Generative Transition Mechanism to Image-to-Image Translation via Encoded Transformation

In this paper, we revisit the Image-to-Image (I2I) translation problem with transition consistency, namely the consistency defined on the conditional data mapping between each data pairs. Explicitly parameterizing each data mappings with a transition variable $t$, i.e., $x \overset{t(x,y)}{\mapsto}y$, we discover that existing I2I translation models mainly focus on maintaining consistency on results, e.g., image reconstruction or attribute prediction, named result consistency in our paper. This restricts their generalization ability to generate satisfactory results with unseen transitions in the test phase. Consequently, we propose to enforce both result consistency and transition consistency for I2I translation, to benefit the problem with a closer consistency between the input and output. To benefit the generalization ability of the translation model, we propose transition encoding to facilitate explicit regularization of these two {kinds} of consistencies on unseen transitions. We further generalize such explicitly regularized consistencies to distribution-level, thus facilitating a generalized overall consistency for I2I translation problems. With the above design, our proposed model, named Transition Encoding GAN (TEGAN), can poss superb generalization ability to generate realistic and semantically consistent translation results with unseen transitions in the test phase. It also provides a unified understanding of the existing GAN-based I2I transition models with our explicitly modeling of the data mapping, i.e., transition. Experiments on four different I2I translation tasks demonstrate the efficacy and generality of TEGAN.

A survey of image labelling for computer vision applications

Supervised machine learning methods for image analysis require large amounts of labelled training data to solve computer vision problems. The recent rise of deep learning algorithms for recognising image content has led to the emergence of many ad-hoc labelling tools. With this survey, we capture and systematise the commonalities as well as the distinctions between existing image labelling software. We perform a structured literature review to compile the underlying concepts and features of image labelling software such as annotation expressiveness and degree of automation. We structure the manual labelling task by its organisation of work, user interface design options, and user support techniques to derive a systematisation schema for this survey. Applying it to available software and the body of literature, enabled us to uncover several application archetypes and key domains such as image retrieval or instance identification in healthcare or television.

An Iterative Labeling Method for Annotating Fisheries Imagery

In this paper, we present a methodology for fisheries-related data that allows us to converge on a labeled image dataset by iterating over the dataset with multiple training and production loops that can exploit crowdsourcing interfaces. We present our algorithm and its results on two separate sets of image data collected using the Seabed autonomous underwater vehicle. The first dataset comprises of 2,026 completely unlabeled images, while the second consists of 21,968 images that were point annotated by experts. Our results indicate that training with a small subset and iterating on that to build a larger set of labeled data allows us to converge to a fully annotated dataset with a small number of iterations. Even in the case of a dataset labeled by experts, a single iteration of the methodology improves the labels by discovering additional complicated examples of labels associated with fish that overlap, are very small, or obscured by the contrast limitations associated with underwater imagery.

A Distillation Learning Model of Adaptive Structural Deep Belief Network for AffectNet: Facial Expression Image Database

Deep Learning has a hierarchical network architecture to represent the complicated feature of input patterns. We have developed the adaptive structure learning method of Deep Belief Network (DBN) that can discover an optimal number of hidden neurons for given input data in a Restricted Boltzmann Machine (RBM) by neuron generation-annihilation algorithm, and can obtain the appropriate number of hidden layers in DBN. In this paper, our model is applied to a facial expression image data set, AffectNet. The system has higher classification capability than the traditional CNN. However, our model was not able to classify some test cases correctly because human emotions contain many ambiguous features or patterns leading wrong answer by two or more annotators who have different subjective judgment for a facial image. In order to represent such cases, this paper investigated a distillation learning model of Adaptive DBN. The original trained model can be seen as a parent model and some child models are trained for some mis-classified cases. For the difference between the parent model and the child one, KL divergence is monitored and then some appropriate new neurons at the parent model are generated according to KL divergence to improve classification accuracy. In this paper, the classification accuracy was improved from 78.4% to 91.3% by the proposed method.

Motion Compensated Three-Dimensional Frequency Selective Extrapolation for Improved Error Concealment in Video Communication

During transmission of video data over error-prone channels the risk of getting severe image distortions due to transmission errors is ubiquitous. To deal with image distortions at decoder side, error concealment is applied. This article presents Motion Compensated Three-Dimensional Frequency Selective Extrapolation, a novel spatio-temporal error concealment algorithm. The algorithm uses fractional-pel motion estimation and compensation as initial step, being followed by the generation of a model of the distorted signal. The model generation is conducted by an enhanced version of Three-Dimensional Frequency Selective Extrapolation, an existing error concealment algorithm. Compared to this existent algorithm, the proposed one yields an improvement in concealment quality of up to 1.64 dB PSNR. Altogether, the incorporation of motion compensation and the improved model generation extends the already high extrapolation quality of the underlying Frequency Selective Extrapolation, resulting in a gain of more than 3 dB compared to other well-known error concealment algorithms.

