Distributed Submodular Minimization via Block-Wise Updates and Communications

In this paper we deal with a network of computing agents with local processing and neighboring communication capabilities that aim at solving (without any central unit) a submodular optimization problem. The cost function is the sum of many local submodular functions and each agent in the network has access to one function in the sum only. In this \emph{distributed} set-up, in order to preserve their own privacy, agents communicate with neighbors but do not share their local cost functions. We propose a distributed algorithm in which agents resort to the Lov\`{a}sz extension of their local submodular functions and perform local updates and communications in terms of single blocks of the entire optimization variable. Updates are performed by means of a greedy algorithm which is run only until the selected block is computed, thus resulting in a reduced computational burden. The proposed algorithm is shown to converge in expected value to the optimal cost of the problem, and an approximate solution to the submodular problem is retrieved by a thresholding operation. As an application, we consider a distributed image segmentation problem in which each agent has access only to a portion of the entire image. While agent cannot segment the entire image on their own, they correctly complete the task by cooperating through the proposed distributed algorithm.

Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling

We show that the sum of the implicit generator log-density $\log p_g$ of a GAN with the logit score of the discriminator defines an energy function which yields the true data density when the generator is imperfect but the discriminator is optimal, thus making it possible to improve on the typical generator (with implicit density $p_g$). To make that practical, we show that sampling from this modified density can be achieved by sampling in latent space according to an energy-based model induced by the sum of the latent prior log-density and the discriminator output score. This can be achieved by running a Langevin MCMC in latent space and then applying the generator function, which we call Discriminator Driven Latent Sampling~(DDLS). We show that DDLS is highly efficient compared to previous methods which work in the high-dimensional pixel space and can be applied to improve on previously trained GANs of many types. We evaluate DDLS on both synthetic and real-world datasets qualitatively and quantitatively. On CIFAR-10, DDLS substantially improves the Inception Score of an off-the-shelf pre-trained SN-GAN~\citep{sngan} from $8.22$ to $9.09$ which is even comparable to the class-conditional BigGAN~\citep{biggan} model. This achieves a new state-of-the-art in unconditional image synthesis setting without introducing extra parameters or additional training.

Three-Dimensional Fourier Scattering Transform and Classification of Hyperspectral Images

Recent research has resulted in many new techniques that are able to capture the special properties of hyperspectral data for hyperspectral image analysis, with hyperspectral image classification as one of the most active tasks. Time-frequency methods decompose spectra into multi-spectral bands, while hierarchical methods like neural networks incorporate spatial information across scales and model multiple levels of dependencies between spectral features. The Fourier scattering transform is an amalgamation of time-frequency representations with neural network architectures, both of which have recently been proven to provide significant advances in spectral-spatial classification. We test the proposed three dimensional Fourier scattering method on four standard hyperspectral datasets, and present results that indicate that the Fourier scattering transform is highly effective at representing spectral data when compared with other state-of-the-art spectral-spatial classification methods.

Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement

In this paper, we propose a Hierarchical Learned Video Compression (HLVC) method with three hierarchical quality layers and recurrent enhancement. The frames in the first layer are compressed by a image compression method with the highest quality. Using these frames as references, we propose the Bi-Directional Deep Compression (BDDC) network to compress the second layer with relatively high quality. Then, the third layer frames are compressed with the lowest quality, by the proposed Single Motion Deep Compression (SMDC) network, which adopts a single motion map to estimate the motions of multiple frames, thus saving bits for motion information. In our deep decoder, we develop the Weighted Recurrent Quality Enhancement (WRQE) network, which takes both compressed frames and the bit stream as inputs. In the recurrent cell of the WRQE, the memory and update signal are weighted by quality features to reasonably leverage multi-frame information for enhancement. In our HLVC approach, the hierarchical quality benefits the coding efficiency, since the high quality information facilitates the compression and enhancement of low quality frames at encoder and decoder sides, respectively. Finally, the experiments validate that our HLVC approach advances the state-of-the-art of deep video compression methods, and outperforms the "Low-Delay P (LDP) very fast" mode of x265 in terms of both PSNR and MS-SSIM. The project page is at https://github.com/RenYang-home/HLVC.

