February 1, 2020

3205 words 16 mins read

Paper Group AWR 281

Kindling the Darkness: A Practical Low-light Image Enhancer. Blind Deblurring Using GANs. Maximum Entropy-Regularized Multi-Goal Reinforcement Learning. Diversified Arbitrary Style Transfer via Deep Feature Perturbation. Drug-Target Indication Prediction by Integrating End-to-End Learning and Fingerprints. Neural Spline Flows. Flickr1024: A Large-S …

Kindling the Darkness: A Practical Low-light Image Enhancer


Title	Kindling the Darkness: A Practical Low-light Image Enhancer
Authors	Yonghua Zhang, Jiawan Zhang, Xiaojie Guo
Abstract	Images captured under low-light conditions often suffer from (partially) poor visibility. Besides unsatisfactory lightings, multiple types of degradations, such as noise and color distortion due to the limited quality of cameras, hide in the dark. In other words, solely turning up the brightness of dark regions will inevitably amplify hidden artifacts. This work builds a simple yet effective network for \textbf{Kin}dling the \textbf{D}arkness (denoted as KinD), which, inspired by Retinex theory, decomposes images into two components. One component (illumination) is responsible for light adjustment, while the other (reflectance) for degradation removal. In such a way, the original space is decoupled into two smaller subspaces, expecting to be better regularized/learned. It is worth to note that our network is trained with paired images shot under different exposure conditions, instead of using any ground-truth reflectance and illumination information. Extensive experiments are conducted to demonstrate the efficacy of our design and its superiority over state-of-the-art alternatives. Our KinD is robust against severe visual defects, and user-friendly to arbitrarily adjust light levels. In addition, our model spends less than 50ms to process an image in VGA resolution on a 2080Ti GPU. All the above merits make our KinD attractive for practical use.
Tasks	Low-Light Image Enhancement
Published	2019-05-04
URL	https://arxiv.org/abs/1905.04161v1
PDF	https://arxiv.org/pdf/1905.04161v1.pdf
PWC	https://paperswithcode.com/paper/190504161
Repo	https://github.com/zhangyhuaee/KinD
Framework	tf


Title	Blind Deblurring Using GANs
Authors	Manoj Kumar Lenka, Anubha Pandey, Anurag Mittal
Abstract	Deblurring is the task of restoring a blurred image to a sharp one, retrieving the information lost due to the blur. In blind deblurring we have no information regarding the blur kernel. As deblurring can be considered as an image to image translation task, deep learning based solutions, including the ones which use GAN (Generative Adversarial Network), have been proven effective for deblurring. Most of them have an encoder-decoder structure. Our objective is to try different GAN structures and improve its performance through various modifications to the existing structure for supervised deblurring. In supervised deblurring we have pairs of blurred and their corresponding sharp images, while in the unsupervised case we have a set of blurred and sharp images but their is no correspondence between them. Modifications to the structures is done to improve the global perception of the model. As blur is non-uniform in nature, for deblurring we require global information of the entire image, whereas convolution used in CNN is able to provide only local perception. Deep models can be used to improve global perception but due to large number of parameters it becomes difficult for it to converge and inference time increases, to solve this we propose the use of attention module (non-local block) which was previously used in language translation and other image to image translation tasks in deblurring. Use of residual connection also improves the performance of deblurring as features from the lower layers are added to the upper layers of the model. It has been found that classical losses like L1, L2, and perceptual loss also help in training of GANs when added together with adversarial loss. We also concatenate edge information of the image to observe its effects on deblurring. We also use feedback modules to retain long term dependencies
Tasks	Deblurring, Image-to-Image Translation
Published	2019-07-27
URL	https://arxiv.org/abs/1907.11880v1
PDF	https://arxiv.org/pdf/1907.11880v1.pdf
PWC	https://paperswithcode.com/paper/blind-deblurring-using-gans
Repo	https://github.com/lenka98/Bind-Deblurring-using-GANs
Framework	tf

