Among the wide variety of image generative models, two models stand out: Variational Auto Encoders (VAE) and Generative Adversarial Networks (GAN). GANs can produce realistic images, but they suffer from mode collapse and do not provide simple ways to get the latent representation of an image. On the other hand, VAEs do not have these problems, but they often generate images less realistic than GANs. In this article, we explain that this lack of realism is partially due to a common underestimation of the natural image manifold dimensionality. To solve this issue we introduce a new framework that combines VAE and GAN in a novel and complementary way to produce an auto-encoding model that keeps VAEs properties while generating images of GAN-quality. We evaluate our approach both qualitatively and quantitatively on five image datasets.
Deep Neural Networks (DNNs) have become the de-facto standard in computer vision, as well as in many other pattern recognition tasks. A key drawback of DNNs is that the training phase can be very computationally expensive. Organizations or individuals that cannot afford purchasing state-of-the-art hardware or tapping into cloud-hosted infrastructures may face a long waiting time before the training completes or might not be able to train a model at all. Investigating novel ways to reduce the training time could be a potential solution to alleviate this drawback, and thus enabling more rapid development of new algorithms and models. In this paper, we propose LightLayers, a method for reducing the number of trainable parameters in deep neural networks (DNN). The proposed LightLayers consists of LightDense andLightConv2D layer that are as efficient as regular Conv2D and Dense layers, but uses less parameters. We resort to Matrix Factorization to reduce the complexity of the DNN models resulting into lightweight DNNmodels that require less computational power, without much loss in the accuracy. We have tested LightLayers on MNIST, Fashion MNIST, CI-FAR 10, and CIFAR 100 datasets. Promising results are obtained for MNIST, Fashion MNIST, CIFAR-10 datasets whereas CIFAR 100 shows acceptable performance by using fewer parameters.
Privacy protection on human biological information has drawn increasing attention in recent years, among which face anonymization plays an importance role. We propose a novel approach which protects identity information of facial images from leakage with slightest modification. Specifically, we disentangle identity representation from other facial attributes leveraging the power of generative adversarial networks trained on a conditional multi-scale reconstruction (CMR) loss and an identity loss. We evaulate the disentangle ability of our model, and propose an effective method for identity anonymization, namely Anonymous Identity Generation (AIG), to reach the goal of face anonymization meanwhile maintaining similarity to the original image as much as possible. Quantitative and qualitative results demonstrate our method's superiority compared with the SOTAs on both visual quality and anonymization success rate.
The analysis of lesion within medical image data is desirable for efficient disease diagnosis, treatment and prognosis. The common lesion analysis tasks like segmentation and classification 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. Inspired by the fact that radiologists make diagnoses based on expert knowledge on "healthiness" and "unhealthiness" developed from extensive experience, we propose an medical image synthesis model named abnormal-to-normal translation generative adversarial network (ANT-GAN) to predict a normal-looking medical image based on its abnormal-looking counterpart without the need of paired data for training. Unlike typical GANs, whose aim is to generate realistic samples with variations, our more restrictive model aims at producing the underlying normal-looking image corresponding to an image containing lesions, and thus requires a specialized design. With an ability to segment normal from abnormal tissue, our model is able to generate a highly realistic lesion-free medical image based on its true lesion-containing counterpart. Being able to provide a "normal" version of a medical image (possibly the same image if there is no illness) is not only an intriguing topic, but also can serve as a pre-processing and provide useful side information for medical imaging tasks like lesion segmentation or classification validated by our experiments.
While working with fingerprint images acquired from crime scenes, mobile cameras, or low-quality sensors, it becomes difficult for automated identification systems to verify the identity due to image blur and distortion. We propose a fingerprint deblurring model FDeblur-GAN, based on the conditional Generative Adversarial Networks (cGANs) and multi-stage framework of the stack GAN. Additionally, we integrate two auxiliary sub-networks into the model for the deblurring task. The first sub-network is a ridge extractor model. It is added to generate ridge maps to ensure that fingerprint information and minutiae are preserved in the deblurring process and prevent the model from generating erroneous minutiae. The second sub-network is a verifier that helps the generator to preserve the ID information during the generation process. Using a database of blurred fingerprints and corresponding ridge maps, the deep network learns to deblur from the input blurry samples. We evaluate the proposed method in combination with two different fingerprint matching algorithms. We achieved an accuracy of 95.18% on our fingerprint database for the task of matching deblurred and ground truth fingerprints.
