October 21, 2019

3308 words 16 mins read

Paper Group AWR 49

Dopamine: A Research Framework for Deep Reinforcement Learning. PCGAN: Partition-Controlled Human Image Generation. Cancer Metastasis Detection With Neural Conditional Random Field. Exploiting Contextual Information via Dynamic Memory Network for Event Detection. Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers. BACH: Grand Chall …

Dopamine: A Research Framework for Deep Reinforcement Learning


Title	Dopamine: A Research Framework for Deep Reinforcement Learning
Authors	Pablo Samuel Castro, Subhodeep Moitra, Carles Gelada, Saurabh Kumar, Marc G. Bellemare
Abstract	Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
Tasks
Published	2018-12-14
URL	http://arxiv.org/abs/1812.06110v1
PDF	http://arxiv.org/pdf/1812.06110v1.pdf
PWC	https://paperswithcode.com/paper/dopamine-a-research-framework-for-deep
Repo	https://github.com/ACampero/dopamine
Framework	tf

PCGAN: Partition-Controlled Human Image Generation


Title	PCGAN: Partition-Controlled Human Image Generation
Authors	Dong Liang, Rui Wang, Xiaowei Tian, Cong Zou
Abstract	Human image generation is a very challenging task since it is affected by many factors. Many human image generation methods focus on generating human images conditioned on a given pose, while the generated backgrounds are often blurred.In this paper,we propose a novel Partition-Controlled GAN to generate human images according to target pose and background. Firstly, human poses in the given images are extracted, and foreground/background are partitioned for further use. Secondly, we extract and fuse appearance features, pose features and background features to generate the desired images. Experiments on Market-1501 and DeepFashion datasets show that our model not only generates realistic human images but also produce the human pose and background as we want. Extensive experiments on COCO and LIP datasets indicate the potential of our method.
Tasks	Image Generation
Published	2018-11-25
URL	http://arxiv.org/abs/1811.09928v1
PDF	http://arxiv.org/pdf/1811.09928v1.pdf
PWC	https://paperswithcode.com/paper/pcgan-partition-controlled-human-image
Repo	https://github.com/AlanIIE/PCGAN
Framework	tf

Cancer Metastasis Detection With Neural Conditional Random Field


Title	Cancer Metastasis Detection With Neural Conditional Random Field
Authors	Yi Li, Wei Ping
Abstract	Breast cancer diagnosis often requires accurate detection of metastasis in lymph nodes through Whole-slide Images (WSIs). Recent advances in deep convolutional neural networks (CNNs) have shown significant successes in medical image analysis and particularly in computational histopathology. Because of the outrageous large size of WSIs, most of the methods divide one slide into lots of small image patches and perform classification on each patch independently. However, neighboring patches often share spatial correlations, and ignoring these spatial correlations may result in inconsistent predictions. In this paper, we propose a neural conditional random field (NCRF) deep learning framework to detect cancer metastasis in WSIs. NCRF considers the spatial correlations between neighboring patches through a fully connected CRF which is directly incorporated on top of a CNN feature extractor. The whole deep network can be trained end-to-end with standard back-propagation algorithm with minor computational overhead from the CRF component. The CNN feature extractor can also benefit from considering spatial correlations via the CRF component. Compared to the baseline method without considering spatial correlations, we show that the proposed NCRF framework obtains probability maps of patch predictions with better visual quality. We also demonstrate that our method outperforms the baseline in cancer metastasis detection on the Camelyon16 dataset and achieves an average FROC score of 0.8096 on the test set. NCRF is open sourced at https://github.com/baidu-research/NCRF.
Tasks	Cancer Metastasis Detection
Published	2018-06-19
URL	http://arxiv.org/abs/1806.07064v1
PDF	http://arxiv.org/pdf/1806.07064v1.pdf
PWC	https://paperswithcode.com/paper/cancer-metastasis-detection-with-neural
Repo	https://github.com/baidu-research/NCRF
Framework	pytorch