Maximum Entropy-Regularized Multi-Goal Reinforcement Learning


Title	Maximum Entropy-Regularized Multi-Goal Reinforcement Learning
Authors	Rui Zhao, Xudong Sun, Volker Tresp
Abstract	In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected randomly for replay. However, the achieved goals in the replay buffer are often biased towards the behavior policies. From a Bayesian perspective, when there is no prior knowledge about the target goal distribution, the agent should learn uniformly from diverse achieved goals. Therefore, we first propose a novel multi-goal RL objective based on weighted entropy. This objective encourages the agent to maximize the expected return, as well as to achieve more diverse goals. Secondly, we developed a maximum entropy-based prioritization framework to optimize the proposed objective. For evaluation of this framework, we combine it with Deep Deterministic Policy Gradient, both with or without Hindsight Experience Replay. On a set of multi-goal robotic tasks of OpenAI Gym, we compare our method with other baselines and show promising improvements in both performance and sample-efficiency.
Tasks	Multi-Goal Reinforcement Learning
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08786v2
PDF	https://arxiv.org/pdf/1905.08786v2.pdf
PWC	https://paperswithcode.com/paper/maximum-entropy-regularized-multi-goal
Repo	https://github.com/ruizhaogit/mep
Framework	none

Diversified Arbitrary Style Transfer via Deep Feature Perturbation


Title	Diversified Arbitrary Style Transfer via Deep Feature Perturbation
Authors	Zhizhong Wang, Lei Zhao, Haibo Chen, Lihong Qiu, Qihang Mo, Sihuan Lin, Wei Xing, Dongming Lu
Abstract	Image style transfer is an underdetermined problem, where a large number of solutions can satisfy the same constraint (the content and style). Although there have been some efforts to improve the diversity of style transfer by introducing an alternative diversity loss, they have restricted generalization, limited diversity and poor scalability. In this paper, we tackle these limitations and propose a simple yet effective method for diversified arbitrary style transfer. The key idea of our method is an operation called deep feature perturbation (DFP), which uses an orthogonal random noise matrix to perturb the deep image feature maps while keeping the original style information unchanged. Our DFP operation can be easily integrated into many existing WCT (whitening and coloring transform)-based methods, and empower them to generate diverse results for arbitrary styles. Experimental results demonstrate that this learning-free and universal method can greatly increase the diversity while maintaining the quality of stylization.
Tasks	Style Transfer
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08223v3
PDF	https://arxiv.org/pdf/1909.08223v3.pdf
PWC	https://paperswithcode.com/paper/diversified-arbitrary-style-transfer-via-deep
Repo	https://github.com/EndyWon/Deep-Feature-Perturbation
Framework	none

Drug-Target Indication Prediction by Integrating End-to-End Learning and Fingerprints


Title	Drug-Target Indication Prediction by Integrating End-to-End Learning and Fingerprints
Authors	Brighter Agyemang, Wei-Ping Wu, Michael Y. Kpiebaareh, Ebenezer Nanor
Abstract	Computer-Aided Drug Discovery research has proven to be a promising direction in drug discovery. In recent years, Deep Learning approaches have been applied to problems in the domain such as Drug-Target Interaction Prediction and have shown improvements over traditional screening methods. An existing challenge is how to represent compound-target pairs in deep learning models. While several representation methods exist, such descriptor schemes tend to complement one another in many instances, as reported in the literature. In this study, we propose a multi-view architecture trained adversarially to leverage this complementary behavior by integrating both differentiable and predefined molecular descriptors. We conduct experiments on clinically relevant benchmark datasets to demonstrate the potential of our approach.
Tasks	Drug Discovery
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01163v2
PDF	https://arxiv.org/pdf/1912.01163v2.pdf
PWC	https://paperswithcode.com/paper/drug-target-indication-prediction-by
Repo	https://github.com/bbrighttaer/ivpgan
Framework	pytorch

Neural Spline Flows


Title	Neural Spline Flows
Authors	Conor Durkan, Artur Bekasov, Iain Murray, George Papamakarios
Abstract	A normalizing flow models a complex probability density as an invertible transformation of a simple base density. Flows based on either coupling or autoregressive transforms both offer exact density evaluation and sampling, but rely on the parameterization of an easily invertible elementwise transformation, whose choice determines the flexibility of these models. Building upon recent work, we propose a fully-differentiable module based on monotonic rational-quadratic splines, which enhances the flexibility of both coupling and autoregressive transforms while retaining analytic invertibility. We demonstrate that neural spline flows improve density estimation, variational inference, and generative modeling of images.
Tasks	Density Estimation
Published	2019-06-10
URL	https://arxiv.org/abs/1906.04032v2
PDF	https://arxiv.org/pdf/1906.04032v2.pdf
PWC	https://paperswithcode.com/paper/neural-spline-flows
Repo	https://github.com/bayesiains/nsf
Framework	pytorch

