state-of-the-art in the field of image classification. However, not everything is understood about their inner representations. This paper tackles the interpretability and explainability of the predictions of CNNs for multi-class classification problems. Specifically, we propose a novel visualization method of pixel-wise input attribution called Softmax-Gradient Layer-wise Relevance Propagation (SGLRP). The proposed model is a class discriminate extension to Deep Taylor Decomposition (DTD) using the gradient of softmax to back propagate the relev…
BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference
Qing Yuan Research Institute（清源研究院）；SEIEE, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）；School of Computer Science, Fudan University（复旦大学计算机科学技术学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）
This paper contributes to automating medical image segmentation by proposing generative adversarial network-based models to segment both polyps and instruments in endoscopy images. A major contribution of this work is to provide explanations for the predictions using a layer-wise relevance propagation approach designating which input image pixels are relevant to the predictions and to what extent. On the polyp segmentation task, the models achieved 0.84 of accuracy and 0.46 on Jaccard index. On the instrument segmentation task, the models achieved 0.96 of accuracy and 0.70 on Jaccard index. Th…
Singapore University of Technology and Design（新加坡科技设计大学）；Technische Universität Berlin（柏林工业大学）；Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；Korea University（高丽大学）
Layer-wise relevance propagation is a framework which allows to decompose the prediction of a deep neural network computed over a sample, e.g. an image, down to relevance scores for the single input dimensions of the sample such as subpixels of an image. While this approach can be applied directly to generalized linear mappings, product type non-linearities are not covered. This paper proposes an approach to extend layer-wise relevance propagation to neural networks with local renormalization layers, which is a very common product-type non-linearity in convolutional neural networks. We evaluat…
Pixel-wise street segmentation of photographs taken from a drivers perspective is important for self-driving cars and can also support other object recognition tasks. A framework called SST was developed to examine the accuracy and execution time of different neural networks. The best neural network achieved an $F_1$-score of 89.5% with a simple feedforward neural network which trained to solve a regression task.
Korea University（高丽大学）；Chungbuk National University Hospital（忠北国立大学医院）；Hannam University（韩南大学）
Region-adaptive normalization (RAN) methods have been widely used in the generative adversarial network (GAN)-based image-to-image translation technique. However, since these approaches need a mask image to infer the pixel-wise affine transformation parameters, they cannot be applied to the general image generation models having no paired mask images. To resolve this problem, this paper presents a novel normalization method, called self pixel-wise normalization (SPN), which effectively boosts the generative performance by performing the pixel-adaptive affine transformation without the mask ima…
Generative Adversarial Networks (GANs) have proven successful for unsupervised image generation. Several works extended GANs to image inpainting by conditioning the generation with parts of the image one wants to reconstruct. However, these methods have limitations in settings where only a small subset of the image pixels is known beforehand. In this paper, we study the effectiveness of conditioning GANs by adding an explicit regularization term to enforce pixel-wise conditions when very few pixel values are provided. In addition, we also investigate the influence of this regularization term o…
Army Research Laboratory（美国陆军研究实验室）；Pusan National University（釜山国立大学）
Pixel-wise classification in remote sensing identifies entities in large-scale satellite-based images at the pixel level. Few fully annotated large-scale datasets for pixel-wise classification exist due to the challenges of annotating individual pixels. Training data scarcity inevitably ensues from the annotation challenge, leading to overfitting classifiers and degraded classification performance. The lack of annotated pixels also necessarily results in few hard examples of various entities critical for generating a robust classification hyperplane. To overcome the problem of the data scarcit…
Technical University of Denmark（丹麦技术大学）；University of Copenhagen（哥本哈根大学）；Twitter
We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the GAN discriminator as basis for the VAE reconstruction objective. Thereby, we replace element-wise errors with feature-wise errors to better capture the data distribution while offering invariance towards e.g. translation. We apply our method to images of faces and show that it outperforms VAEs with element-wise similarity measures in terms of visual fidelity. …