Exploiting Contextual Information via Dynamic Memory Network for Event Detection


Title	Exploiting Contextual Information via Dynamic Memory Network for Event Detection
Authors	Shaobo Liu, Rui Cheng, Xiaoming Yu, Xueqi Cheng
Abstract	The task of event detection involves identifying and categorizing event triggers. Contextual information has been shown effective on the task. However, existing methods which utilize contextual information only process the context once. We argue that the context can be better exploited by processing the context multiple times, allowing the model to perform complex reasoning and to generate better context representation, thus improving the overall performance. Meanwhile, dynamic memory network (DMN) has demonstrated promising capability in capturing contextual information and has been applied successfully to various tasks. In light of the multi-hop mechanism of the DMN to model the context, we propose the trigger detection dynamic memory network (TD-DMN) to tackle the event detection problem. We performed a five-fold cross-validation on the ACE-2005 dataset and experimental results show that the multi-hop mechanism does improve the performance and the proposed model achieves best $F_1$ score compared to the state-of-the-art methods.
Tasks
Published	2018-10-03
URL	http://arxiv.org/abs/1810.03449v1
PDF	http://arxiv.org/pdf/1810.03449v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-contextual-information-via-dynamic
Repo	https://github.com/AveryLiu/TD-DMN
Framework	pytorch

Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers


Title	Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers
Authors	Stephan R. Richter, Stefan Roth
Abstract	In this paper, we develop novel, efficient 2D encodings for 3D geometry, which enable reconstructing full 3D shapes from a single image at high resolution. The key idea is to pose 3D shape reconstruction as a 2D prediction problem. To that end, we first develop a simple baseline network that predicts entire voxel tubes at each pixel of a reference view. By leveraging well-proven architectures for 2D pixel-prediction tasks, we attain state-of-the-art results, clearly outperforming purely voxel-based approaches. We scale this baseline to higher resolutions by proposing a memory-efficient shape encoding, which recursively decomposes a 3D shape into nested shape layers, similar to the pieces of a Matryoshka doll. This allows reconstructing highly detailed shapes with complex topology, as demonstrated in extensive experiments; we clearly outperform previous octree-based approaches despite having a much simpler architecture using standard network components. Our Matryoshka networks further enable reconstructing shapes from IDs or shape similarity, as well as shape sampling.
Tasks
Published	2018-04-29
URL	http://arxiv.org/abs/1804.10975v1
PDF	http://arxiv.org/pdf/1804.10975v1.pdf
PWC	https://paperswithcode.com/paper/matryoshka-networks-predicting-3d-geometry
Repo	https://github.com/JeremyFisher/deep_level_sets
Framework	pytorch

BACH: Grand Challenge on Breast Cancer Histology Images


Title	BACH: Grand Challenge on Breast Cancer Histology Images
Authors	Guilherme Aresta, Teresa Araújo, Scotty Kwok, Sai Saketh Chennamsetty, Mohammed Safwan, Varghese Alex, Bahram Marami, Marcel Prastawa, Monica Chan, Michael Donovan, Gerardo Fernandez, Jack Zeineh, Matthias Kohl, Christoph Walz, Florian Ludwig, Stefan Braunewell, Maximilian Baust, Quoc Dang Vu, Minh Nguyen Nhat To, Eal Kim, Jin Tae Kwak, Sameh Galal, Veronica Sanchez-Freire, Nadia Brancati, Maria Frucci, Daniel Riccio, Yaqi Wang, Lingling Sun, Kaiqiang Ma, Jiannan Fang, Ismael Kone, Lahsen Boulmane, Aurélio Campilho, Catarina Eloy, António Polónia, Paulo Aguiar
Abstract	Breast cancer is the most common invasive cancer in women, affecting more than 10% of women worldwide. Microscopic analysis of a biopsy remains one of the most important methods to diagnose the type of breast cancer. This requires specialized analysis by pathologists, in a task that i) is highly time- and cost-consuming and ii) often leads to nonconsensual results. The relevance and potential of automatic classification algorithms using hematoxylin-eosin stained histopathological images has already been demonstrated, but the reported results are still sub-optimal for clinical use. With the goal of advancing the state-of-the-art in automatic classification, the Grand Challenge on BreAst Cancer Histology images (BACH) was organized in conjunction with the 15th International Conference on Image Analysis and Recognition (ICIAR 2018). A large annotated dataset, composed of both microscopy and whole-slide images, was specifically compiled and made publicly available for the BACH challenge. Following a positive response from the scientific community, a total of 64 submissions, out of 677 registrations, effectively entered the competition. From the submitted algorithms it was possible to push forward the state-of-the-art in terms of accuracy (87%) in automatic classification of breast cancer with histopathological images. Convolutional neuronal networks were the most successful methodology in the BACH challenge. Detailed analysis of the collective results allowed the identification of remaining challenges in the field and recommendations for future developments. The BACH dataset remains publically available as to promote further improvements to the field of automatic classification in digital pathology.
Tasks
Published	2018-08-13
URL	https://arxiv.org/abs/1808.04277v2
PDF	https://arxiv.org/pdf/1808.04277v2.pdf
PWC	https://paperswithcode.com/paper/bach-grand-challenge-on-breast-cancer
Repo	https://github.com/scottykwok/bach2018
Framework	none