Flickr1024: A Large-Scale Dataset for Stereo Image Super-Resolution


Title	Flickr1024: A Large-Scale Dataset for Stereo Image Super-Resolution
Authors	Yingqian Wang, Longguang Wang, Jungang Yang, Wei An, Yulan Guo
Abstract	With the popularity of dual cameras in recently released smart phones, a growing number of super-resolution (SR) methods have been proposed to enhance the resolution of stereo image pairs. However, the lack of high-quality stereo datasets has limited the research in this area. To facilitate the training and evaluation of novel stereo SR algorithms, in this paper, we present a large-scale stereo dataset named Flickr1024, which contains 1024 pairs of high-quality images and covers diverse scenarios. We first introduce the data acquisition and processing pipeline, and then compare several popular stereo datasets. Finally, we conduct crossdataset experiments to investigate the potential benefits introduced by our dataset. Experimental results show that, as compared to the KITTI and Middlebury datasets, our Flickr1024 dataset can help to handle the over-fitting problem and significantly improves the performance of stereo SR methods. The Flickr1024 dataset is available online at: https://yingqianwang.github.io/Flickr1024.
Tasks	Image Super-Resolution, Stereo Image Super-Resolution, Super-Resolution
Published	2019-03-15
URL	https://arxiv.org/abs/1903.06332v2
PDF	https://arxiv.org/pdf/1903.06332v2.pdf
PWC	https://paperswithcode.com/paper/flickr1024-a-dataset-for-stereo-image-super
Repo	https://github.com/YingqianWang/Flickr1024
Framework	none

From Dark Matter to Galaxies with Convolutional Neural Networks


Title	From Dark Matter to Galaxies with Convolutional Neural Networks
Authors	Jacky H. T. Yip, Xinyue Zhang, Yanfang Wang, Wei Zhang, Yueqiu Sun, Gabriella Contardo, Francisco Villaescusa-Navarro, Siyu He, Shy Genel, Shirley Ho
Abstract	Cosmological simulations play an important role in the interpretation of astronomical data, in particular in comparing observed data to our theoretical expectations. However, to compare data with these simulations, the simulations in principle need to include gravity, magneto-hydrodyanmics, radiative transfer, etc. These ideal large-volume simulations (gravo-magneto-hydrodynamical) are incredibly computationally expensive which can cost tens of millions of CPU hours to run. In this paper, we propose a deep learning approach to map from the dark-matter-only simulation (computationally cheaper) to the galaxy distribution (from the much costlier cosmological simulation). The main challenge of this task is the high sparsity in the target galaxy distribution: space is mainly empty. We propose a cascade architecture composed of a classification filter followed by a regression procedure. We show that our result outperforms a state-of-the-art model used in the astronomical community, and provides a good trade-off between computational cost and prediction accuracy.
Tasks
Published	2019-10-17
URL	https://arxiv.org/abs/1910.07813v1
PDF	https://arxiv.org/pdf/1910.07813v1.pdf
PWC	https://paperswithcode.com/paper/from-dark-matter-to-galaxies-with-1
Repo	https://github.com/jhtyip/From-Dark-Matter-to-Galaxies-with-Convolutional-Neural-Networks
Framework	pytorch

Parametric Majorization for Data-Driven Energy Minimization Methods


Title	Parametric Majorization for Data-Driven Energy Minimization Methods
Authors	Jonas Geiping, Michael Moeller
Abstract	Energy minimization methods are a classical tool in a multitude of computer vision applications. While they are interpretable and well-studied, their regularity assumptions are difficult to design by hand. Deep learning techniques on the other hand are purely data-driven, often provide excellent results, but are very difficult to constrain to predefined physical or safety-critical models. A possible combination between the two approaches is to design a parametric energy and train the free parameters in such a way that minimizers of the energy correspond to desired solution on a set of training examples. Unfortunately, such formulations typically lead to bi-level optimization problems, on which common optimization algorithms are difficult to scale to modern requirements in data processing and efficiency. In this work, we present a new strategy to optimize these bi-level problems. We investigate surrogate single-level problems that majorize the target problems and can be implemented with existing tools, leading to efficient algorithms without collapse of the energy function. This framework of strategies enables new avenues to the training of parameterized energy minimization models from large data.
Tasks
Published	2019-08-17
URL	https://arxiv.org/abs/1908.06209v1
PDF	https://arxiv.org/pdf/1908.06209v1.pdf
PWC	https://paperswithcode.com/paper/parametric-majorization-for-data-driven
Repo	https://github.com/JonasGeiping/ParametricMajorization
Framework	pytorch

Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective


Title	Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective
Authors	Chengqiang Lu, Qi Liu, Chao Wang, Zhenya Huang, Peize Lin, Lixin He
Abstract	Predicting molecular properties (e.g., atomization energy) is an essential issue in quantum chemistry, which could speed up much research progress, such as drug designing and substance discovery. Traditional studies based on density functional theory (DFT) in physics are proved to be time-consuming for predicting large number of molecules. Recently, the machine learning methods, which consider much rule-based information, have also shown potentials for this issue. However, the complex inherent quantum interactions of molecules are still largely underexplored by existing solutions. In this paper, we propose a generalizable and transferable Multilevel Graph Convolutional neural Network (MGCN) for molecular property prediction. Specifically, we represent each molecule as a graph to preserve its internal structure. Moreover, the well-designed hierarchical graph neural network directly extracts features from the conformation and spatial information followed by the multilevel interactions. As a consequence, the multilevel overall representations can be utilized to make the prediction. Extensive experiments on both datasets of equilibrium and off-equilibrium molecules demonstrate the effectiveness of our model. Furthermore, the detailed results also prove that MGCN is generalizable and transferable for the prediction.
Tasks	Graph Regression, Molecular Property Prediction
Published	2019-06-25
URL	https://arxiv.org/abs/1906.11081v1
PDF	https://arxiv.org/pdf/1906.11081v1.pdf
PWC	https://paperswithcode.com/paper/molecular-property-prediction-a-multilevel
Repo	https://github.com/tencent-alchemy/Alchemy
Framework	pytorch

Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification


Title	Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
Authors	Zhun Zhong, Liang Zheng, Zhiming Luo, Shaozi Li, Yi Yang
Abstract	This paper considers the domain adaptive person re-identification (re-ID) problem: learning a re-ID model from a labeled source domain and an unlabeled target domain. Conventional methods are mainly to reduce feature distribution gap between the source and target domains. However, these studies largely neglect the intra-domain variations in the target domain, which contain critical factors influencing the testing performance on the target domain. In this work, we comprehensively investigate into the intra-domain variations of the target domain and propose to generalize the re-ID model w.r.t three types of the underlying invariance, i.e., exemplar-invariance, camera-invariance and neighborhood-invariance. To achieve this goal, an exemplar memory is introduced to store features of the target domain and accommodate the three invariance properties. The memory allows us to enforce the invariance constraints over global training batch without significantly increasing computation cost. Experiment demonstrates that the three invariance properties and the proposed memory are indispensable towards an effective domain adaptation system. Results on three re-ID domains show that our domain adaptation accuracy outperforms the state of the art by a large margin. Code is available at: https://github.com/zhunzhong07/ECN
Tasks	Domain Adaptation, Person Re-Identification
Published	2019-04-03
URL	http://arxiv.org/abs/1904.01990v1
PDF	http://arxiv.org/pdf/1904.01990v1.pdf
PWC	https://paperswithcode.com/paper/invariance-matters-exemplar-memory-for-domain
Repo	https://github.com/zhunzhong07/ECN
Framework	pytorch

Methods and open-source toolkit for analyzing and visualizing challenge results


Title	Methods and open-source toolkit for analyzing and visualizing challenge results
Authors	Manuel Wiesenfarth, Annika Reinke, Bennett A. Landman, Manuel Jorge Cardoso, Lena Maier-Hein, Annette Kopp-Schneider
Abstract	Biomedical challenges have become the de facto standard for benchmarking biomedical image analysis algorithms. While the number of challenges is steadily increasing, surprisingly little effort has been invested in ensuring high quality design, execution and reporting for these international competitions. Specifically, results analysis and visualization in the event of uncertainties have been given almost no attention in the literature. Given these shortcomings, the contribution of this paper is two-fold: (1) We present a set of methods to comprehensively analyze and visualize the results of single-task and multi-task challenges and apply them to a number of simulated and real-life challenges to demonstrate their specific strengths and weaknesses; (2) We release the open-source framework challengeR as part of this work to enable fast and wide adoption of the methodology proposed in this paper. Our approach offers an intuitive way to gain important insights into the relative and absolute performance of algorithms, which cannot be revealed by commonly applied visualization techniques. This is demonstrated by the experiments performed within this work. Our framework could thus become an important tool for analyzing and visualizing challenge results in the field of biomedical image analysis and beyond.
Tasks
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05121v2
PDF	https://arxiv.org/pdf/1910.05121v2.pdf
PWC	https://paperswithcode.com/paper/methods-and-open-source-toolkit-for-analyzing
Repo	https://github.com/wiesenfa/challengeR
Framework	none