Breast mass segmentation based on ultrasonic entropy maps and attention gated U-Net

We propose a novel deep learning based approach to breast mass segmentation in ultrasound (US) imaging. In comparison to commonly applied segmentation methods, which use US images, our approach is based on quantitative entropy parametric maps. To segment the breast masses we utilized an attention gated U-Net convolutional neural network. US images and entropy maps were generated based on raw US signals collected from 269 breast masses. The segmentation networks were developed separately using US image and entropy maps, and evaluated on a test set of 81 breast masses. The attention U-Net trained based on entropy maps achieved average Dice score of 0.60 (median 0.71), while for the model trained using US images we obtained average Dice score of 0.53 (median 0.59). Our work presents the feasibility of using quantitative US parametric maps for the breast mass segmentation. The obtained results suggest that US parametric maps, which provide the information about local tissue scattering properties, might be more suitable for the development of breast mass segmentation methods than regular US images.

Unified Attentional Generative Adversarial Network for Brain Tumor Segmentation From Multimodal Unpaired Images

In medical applications, the same anatomical structures may be observed in multiple modalities despite the different image characteristics. Currently, most deep models for multimodal segmentation rely on paired registered images. However, multimodal paired registered images are difficult to obtain in many cases. Therefore, developing a model that can segment the target objects from different modalities with unpaired images is significant for many clinical applications. In this work, we propose a novel two-stream translation and segmentation unified attentional generative adversarial network (UAGAN), which can perform any-to-any image modality translation and segment the target objects simultaneously in the case where two or more modalities are available. The translation stream is used to capture modality-invariant features of the target anatomical structures. In addition, to focus on segmentation-related features, we add attentional blocks to extract valuable features from the translation stream. Experiments on three-modality brain tumor segmentation indicate that UAGAN outperforms the existing methods in most cases.

An Empirical Study on Leveraging Scene Graphs for Visual Question Answering

Visual question answering (Visual QA) has attracted significant attention these years. While a variety of algorithms have been proposed, most of them are built upon different combinations of image and language features as well as multi-modal attention and fusion. In this paper, we investigate an alternative approach inspired by conventional QA systems that operate on knowledge graphs. Specifically, we investigate the use of scene graphs derived from images for Visual QA: an image is abstractly represented by a graph with nodes corresponding to object entities and edges to object relationships. We adapt the recently proposed graph network (GN) to encode the scene graph and perform structured reasoning according to the input question. Our empirical studies demonstrate that scene graphs can already capture essential information of images and graph networks have the potential to outperform state-of-the-art Visual QA algorithms but with a much cleaner architecture. By analyzing the features generated by GNs we can further interpret the reasoning process, suggesting a promising direction towards explainable Visual QA.

Playing Games in the Dark: An approach for cross-modality transfer in reinforcement learning

In this work we explore the use of latent representations obtained from multiple input sensory modalities (such as images or sounds) in allowing an agent to learn and exploit policies over different subsets of input modalities. We propose a three-stage architecture that allows a reinforcement learning agent trained over a given sensory modality, to execute its task on a different sensory modality-for example, learning a visual policy over image inputs, and then execute such policy when only sound inputs are available. We show that the generalized policies achieve better out-of-the-box performance when compared to different baselines. Moreover, we show this holds in different OpenAI gym and video game environments, even when using different multimodal generative models and reinforcement learning algorithms.

Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation

Sequence generation models are commonly refined with reinforcement learning over user-defined metrics. However, high gradient variance hinders the practical use of this method. To stabilize this method, we adapt to contextual generation of categorical sequences a policy gradient estimator, which evaluates a set of correlated Monte Carlo (MC) rollouts for variance control. Due to the correlation, the number of unique rollouts is random and adaptive to model uncertainty; those rollouts naturally become baselines for each other, and hence are combined to effectively reduce gradient variance. We also demonstrate the use of correlated MC rollouts for binary-tree softmax models, which reduce the high generation cost in large vocabulary scenarios by decomposing each categorical action into a sequence of binary actions. We evaluate our methods on both neural program synthesis and image captioning. The proposed methods yield lower gradient variance and consistent improvement over related baselines.

Adding Intuitive Physics to Neural-Symbolic Capsules Using Interaction Networks

Many current methods to learn intuitive physics are based on interaction networks and similar approaches. However, they rely on information that has proven difficult to estimate directly from image data in the past. We aim to narrow this gap by inferring all the semantic information needed from raw pixel data in the form of a scene-graph. Our approach is based on neural-symbolic capsules, which identify which objects in the scene are static, dynamic, elastic or rigid, possible joints between them, as well as their collision information. By integrating all this with interaction networks, we demonstrate how our method is able to learn intuitive physics directly from image sequences and apply its knowledge to new scenes and objects, resulting in an inverse-simulation pipeline.