Grounded Human-Object Interaction Hotspots from Video


Title	Grounded Human-Object Interaction Hotspots from Video
Authors	Tushar Nagarajan, Christoph Feichtenhofer, Kristen Grauman
Abstract	Learning how to interact with objects is an important step towards embodied visual intelligence, but existing techniques suffer from heavy supervision or sensing requirements. We propose an approach to learn human-object interaction “hotspots” directly from video. Rather than treat affordances as a manually supervised semantic segmentation task, our approach learns about interactions by watching videos of real human behavior and anticipating afforded actions. Given a novel image or video, our model infers a spatial hotspot map indicating how an object would be manipulated in a potential interaction– even if the object is currently at rest. Through results with both first and third person video, we show the value of grounding affordances in real human-object interactions. Not only are our weakly supervised hotspots competitive with strongly supervised affordance methods, but they can also anticipate object interaction for novel object categories.
Tasks	Human-Object Interaction Detection, Object Recognition, Semantic Segmentation
Published	2018-12-11
URL	http://arxiv.org/abs/1812.04558v2
PDF	http://arxiv.org/pdf/1812.04558v2.pdf
PWC	https://paperswithcode.com/paper/grounded-human-object-interaction-hotspots
Repo	https://github.com/Tushar-N/interaction-hotspots
Framework	pytorch

Graphical Generative Adversarial Networks


Title	Graphical Generative Adversarial Networks
Authors	Chongxuan Li, Max Welling, Jun Zhu, Bo Zhang
Abstract	We propose Graphical Generative Adversarial Networks (Graphical-GAN) to model structured data. Graphical-GAN conjoins the power of Bayesian networks on compactly representing the dependency structures among random variables and that of generative adversarial networks on learning expressive dependency functions. We introduce a structured recognition model to infer the posterior distribution of latent variables given observations. We generalize the Expectation Propagation (EP) algorithm to learn the generative model and recognition model jointly. Finally, we present two important instances of Graphical-GAN, i.e. Gaussian Mixture GAN (GMGAN) and State Space GAN (SSGAN), which can successfully learn the discrete and temporal structures on visual datasets, respectively.
Tasks
Published	2018-04-10
URL	http://arxiv.org/abs/1804.03429v2
PDF	http://arxiv.org/pdf/1804.03429v2.pdf
PWC	https://paperswithcode.com/paper/graphical-generative-adversarial-networks
Repo	https://github.com/zhenxuan00/graphical-gan
Framework	tf

Actions Speak Louder Than Goals: Valuing Player Actions in Soccer


Title	Actions Speak Louder Than Goals: Valuing Player Actions in Soccer
Authors	Tom Decroos, Lotte Bransen, Jan Van Haaren, Jesse Davis
Abstract	Assessing the impact of the individual actions performed by soccer players during games is a crucial aspect of the player recruitment process. Unfortunately, most traditional metrics fall short in addressing this task as they either focus on rare actions like shots and goals alone or fail to account for the context in which the actions occurred. This paper introduces (1) a new language for describing individual player actions on the pitch and (2) a framework for valuing any type of player action based on its impact on the game outcome while accounting for the context in which the action happened. By aggregating soccer players’ action values, their total offensive and defensive contributions to their team can be quantified. We show how our approach considers relevant contextual information that traditional player evaluation metrics ignore and present a number of use cases related to scouting and playing style characterization in the 2016/2017 and 2017/2018 seasons in Europe’s top competitions.
Tasks	Football Action Valuation
Published	2018-02-18
URL	https://arxiv.org/abs/1802.07127v2
PDF	https://arxiv.org/pdf/1802.07127v2.pdf
PWC	https://paperswithcode.com/paper/actions-speak-louder-than-goals-valuing
Repo	https://github.com/ML-KULeuven/socceraction
Framework	none

Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games


Title	Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games
Authors	Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo
Abstract	Reinforcement learning (RL) is an area of research that has blossomed tremendously in recent years and has shown remarkable potential for artificial intelligence based opponents in computer games. This success is primarily due to the vast capabilities of convolutional neural networks, that can extract useful features from noisy and complex data. Games are excellent tools to test and push the boundaries of novel RL algorithms because they give valuable insight into how well an algorithm can perform in isolated environments without the real-life consequences. Real-time strategy games (RTS) is a genre that has tremendous complexity and challenges the player in short and long-term planning. There is much research that focuses on applied RL in RTS games, and novel advances are therefore anticipated in the not too distant future. However, there are to date few environments for testing RTS AIs. Environments in the literature are often either overly simplistic, such as microRTS, or complex and without the possibility for accelerated learning on consumer hardware like StarCraft II. This paper introduces the Deep RTS game environment for testing cutting-edge artificial intelligence algorithms for RTS games. Deep RTS is a high-performance RTS game made specifically for artificial intelligence research. It supports accelerated learning, meaning that it can learn at a magnitude of 50 000 times faster compared to existing RTS games. Deep RTS has a flexible configuration, enabling research in several different RTS scenarios, including partially observable state-spaces and map complexity. We show that Deep RTS lives up to our promises by comparing its performance with microRTS, ELF, and StarCraft II on high-end consumer hardware. Using Deep RTS, we show that a Deep Q-Network agent beats random-play agents over 70% of the time. Deep RTS is publicly available at https://github.com/cair/DeepRTS.
Tasks	Real-Time Strategy Games, Starcraft, Starcraft II
Published	2018-08-15
URL	http://arxiv.org/abs/1808.05032v1
PDF	http://arxiv.org/pdf/1808.05032v1.pdf
PWC	https://paperswithcode.com/paper/deep-rts-a-game-environment-for-deep
Repo	https://github.com/cair/DeepRTS
Framework	none

Human-guided data exploration using randomisation


Title	Human-guided data exploration using randomisation
Authors	Kai Puolamäki, Emilia Oikarinen, Buse Atli, Andreas Henelius
Abstract	An explorative data analysis system should be aware of what the user already knows and what the user wants to know of the data: otherwise the system cannot provide the user with the most informative and useful views of the data. We propose a principled way to do exploratory data analysis, where the user’s background knowledge is modeled by a distribution parametrised by subsets of rows and columns in the data, called tiles. The user can also use tiles to describe his or her interests concerning relations in the data. We provide a computationally efficient implementation of this concept based on constrained randomisation. The implementation is used to model both the background knowledge and the user’s information request and is a necessary prerequisite for any interactive system. Furthermore, we describe a novel linear projection pursuit method to find and show the views most informative to the user, which at the limit of no background knowledge and with generic objectives reduces to PCA. We show that our method is robust under noise and fast enough for interactive use. We also show that the method gives understandable and useful results when analysing real-world data sets. We will release an open source library implementing the idea, including the experiments presented in this paper. We show that our method can outperform standard projection pursuit visualisation methods in exploration tasks. Our framework makes it possible to construct human-guided data exploration systems which are fast, powerful, and give results that are easy to comprehend.
Tasks
Published	2018-05-20
URL	http://arxiv.org/abs/1805.07725v2
PDF	http://arxiv.org/pdf/1805.07725v2.pdf
PWC	https://paperswithcode.com/paper/human-guided-data-exploration-using
Repo	https://github.com/edahelsinki/corand
Framework	none

Subspace Network: Deep Multi-Task Censored Regression for Modeling Neurodegenerative Diseases


Title	Subspace Network: Deep Multi-Task Censored Regression for Modeling Neurodegenerative Diseases
Authors	Mengying Sun, Inci M. Baytas, Liang Zhan, Zhangyang Wang, Jiayu Zhou
Abstract	Over the past decade a wide spectrum of machine learning models have been developed to model the neurodegenerative diseases, associating biomarkers, especially non-intrusive neuroimaging markers, with key clinical scores measuring the cognitive status of patients. Multi-task learning (MTL) has been commonly utilized by these studies to address high dimensionality and small cohort size challenges. However, most existing MTL approaches are based on linear models and suffer from two major limitations: 1) they cannot explicitly consider upper/lower bounds in these clinical scores; 2) they lack the capability to capture complicated non-linear interactions among the variables. In this paper, we propose Subspace Network, an efficient deep modeling approach for non-linear multi-task censored regression. Each layer of the subspace network performs a multi-task censored regression to improve upon the predictions from the last layer via sketching a low-dimensional subspace to perform knowledge transfer among learning tasks. Under mild assumptions, for each layer the parametric subspace can be recovered using only one pass of training data. Empirical results demonstrate that the proposed subspace network quickly picks up the correct parameter subspaces, and outperforms state-of-the-arts in predicting neurodegenerative clinical scores using information in brain imaging.
Tasks	Multi-Task Learning, Transfer Learning
Published	2018-02-19
URL	http://arxiv.org/abs/1802.06516v2
PDF	http://arxiv.org/pdf/1802.06516v2.pdf
PWC	https://paperswithcode.com/paper/subspace-network-deep-multi-task-censored
Repo	https://github.com/illidanlab/subspace-net
Framework	none