Australian Institute for Machine Learning（澳大利亚机器学习研究所）；University of Adelaide（阿德莱德大学）；Singapore Management University（新加坡管理大学）
State-of-the-art (SOTA) anomaly segmentation approaches on complex urban driving scenes explore pixel-wise classification uncertainty learned from outlier exposure, or external reconstruction models. However, previous uncertainty approaches that directly associate high uncertainty to anomaly may sometimes lead to incorrect anomaly predictions, and external reconstruction models tend to be too inefficient for real-time self-driving embedded systems. In this paper, we propose a new anomaly segmentation method, named pixel-wise energy-biased abstention learning (PEBAL), that explores pixel-wise a…
The real human attention is an interactive activity between our visual system and our brain, using both low-level visual stimulus and high-level semantic information. Previous image salient object detection (SOD) works conduct their saliency predictions in a multi-task manner, i.e., performing pixel-wise saliency regression and segmentation-like saliency refinement at the same time, which degenerates their feature backbones in revealing semantic information. However, given an image, we tend to pay more attention to those regions which are semantically salient even in the case that these region…
K.J. Somaiya College of Engineering（K.J. 索马亚工程学院）；University of Mumbai（孟买大学）
This paper presents a novel technique for skin colour segmentation that overcomes the limitations faced by existing techniques such as Colour Range Thresholding. Skin colour segmentation is affected by the varied skin colours and surrounding lighting conditions, leading to poorskin segmentation for many techniques. We propose a new two stage Pixel Neighbourhood technique that classifies any pixel as skin or non-skin based on its neighbourhood pixels. The first step calculates the probability of each pixel being skin by passing HSV values of the pixel to a Deep Neural Network model. In the next…
State Key Lab. LIESMARS, Wuhan University（武汉大学测绘遥感信息工程国家重点实验室）；School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）
Given an aerial image, aerial scene parsing (ASP) targets to interpret the semantic structure of the image content, e.g., by assigning a semantic label to every pixel of the image. With the popularization of data-driven methods, the past decades have witnessed promising progress on ASP by approaching the problem with the schemes of tile-level scene classification or segmentation-based image analysis, when using high-resolution aerial images. However, the former scheme often produces results with tile-wise boundaries, while the latter one needs to handle the complex modeling process from pixels…
Among the neural network compression techniques, knowledge distillation is an effective one which forces a simpler student network to mimic the output of a larger teacher network. However, most of such model distillation methods focus on the image-level classification task. Directly adapting these methods to the task of semantic segmentation only brings marginal improvements. In this paper, we propose a simple, yet effective knowledge representation referred to as pixel-wise feature similarities (PFS) to tackle the challenging distillation problem of semantic segmentation. The developed PFS en…
This paper introduces pixel-wise prediction based visual odometry (PWVO), which is a dense prediction task that evaluates the values of translation and rotation for every pixel in its input observations. PWVO employs uncertainty estimation to identify the noisy regions in the input observations, and adopts a selection mechanism to integrate pixel-wise predictions based on the estimated uncertainty maps to derive the final translation and rotation. In order to train PWVO in a comprehensive fashion, we further develop a data generation workflow for generating synthetic training data. The experim…
In this paper, we propose a novel pixel-wise visual object tracking framework that can track any anonymous object in a noisy background. The framework consists of two submodels, a global attention model and a local segmentation model. The global model generates a region of interests (ROI) that the object may lie in the new frame based on the past object segmentation maps, while the local model segments the new image in the ROI. Each model uses a LSTM structure to model the temporal dynamics of the motion and appearance, respectively. To circumvent the dependency of the training data between th…
Department of Electrical Engineering, City Univeristy of Hong Kong, Hong Kong
Noisy labels collected with limited annotation cost prevent medical image segmentation algorithms from learning precise semantic correlations. Previous segmentation arts of learning with noisy labels merely perform a pixel-wise manner to preserve semantics, such as pixel-wise label correction, but neglect the pair-wise manner. In fact, we observe that the pair-wise manner capturing affinity relations between pixels can greatly reduce the label noise rate. Motivated by this observation, we present a novel perspective for noisy mitigation by incorporating both pixel-wise and pair-wise manners, w…