On Measuring and Controlling the Spectral Bias of the Deep Image Prior

The deep image prior has demonstrated the remarkable ability that untrained networks can address inverse imaging problems, such as denoising, inpainting and super-resolution, by optimizing on just a single degraded image. Despite its promise, it suffers from two limitations. First, it remains unclear how one can control the prior beyond the choice of the network architecture. Second, it requires an oracle to determine when to stop the optimization as the performance degrades after reaching a peak. In this paper, we study the deep image prior from a spectral bias perspective to address these problems. By introducing a frequency-band correspondence measure, we observe that deep image priors for inverse imaging exhibit a spectral bias during optimization, where low-frequency image signals are learned faster and better than high-frequency noise signals. This pinpoints why degraded images can be denoised or inpainted when the optimization is stopped at the right time. Based on our observations, we propose to control the spectral bias in the deep image prior to prevent performance degradation and to speed up optimization convergence. We do so in the two core layer types of inverse imaging networks: the convolution layer and the upsampling layer. We present a Lipschitz-controlled approach for the convolution and a Gaussian-controlled approach for the upsampling layer. We further introduce a stopping criterion to avoid superfluous computation. The experiments on denoising, inpainting and super-resolution show that our method no longer suffers from performance degradation during optimization, relieving us from the need for an oracle criterion to stop early. We further outline a stopping criterion to avoid superfluous computation. Finally, we show that our approach obtains favorable restoration results compared to current approaches, across all tasks.

OPD: Single-view 3D Openable Part Detection

We address the task of predicting what parts of an object can open and how they move when they do so. The input is a single image of an object, and as output we detect what parts of the object can open, and the motion parameters describing the articulation of each openable part. To tackle this task, we create two datasets of 3D objects: OPDSynth based on existing synthetic objects, and OPDReal based on RGBD reconstructions of real objects. We then design OPDRCNN, a neural architecture that detects openable parts and predicts their motion parameters. Our experiments show that this is a challenging task especially when considering generalization across object categories, and the limited amount of information in a single image. Our architecture outperforms baselines and prior work especially for RGB image inputs. Short video summary at https://www.youtube.com/watch?v=P85iCaD0rfc

Online progressive instance-balanced sampling for weakly supervised object detection

Based on multiple instance detection networks (MIDN), plenty of works have contributed tremendous efforts to weakly supervised object detection (WSOD). However, most methods neglect the fact that the overwhelming negative instances exist in each image during the training phase, which would mislead the training and make the network fall into local minima. To tackle this problem, an online progressive instance-balanced sampling (OPIS) algorithm based on hard sampling and soft sampling is proposed in this paper. The algorithm includes two modules: a progressive instance balance (PIB) module and a progressive instance reweighting (PIR) module. The PIB module combining random sampling and IoU-balanced sampling progressively mines hard negative instances while balancing positive instances and negative instances. The PIR module further utilizes classifier scores and IoUs of adjacent refinements to reweight the weights of positive instances for making the network focus on positive instances. Extensive experimental results on the PASCAL VOC 2007 and 2012 datasets demonstrate the proposed method can significantly improve the baseline, which is also comparable to many existing state-of-the-art results. In addition, compared to the baseline, the proposed method requires no extra network parameters and the supplementary training overheads are small, which could be easily integrated into other methods based on the instance classifier refinement paradigm.

Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots

Real noisy-clean pairs on a large scale are costly and difficult to obtain. Meanwhile, supervised denoisers trained on synthetic data perform poorly in practice. Self-supervised denoisers, which learn only from single noisy images, solve the data collection problem. However, self-supervised denoising methods, especially blindspot-driven ones, suffer sizable information loss during input or network design. The absence of valuable information dramatically reduces the upper bound of denoising performance. In this paper, we propose a simple yet efficient approach called Blind2Unblind to overcome the information loss in blindspot-driven denoising methods. First, we introduce a global-aware mask mapper that enables global perception and accelerates training. The mask mapper samples all pixels at blind spots on denoised volumes and maps them to the same channel, allowing the loss function to optimize all blind spots at once. Second, we propose a re-visible loss to train the denoising network and make blind spots visible. The denoiser can learn directly from raw noise images without losing information or being trapped in identity mapping. We also theoretically analyze the convergence of the re-visible loss. Extensive experiments on synthetic and real-world datasets demonstrate the superior performance of our approach compared to previous work. Code is available at https://github.com/demonsjin/Blind2Unblind.

Learning to generate imaginary tasks for improving generalization in meta-learning

The success of meta-learning on existing benchmarks is predicated on the assumption that the distribution of meta-training tasks covers meta-testing tasks. Frequent violation of the assumption in applications with either insufficient tasks or a very narrow meta-training task distribution leads to memorization or learner overfitting. Recent solutions have pursued augmentation of meta-training tasks, while it is still an open question to generate both correct and sufficiently imaginary tasks. In this paper, we seek an approach that up-samples meta-training tasks from the task representation via a task up-sampling network. Besides, the resulting approach named Adversarial Task Up-sampling (ATU) suffices to generate tasks that can maximally contribute to the latest meta-learner by maximizing an adversarial loss. On few-shot sine regression and image classification datasets, we empirically validate the marked improvement of ATU over state-of-the-art task augmentation strategies in the meta-testing performance and also the quality of up-sampled tasks.