Self-Attention: A Better Building Block for Sentiment Analysis Neural Network Classifiers


Title	Self-Attention: A Better Building Block for Sentiment Analysis Neural Network Classifiers
Authors	Artaches Ambartsoumian, Fred Popowich
Abstract	Sentiment Analysis has seen much progress in the past two decades. For the past few years, neural network approaches, primarily RNNs and CNNs, have been the most successful for this task. Recently, a new category of neural networks, self-attention networks (SANs), have been created which utilizes the attention mechanism as the basic building block. Self-attention networks have been shown to be effective for sequence modeling tasks, while having no recurrence or convolutions. In this work we explore the effectiveness of the SANs for sentiment analysis. We demonstrate that SANs are superior in performance to their RNN and CNN counterparts by comparing their classification accuracy on six datasets as well as their model characteristics such as training speed and memory consumption. Finally, we explore the effects of various SAN modifications such as multi-head attention as well as two methods of incorporating sequence position information into SANs.
Tasks	Sentiment Analysis
Published	2018-12-19
URL	http://arxiv.org/abs/1812.07860v1
PDF	http://arxiv.org/pdf/1812.07860v1.pdf
PWC	https://paperswithcode.com/paper/self-attention-a-better-building-block-for
Repo	https://github.com/Artaches/SSAN-self-attention-sentiment-analysis-classification
Framework	none

Hate Speech Dataset from a White Supremacy Forum


Title	Hate Speech Dataset from a White Supremacy Forum
Authors	Ona de Gibert, Naiara Perez, Aitor García-Pablos, Montse Cuadros
Abstract	Hate speech is commonly defined as any communication that disparages a target group of people based on some characteristic such as race, colour, ethnicity, gender, sexual orientation, nationality, religion, or other characteristic. Due to the massive rise of user-generated web content on social media, the amount of hate speech is also steadily increasing. Over the past years, interest in online hate speech detection and, particularly, the automation of this task has continuously grown, along with the societal impact of the phenomenon. This paper describes a hate speech dataset composed of thousands of sentences manually labelled as containing hate speech or not. The sentences have been extracted from Stormfront, a white supremacist forum. A custom annotation tool has been developed to carry out the manual labelling task which, among other things, allows the annotators to choose whether to read the context of a sentence before labelling it. The paper also provides a thoughtful qualitative and quantitative study of the resulting dataset and several baseline experiments with different classification models. The dataset is publicly available.
Tasks	Hate Speech Detection
Published	2018-09-12
URL	http://arxiv.org/abs/1809.04444v1
PDF	http://arxiv.org/pdf/1809.04444v1.pdf
PWC	https://paperswithcode.com/paper/hate-speech-dataset-from-a-white-supremacy
Repo	https://github.com/aitor-garcia-p/hate-speech-dataset
Framework	none

BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning


Title	BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning
Authors	Boris Ivanovic, James Harrison, Apoorva Sharma, Mo Chen, Marco Pavone
Abstract	Model-free Reinforcement Learning (RL) offers an attractive approach to learn control policies for high-dimensional systems, but its relatively poor sample complexity often forces training in simulated environments. Even in simulation, goal-directed tasks whose natural reward function is sparse remain intractable for state-of-the-art model-free algorithms for continuous control. The bottleneck in these tasks is the prohibitive amount of exploration required to obtain a learning signal from the initial state of the system. In this work, we leverage physical priors in the form of an approximate system dynamics model to design a curriculum scheme for a model-free policy optimization algorithm. Our Backward Reachability Curriculum (BaRC) begins policy training from states that require a small number of actions to accomplish the task, and expands the initial state distribution backwards in a dynamically-consistent manner once the policy optimization algorithm demonstrates sufficient performance. BaRC is general, in that it can accelerate training of any model-free RL algorithm on a broad class of goal-directed continuous control MDPs. Its curriculum strategy is physically intuitive, easy-to-tune, and allows incorporating physical priors to accelerate training without hindering the performance, flexibility, and applicability of the model-free RL algorithm. We evaluate our approach on two representative dynamic robotic learning problems and find substantial performance improvement relative to previous curriculum generation techniques and naive exploration strategies.
Tasks	Continuous Control
Published	2018-06-16
URL	http://arxiv.org/abs/1806.06161v2
PDF	http://arxiv.org/pdf/1806.06161v2.pdf
PWC	https://paperswithcode.com/paper/barc-backward-reachability-curriculum-for
Repo	https://github.com/StanfordASL/BaRC
Framework	none