Unsupervised Person Re-identification by Soft Multilabel Learning


Title	Unsupervised Person Re-identification by Soft Multilabel Learning
Authors	Hong-Xing Yu, Wei-Shi Zheng, Ancong Wu, Xiaowei Guo, Shaogang Gong, Jian-Huang Lai
Abstract	Although unsupervised person re-identification (RE-ID) has drawn increasing research attentions due to its potential to address the scalability problem of supervised RE-ID models, it is very challenging to learn discriminative information in the absence of pairwise labels across disjoint camera views. To overcome this problem, we propose a deep model for the soft multilabel learning for unsupervised RE-ID. The idea is to learn a soft multilabel (real-valued label likelihood vector) for each unlabeled person by comparing (and representing) the unlabeled person with a set of known reference persons from an auxiliary domain. We propose the soft multilabel-guided hard negative mining to learn a discriminative embedding for the unlabeled target domain by exploring the similarity consistency of the visual features and the soft multilabels of unlabeled target pairs. Since most target pairs are cross-view pairs, we develop the cross-view consistent soft multilabel learning to achieve the learning goal that the soft multilabels are consistently good across different camera views. To enable effecient soft multilabel learning, we introduce the reference agent learning to represent each reference person by a reference agent in a joint embedding. We evaluate our unified deep model on Market-1501 and DukeMTMC-reID. Our model outperforms the state-of-the-art unsupervised RE-ID methods by clear margins. Code is available at https://github.com/KovenYu/MAR.
Tasks	Person Re-Identification, Unsupervised Person Re-Identification
Published	2019-03-15
URL	http://arxiv.org/abs/1903.06325v2
PDF	http://arxiv.org/pdf/1903.06325v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-person-re-identification-by-soft
Repo	https://github.com/KovenYu/MAR
Framework	pytorch

Tree-Sliced Variants of Wasserstein Distances


Title	Tree-Sliced Variants of Wasserstein Distances
Authors	Tam Le, Makoto Yamada, Kenji Fukumizu, Marco Cuturi
Abstract	Optimal transport (\OT) theory defines a powerful set of tools to compare probability distributions. \OT~suffers however from a few drawbacks, computational and statistical, which have encouraged the proposal of several regularized variants of OT in the recent literature, one of the most notable being the \textit{sliced} formulation, which exploits the closed-form formula between univariate distributions by projecting high-dimensional measures onto random lines. We consider in this work a more general family of ground metrics, namely \textit{tree metrics}, which also yield fast closed-form computations and negative definite, and of which the sliced-Wasserstein distance is a particular case (the tree is a chain). We propose the tree-sliced Wasserstein distance, computed by averaging the Wasserstein distance between these measures using random tree metrics, built adaptively in either low or high-dimensional spaces. Exploiting the negative definiteness of that distance, we also propose a positive definite kernel, and test it against other baselines on a few benchmark tasks.
Tasks
Published	2019-02-01
URL	https://arxiv.org/abs/1902.00342v3
PDF	https://arxiv.org/pdf/1902.00342v3.pdf
PWC	https://paperswithcode.com/paper/tree-sliced-approximation-of-wasserstein
Repo	https://github.com/lttam/TreeWasserstein
Framework	none

Contextually Propagated Term Weights for Document Representation


Title	Contextually Propagated Term Weights for Document Representation
Authors	Casper Hansen, Christian Hansen, Stephen Alstrup, Jakob Grue Simonsen, Christina Lioma
Abstract	Word embeddings predict a word from its neighbours by learning small, dense embedding vectors. In practice, this prediction corresponds to a semantic score given to the predicted word (or term weight). We present a novel model that, given a target word, redistributes part of that word’s weight (that has been computed with word embeddings) across words occurring in similar contexts as the target word. Thus, our model aims to simulate how semantic meaning is shared by words occurring in similar contexts, which is incorporated into bag-of-words document representations. Experimental evaluation in an unsupervised setting against 8 state of the art baselines shows that our model yields the best micro and macro F1 scores across datasets of increasing difficulty.
Tasks	Word Embeddings
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00674v1
PDF	https://arxiv.org/pdf/1906.00674v1.pdf
PWC	https://paperswithcode.com/paper/190600674
Repo	https://github.com/casperhansen/CPTW
Framework	none