KTH Royal Institute of Technology（瑞典皇家理工学院）；Univrses AB（Univrses公司）
We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via strong data augmentation. We enable the application of FixMatch in semi-supervised learning problems beyond image classification by adding a matching operation on the pseudo-labels. This allows us to still use the full strength of data augmentation pipelines, including geometric transformations. We evaluate it on semi-supervised semantic segmentation on Cityscapes and Pascal VOC with different percentages of labeled…
In this paper, a learning-free color constancy algorithm called the Patch-wise Bright Pixels (PBP) is proposed. In this algorithm, an input image is first downsampled and then cut equally into a few patches. After that, according to the modified brightness of each patch, a proper fraction of brightest pixels in the patch is selected. Finally, Gray World (GW)-based methods are applied to the selected bright pixels to estimate the illuminant of the scene. Experiments on NUS $8$-Camera Dataset show that the PBP algorithm outperforms the state-of-the-art learning-free methods as well as a broad ra…
Generative Adversarial Networks (GANs) have proven successful for unsupervised image generation. Several works have extended GANs to image inpainting by conditioning the generation with parts of the image to be reconstructed. Despite their success, these methods have limitations in settings where only a small subset of the image pixels is known beforehand. In this paper we investigate the effectiveness of conditioning GANs when very few pixel values are provided. We propose a modelling framework which results in adding an explicit cost term to the GAN objective function to enforce pixel-wise c…
To achieve parsimonious inference in per-pixel labeling tasks with a limited computational budget, we propose a \emph{Pixel-wise Attentional Gating} unit (\emph{PAG}) that learns to selectively process a subset of spatial locations at each layer of a deep convolutional network. PAG is a generic, architecture-independent, problem-agnostic mechanism that can be readily "plugged in" to an existing model with fine-tuning. We utilize PAG in two ways: 1) learning spatially varying pooling fields that improve model performance without the extra computation cost associated with multi-scale pooling, an…
Conditional Generative Adversarial Nets (CGANs) need a significantly huge dataset with a detailed pixel-wise annotation to generate high-quality images. Unfortunately, any amount of missing pixel annotations may significantly impact the result not only locally, but also in annotated areas. To the best of our knowledge, such a challenge has never been investigated in the broader field of GANs. In this paper, we take the first step in this direction to study the problem of CGAN-based satellite image synthesis given partially annotated images. We first define the problem of image synthesis using …
Pixel-Wise Symbol Spotting via Progressive Points Location for Parsing CAD Images
Faculty of Information Technology, Beijing University of Technology（北京工业大学信息技术学院）；Software Development Center, China Information Technology Designing and Consulting Institute Co., Ltd（中国电子工程设计院有限公司软件开发中心）
University of Technology Sydney（悉尼科技大学）；National University of Singapore（新加坡国立大学）；Zhejiang University（浙江大学）
Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned model to other domains. The domain-invariant knowledge is transferred from the model trained on labeled source domain, e.g., video game, to unlabeled target domains, e.g., real-world scenarios, saving annotation expenses. Existing UDA methods for semantic segmentation usually focus on minimizing the inter-domain discrepancy of various levels, e.g., pixels, features, and predictions, for extracting domain-invariant knowledge. However, the primary intra-domain knowledge, such as context correlation inside an i…
Zero-shot learning has been actively studied for image classification task to relieve the burden of annotating image labels. Interestingly, semantic segmentation task requires more labor-intensive pixel-wise annotation, but zero-shot semantic segmentation has only attracted limited research interest. Thus, we focus on zero-shot semantic segmentation, which aims to segment unseen objects with only category-level semantic representations provided for unseen categories. In this paper, we propose a novel Context-aware feature Generation Network (CaGNet), which can synthesize context-aware pixel-wi…
Image stitching aims at stitching the images taken from different viewpoints into an image with a wider field of view. Existing methods warp the target image to the reference image using the estimated warp function, and a homography is one of the most commonly used warping functions. However, when images have large parallax due to non-planar scenes and translational motion of a camera, the homography cannot fully describe the mapping between two images. Existing approaches based on global or local homography estimation are not free from this problem and suffer from undesired artifacts due to p…
