In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of semantic image segmentation. To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates. Furthermore, we propose to augment our previously proposed Atrous Spatial Pyramid Pooling module, which probes convolutional features at multiple scales, with image-level features encoding global context and further boost performance. We also elaborate on implementation details and share our experience on training our system. The proposed `DeepLabv3' system significantly improves over our previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.

Rethinking Atrous Convolution for Semantic Image Segmentation

Rendering the semantic content of an image in different styles is a difficult image processing task. Arguably, a major limiting factor for previous approaches has been the lack of image representations that explicitly represent semantic information and, thus, allow to separate image content from style. Here we use image representations derived from Convolutional Neural Networks optimised for object recognition, which make high level image information explicit. We introduce A Neural Algorithm of Artistic Style that can separate and recombine the image content and style of natural images. The algorithm allows us to produce new images of high perceptual quality that combine the content of an arbitrary photograph with the appearance of numerous wellknown artworks. Our results provide new insights into the deep image representations learned by Convolutional Neural Networks and demonstrate their potential for high level image synthesis and manipulation.

/pdf/image-style-transfer-using-convolutional-neural-networks-xq8m0q3iz5.pdf

Image Style Transfer Using Convolutional Neural Networks

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.

/pdf/stacked-hourglass-networks-for-human-pose-estimation-dlf71xnitp.pdf

Stacked Hourglass Networks for Human Pose Estimation

Learning an interpretable factorised representation of the independent data generative factors of the world without supervision is an important precursor for the development of artificial intelligence that is able to learn and reason in the same way that humans do. We introduce beta-VAE, a new state-of-the-art framework for automated discovery of interpretable factorised latent representations from raw image data in a completely unsupervised manner. Our approach is a modification of the variational autoencoder (VAE) framework. We introduce an adjustable hyperparameter beta that balances latent channel capacity and independence constraints with reconstruction accuracy. We demonstrate that beta-VAE with appropriately tuned beta > 1 qualitatively outperforms VAE (beta = 1), as well as state of the art unsupervised (InfoGAN) and semi-supervised (DC-IGN) approaches to disentangled factor learning on a variety of datasets (celebA, faces and chairs). Furthermore, we devise a protocol to quantitatively compare the degree of disentanglement learnt by different models, and show that our approach also significantly outperforms all baselines quantitatively. Unlike InfoGAN, beta-VAE is stable to train, makes few assumptions about the data and relies on tuning a single hyperparameter, which can be directly optimised through a hyper parameter search using weakly labelled data or through heuristic visual inspection for purely unsupervised data.

beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework

Systems, methods, and non-transitory computer-readable media are disclosed for segmenting objects in digital visual media utilizing one or more salient content neural networks. In particular, in one or more embodiments, the disclosed systems and methods train one or more salient content neural networks to efficiently identify foreground pixels in digital visual media. Moreover, in one or more embodiments, the disclosed systems and methods provide a trained salient content neural network to a mobile device, allowing the mobile device to directly select salient objects in digital visual media utilizing a trained neural network. Furthermore, in one or more embodiments, the disclosed systems and methods train and provide multiple salient content neural networks, such that mobile devices can identify objects in real-time digital visual media feeds (utilizing a first salient content neural network) and identify objects in static digital images (utilizing a second salient content neural network).

Deep salient content neural networks for efficient digital object segmentation

We present two approaches to extract regions from structured edge detection. While the state-of-the-art algorithm based on globalized probability of boundary (gPb) generates a hierarchical region tree, it entails significant computational load. In this work, we exploit an efficient algorithm for structured edge prediction to extract regions. To generate high quality regions, we develop a novel algorithm to link the structured edge and gPb hierarchical image segmentation framework with steerable filters. The extracted regions are grouped by the proposed hierarchical grouping method to generate object proposals for effective detection and recognition problems. We demonstrate the effectiveness of our region generation for image segmentation on the BSDS500 database, and region generation for object proposals on the PASCAL VOC 2007 benchmark database. Experimental results show that the proposed algorithm achieves the comparable or superior quality to the state-of-the-art methods.

/pdf/extracting-image-regions-by-structured-edge-prediction-1ilp9ewotz.pdf

Extracting Image Regions by Structured Edge Prediction

Appearance of dressed humans undergoes a complex geometric transformation induced not only by the static pose but also by its dynamics, i.e., there exists a number of cloth geometric configurations given a pose depending on the way it has moved. Such appearance modeling conditioned on motion has been largely neglected in existing human rendering methods, resulting in rendering of physically implausible motion. A key challenge of learning the dynamics of the appearance lies in the requirement of a prohibitively large amount of observations. In this paper, we present a compact motion representation by enforcing equivariance—a representation is expected to be transformed in the way that the pose is transformed. We model an equivariant encoder that can generate the generalizable representation from the spatial and temporal derivatives of the 3D body surface. This learned representation is decoded by a compositional multi-task decoder that renders high fidelity time-varying appearance. Our experiments show that our method can generate a temporally coherent video of dynamic humans for unseen body poses and novel views given a single view video.

Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans from a Single Camera

Recent progress on physics-based character animation has shown impressive breakthroughs on human motion synthesis, through imitating motion capture data via deep reinforcement learning. However, results have mostly been demonstrated on imitating a single distinct motion pattern, and do not generalize to interactive tasks that require flexible motion patterns due to varying human-object spatial configurations. To bridge this gap, we focus on one class of interactive tasks---sitting onto a chair. We propose a hierarchical reinforcement learning framework which relies on a collection of subtask controllers trained to imitate simple, reusable mocap motions, and a meta controller trained to execute the subtasks properly to complete the main task. We experimentally demonstrate the strength of our approach over different non-hierarchical and hierarchical baselines. We also show that our approach can be applied to motion prediction given an image input. A supplementary video can be found at https://youtu.be/3CeN0OGz2cA.

/pdf/learning-to-sit-synthesizing-human-chair-interactions-via-2fzuw17nzg.pdf

Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control

/pdf/decomposed-learning-for-joint-segmentation-and-39ll4a8bhg.pdf

Jimei Yang

Papers

Deep salient content neural networks for efficient digital object segmentation

Extracting Image Regions by Structured Edge Prediction

Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans from a Single Camera

Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control

Decomposed Learning for Joint Segmentation and Categorization.