Automated defect inspection is critical for effective and efficient maintenance, repair, and operations in advanced manufacturing. On the other hand, automated defect inspection is often constrained by the lack of defect samples, especially when we adopt deep neural networks for this task. This paper presents Defect-GAN, an automated defect synthesis network that generates realistic and diverse defect samples for training accurate and robust defect inspection networks. Defect-GAN learns through defacement and restoration processes, where the defacement generates defects on normal surface images while the restoration removes defects to generate normal images. It employs a novel compositional layer-based architecture for generating realistic defects within various image backgrounds with different textures and appearances. It can also mimic the stochastic variations of defects and offer flexible control over the locations and categories of the generated defects within the image background. Extensive experiments show that Defect-GAN is capable of synthesizing various defects with superior diversity and fidelity. In addition, the synthesized defect samples demonstrate their effectiveness in training better defect inspection networks.
Localizing and counting large ungulates -- hoofed mammals like cows and elk -- in very high-resolution satellite imagery is an important task for supporting ecological studies. Prior work has shown that this is feasible with deep learning based methods and sub-meter multi-spectral satellite imagery. We extend this line of work by proposing a baseline method, CowNet, that simultaneously estimates the number of animals in an image (counts), as well as predicts their location at a pixel level (localizes). We also propose an methodology for evaluating such models on counting and localization tasks across large scenes that takes the uncertainty of noisy labels and the information needed by stakeholders in ecological monitoring tasks into account. Finally, we benchmark our baseline method with state of the art vision methods for counting objects in scenes. We specifically test the temporal generalization of the resulting models over a large landscape in Point Reyes Seashore, CA. We find that the LC-FCN model performs the best and achieves an average precision between 0.56 and 0.61 and an average recall between 0.78 and 0.92 over three held out test scenes.
With the development of deep networks on various large-scale datasets, a large zoo of pretrained models are available. When transferring from a model zoo, applying classic single-model based transfer learning methods to each source model suffers from high computational burden and cannot fully utilize the rich knowledge in the zoo. We propose \emph{Zoo-Tuning} to address these challenges, which learns to adaptively transfer the parameters of pretrained models to the target task. With the learnable channel alignment layer and adaptive aggregation layer, Zoo-Tuning \emph{adaptively aggregates channel aligned pretrained parameters} to derive the target model, which promotes knowledge transfer by simultaneously adapting multiple source models to downstream tasks. The adaptive aggregation substantially reduces the computation cost at both training and inference. We further propose lite Zoo-Tuning with the temporal ensemble of batch average gating values to reduce the storage cost at the inference time. We evaluate our approach on a variety of tasks, including reinforcement learning, image classification, and facial landmark detection. Experiment results demonstrate that the proposed adaptive transfer learning approach can transfer knowledge from a zoo of models more effectively and efficiently.
We propose a novel semi-supervised image segmentation method that simultaneously optimizes a supervised segmentation and an unsupervised reconstruction objectives. The reconstruction objective uses an attention mechanism that separates the reconstruction of image areas corresponding to different classes. The proposed approach was evaluated on two applications: brain tumor and white matter hyperintensities segmentation. Our method, trained on unlabeled and a small number of labeled images, outperformed supervised CNNs trained with the same number of images and CNNs pre-trained on unlabeled data. In ablation experiments, we observed that the proposed attention mechanism substantially improves segmentation performance. We explore two multi-task training strategies: joint training and alternating training. Alternating training requires fewer hyperparameters and achieves a better, more stable performance than joint training. Finally, we analyze the features learned by different methods and find that the attention mechanism helps to learn more discriminative features in the deeper layers of encoders.
We describe a robotic learning system for autonomous navigation in diverse environments. At the core of our method are two components: (i) a non-parametric map that reflects the connectivity of the environment but does not require geometric reconstruction or localization, and (ii) a latent variable model of distances and actions that enables efficiently constructing and traversing this map. The model is trained on a large dataset of prior experience to predict the expected amount of time and next action needed to transit between the current image and a goal image. Training the model in this way enables it to develop a representation of goals robust to distracting information in the input images, which aids in deploying the system to quickly explore new environments. We demonstrate our method on a mobile ground robot in a range of outdoor navigation scenarios. Our method can learn to reach new goals, specified as images, in a radius of up to 80 meters in just 20 minutes, and reliably revisit these goals in changing environments. We also demonstrate our method's robustness to previously-unseen obstacles and variable weather conditions. We encourage the reader to visit the project website for videos of our experiments and demonstrations https://sites.google.com/view/recon-robot