Fraunhofer ITWM（弗劳恩霍夫工业数学研究所）；IWR, University of Heidelberg（海德堡大学交互计算与可视化研究所）；Fraunhofer Center Machine Learning（弗劳恩霍夫机器学习中心）；Visual Learning Lab Heidelberg（海德堡视觉学习实验室）；Institute for Machine Learning and Analytics, Offenburg University（奥芬堡大学机器学习与分析研究所）
Recent deep learning based approaches have shown remarkable success on object segmentation tasks. However, there is still room for further improvement. Inspired by generative adversarial networks, we present a generic end-to-end adversarial approach, which can be combined with a wide range of existing semantic segmentation networks to improve their segmentation performance. The key element of our method is to replace the commonly used binary adversarial loss with a high resolution pixel-wise loss. In addition, we train our generator employing stochastic weight averaging fashion, which further …
Zhejiang University（浙江大学）；University of Science and Technology of China（中国科学技术大学）
Single-photon light detection and ranging (LiDAR) has been widely applied to 3D imaging in challenging scenarios. However, limited signal photon counts and high noises in the collected data have posed great challenges for predicting the depth image precisely. In this paper, we propose a pixel-wise residual shrinkage network for photon-efficient imaging from high-noise data, which adaptively generates the optimal thresholds for each pixel and denoises the intermediate features by soft thresholding. Besides, redefining the optimization target as pixel-wise classification provides a sharp advanta…
Computer Vision Laboratory, École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院计算机视觉实验室）；ARTORG Center for Biomedical Engineering Research, University of Bern（伯尔尼大学ARTORG生物医学工程研究中心）
Delineation of curvilinear structures is an important problem in Computer Vision with multiple practical applications. With the advent of Deep Learning, many current approaches on automatic delineation have focused on finding more powerful deep architectures, but have continued using the habitual pixel-wise losses such as binary cross-entropy. In this paper we claim that pixel-wise losses alone are unsuitable for this problem because of their inability to reflect the topological impact of mistakes in the final prediction. We propose a new loss term that is aware of the higher-order topological…
To accelerate deep CNN models, this paper proposes a novel spatially adaptive framework that can dynamically generate pixel-wise sparsity according to the input image. The sparse scheme is pixel-wise refined, regional adaptive under a unified importance map, which makes it friendly to hardware implementation. A sparse controlling method is further presented to enable online adjustment for applications with different precision/latency requirements. The sparse model is applicable to a wide range of vision tasks. Experimental results show that this method efficiently improve the computing efficie…
Observing retinal fundus images by an ophthalmologist is a major diagnosis approach for glaucoma. However, it is still difficult to distinguish the features of the lesion solely through manual observations, especially, in glaucoma early phase. In this paper, we present two deep learning-based automated algorithms for glaucoma detection and optic disc and cup segmentation. We utilize the attention mechanism to learn pixel-wise features for accurate prediction. In particular, we present two convolutional neural networks that can focus on learning various pixel-wise level features. In addition, w…
Learning Pixel-wise Continuous Depth Representation via Clustering for Depth Completion
Dalian University of Technology（大连理工大学）；College of Computer Science and Engineering, Shandong University of Science and Technology（山东科技大学计算机科学与工程学院）；Shanghai Artificial Intelligence Laboratory / Shanghai AI Lab（上海人工智能实验室）
Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形学研究所）；TU Darmstadt（达姆施塔特工业大学）
Iris presentation attack detection (PAD) plays a vital role in iris recognition systems. Most existing CNN-based iris PAD solutions 1) perform only binary label supervision during the training of CNNs, serving global information learning but weakening the capture of local discriminative features, 2) prefer the stacked deeper convolutions or expert-designed networks, raising the risk of overfitting, 3) fuse multiple PAD systems or various types of features, increasing difficulty for deployment on mobile devices. Hence, we propose a novel attention-based deep pixel-wise binary supervision (A-PBS…
Estimating the 6D pose of objects using only RGB images remains challenging because of problems such as occlusion and symmetries. It is also difficult to construct 3D models with precise texture without expert knowledge or specialized scanning devices. To address these problems, we propose a novel pose estimation method, Pix2Pose, that predicts the 3D coordinates of each object pixel without textured models. An auto-encoder architecture is designed to estimate the 3D coordinates and expected errors per pixel. These pixel-wise predictions are then used in multiple stages to form 2D-3D correspon…
