Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic image features. However, in order to successfully learn those features, they usually require massive amounts of manually labeled data, which is both expensive and impractical to scale. Therefore, unsupervised semantic feature learning, i.e., learning without requiring manual annotation effort, is of crucial importance in order to successfully harvest the vast amount of visual data that are available today. In our work we propose to learn image features by training ConvNets to recognize the 2d rotation that is applied to the image that it gets as input. We demonstrate both qualitatively and quantitatively that this apparently simple task actually provides a very powerful supervisory signal for semantic feature learning. We exhaustively evaluate our method in various unsupervised feature learning benchmarks and we exhibit in all of them state-of-the-art performance. Specifically, our results on those benchmarks demonstrate dramatic improvements w.r.t. prior state-of-the-art approaches in unsupervised representation learning and thus significantly close the gap with supervised feature learning. For instance, in PASCAL VOC 2007 detection task our unsupervised pre-trained AlexNet model achieves the state-of-the-art (among unsupervised methods) mAP of 54.4% that is only 2.4 points lower from the supervised case. We get similarly striking results when we transfer our unsupervised learned features on various other tasks, such as ImageNet classification, PASCAL classification, PASCAL segmentation, and CIFAR-10 classification. The code and models of our paper will be published on: https://github.com/gidariss/FeatureLearningRotNet .
Detecting transparent objects in natural scenes is challenging due to the low contrast in texture, brightness and colors. Recent deep-learning-based works reveal that it is effective to leverage boundaries for transparent object detection (TOD). However, these methods usually encounter boundary-related imbalance problem, leading to limited generation capability. Detailly, a kind of boundaries in the background, which share the same characteristics with boundaries of transparent objects but have much smaller amounts, usually hurt the performance. To conquer the boundary-related imbalance problem, we propose a novel content-dependent data augmentation method termed FakeMix. Considering collecting these trouble-maker boundaries in the background is hard without corresponding annotations, we elaborately generate them by appending the boundaries of transparent objects from other samples into the current image during training, which adjusts the data space and improves the generalization of the models. Further, we present AdaptiveASPP, an enhanced version of ASPP, that can capture multi-scale and cross-modality features dynamically. Extensive experiments demonstrate that our methods clearly outperform the state-of-the-art methods. We also show that our approach can also transfer well on related tasks, in which the model meets similar troubles, such as mirror detection, glass detection, and camouflaged object detection. Code will be made publicly available.
Existing semantic segmentation works mainly focus on learning the contextual information in high-level semantic features with CNNs. In order to maintain a precise boundary, low-level texture features are directly skip-connected into the deeper layers. Nevertheless, texture features are not only about local structure, but also include global statistical knowledge of the input image. In this paper, we fully take advantages of the low-level texture features and propose a novel Statistical Texture Learning Network (STLNet) for semantic segmentation. For the first time, STLNet analyzes the distribution of low level information and efficiently utilizes them for the task. Specifically, a novel Quantization and Counting Operator (QCO) is designed to describe the texture information in a statistical manner. Based on QCO, two modules are introduced: (1) Texture Enhance Module (TEM), to capture texture-related information and enhance the texture details; (2) Pyramid Texture Feature Extraction Module (PTFEM), to effectively extract the statistical texture features from multiple scales. Through extensive experiments, we show that the proposed STLNet achieves state-of-the-art performance on three semantic segmentation benchmarks: Cityscapes, PASCAL Context and ADE20K.
Differentiable rendering has paved the way to training neural networks to perform "inverse graphics" tasks such as predicting 3D geometry from monocular photographs. To train high performing models, most of the current approaches rely on multi-view imagery which are not readily available in practice. Recent Generative Adversarial Networks (GANs) that synthesize images, in contrast, seem to acquire 3D knowledge implicitly during training: object viewpoints can be manipulated by simply manipulating the latent codes. However, these latent codes often lack further physical interpretation and thus GANs cannot easily be inverted to perform explicit 3D reasoning. In this paper, we aim to extract and disentangle 3D knowledge learned by generative models by utilizing differentiable renderers. Key to our approach is to exploit GANs as a multi-view data generator to train an inverse graphics network using an off-the-shelf differentiable renderer, and the trained inverse graphics network as a teacher to disentangle the GAN's latent code into interpretable 3D properties. The entire architecture is trained iteratively using cycle consistency losses. We show that our approach significantly outperforms state-of-the-art inverse graphics networks trained on existing datasets, both quantitatively and via user studies. We further showcase the disentangled GAN as a controllable 3D "neural renderer", complementing traditional graphics renderers.
Fingerprint capture systems can be fooled by widely accessible methods to spoof the system using fake fingers, known as presentation attacks. As biometric recognition systems become more extensively relied upon at international borders and in consumer electronics, presentation attacks are becoming an increasingly serious issue. A robust solution is needed that can handle the increased variability and complexity of spoofing techniques. This paper demonstrates the viability of utilizing a sensor with time-series and color-sensing capabilities to improve the robustness of a traditional fingerprint sensor and introduces a comprehensive fingerprint dataset with over 36,000 image sequences and a state-of-the-art set of spoofing techniques. The specific sensor used in this research captures a traditional gray-scale static capture and a time-series color capture simultaneously. Two different methods for Presentation Attack Detection (PAD) are used to assess the benefit of a color dynamic capture. The first algorithm utilizes Static-Temporal Feature Engineering on the fingerprint capture to generate a classification decision. The second generates its classification decision using features extracted by way of the Inception V3 CNN trained on ImageNet. Classification performance is evaluated using features extracted exclusively from the static capture, exclusively from the dynamic capture, and on a fusion of the two feature sets. With both PAD approaches we find that the fusion of the dynamic and static feature-set is shown to improve performance to a level not individually achievable.
Existing works on single-image 3D reconstruction mainly focus on shape recovery. In this work, we study a new problem, that is, simultaneously recovering 3D shape and surface color from a single image, namely "colorful 3D reconstruction". This problem is both challenging and intriguing because the ability to infer textured 3D model from a single image is at the core of visual understanding. Here, we propose an end-to-end trainable framework, Colorful Voxel Network (CVN), to tackle this problem. Conditioned on a single 2D input, CVN learns to decompose shape and surface color information of a 3D object into a 3D shape branch and a surface color branch, respectively. Specifically, for the shape recovery, we generate a shape volume with the state of its voxels indicating occupancy. For the surface color recovery, we combine the strength of appearance hallucination and geometric projection by concurrently learning a regressed color volume and a 2D-to-3D flow volume, which are then fused into a blended color volume. The final textured 3D model is obtained by sampling color from the blended color volume at the positions of occupied voxels in the shape volume. To handle the severe sparse volume representations, a novel loss function, Mean Squared False Cross-Entropy Loss (MSFCEL), is designed. Extensive experiments demonstrate that our approach achieves significant improvement over baselines, and shows great generalization across diverse object categories and arbitrary viewpoints.
This paper concerns the use of objectness measures to improve the calibration performance of Convolutional Neural Networks (CNNs). Objectness is a measure of likelihood of an object from any class being present in a given image. CNNs have proven to be very good classifiers and generally localize objects well; however, the loss functions typically used to train classification CNNs do not penalize inability to localize an object, nor do they take into account an object's relative size in the given image. We present a novel approach to object localization that combines the ideas of objectness and label smoothing during training. Unlike previous methods, we compute a smoothing factor that is adaptive based on relative object size within an image. We present extensive results using ImageNet and OpenImages to demonstrate that CNNs trained using adaptive label smoothing are much less likely to be overconfident in their predictions, as compared to CNNs trained using hard targets. We also show qualitative results using class activation maps to illustrate the improvements.
Age is an essential factor in modern diagnostic procedures. However, assessment of the true biological age (BA) remains a daunting task due to the lack of reference ground-truth labels. Current BA estimation approaches are either restricted to skeletal images or rely on non-imaging modalities that yield a whole-body BA assessment. However, various organ systems may exhibit different aging characteristics due to lifestyle and genetic factors. In this initial study, we propose a new framework for organ-specific BA estimation utilizing 3D magnetic resonance image (MRI) scans. As a first step, this framework predicts the chronological age (CA) together with the corresponding patient-dependent aleatoric uncertainty. An iterative training algorithm is then utilized to segregate atypical aging patients from the given population based on the predicted uncertainty scores. In this manner, we hypothesize that training a new model on the remaining population should approximate the true BA behavior. We apply the proposed methodology on a brain MRI dataset containing healthy individuals as well as Alzheimer's patients. We demonstrate the correlation between the predicted BAs and the expected cognitive deterioration in Alzheimer's patients.
In this paper, we address the problem of predicting the future motion of a dynamic agent (called a target agent) given its current and past states as well as the information on its environment. It is paramount to develop a prediction model that can exploit the contextual information in both static and dynamic environments surrounding the target agent and generate diverse trajectory samples that are meaningful in a traffic context. We propose a novel prediction model, referred to as the lane-aware prediction (LaPred) network, which uses the instance-level lane entities extracted from a semantic map to predict the multi-modal future trajectories. For each lane candidate found in the neighborhood of the target agent, LaPred extracts the joint features relating the lane and the trajectories of the neighboring agents. Then, the features for all lane candidates are fused with the attention weights learned through a self-supervised learning task that identifies the lane candidate likely to be followed by the target agent. Using the instance-level lane information, LaPred can produce the trajectories compliant with the surroundings better than 2D raster image-based methods and generate the diverse future trajectories given multiple lane candidates. The experiments conducted on the public nuScenes dataset and Argoverse dataset demonstrate that the proposed LaPred method significantly outperforms the existing prediction models, achieving state-of-the-art performance in the benchmarks.
Meta-learning models transfer the knowledge acquired from previous tasks to quickly learn new ones. They are tested on benchmarks with a fixed number of data points per training task. This number is usually arbitrary and it is unknown how it affects the performance. Since labelling of data is expensive, finding the optimal allocation of labels across training tasks may reduce costs: given a fixed budget of labels, should we use a small number of highly labelled tasks, or many tasks with few labels each? We show that: 1) The optimal number of data points per task depends on the budget, but it converges to a unique constant value for large budgets; 2) Convergence occurs around the interpolation threshold of the model. We prove our results mathematically on mixed linear regression, and we show empirically that the same results hold for nonlinear regression and few-shot image classification on CIFAR-FS and mini-ImageNet. Our results suggest a simple and efficient procedure for data collection: the optimal allocation of data can be computed at low cost, by using relatively small data, and collection of additional data can be optimized by the knowledge of the optimal allocation.