July 29, 2019

2871 words 14 mins read

Paper Group AWR 180

Like trainer, like bot? Inheritance of bias in algorithmic content moderation. SigNet: Convolutional Siamese Network for Writer Independent Offline Signature Verification. FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis. Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation. Learning to Compose Task-Specif …

Like trainer, like bot? Inheritance of bias in algorithmic content moderation


Title	Like trainer, like bot? Inheritance of bias in algorithmic content moderation
Authors	Reuben Binns, Michael Veale, Max Van Kleek, Nigel Shadbolt
Abstract	The internet has become a central medium through which `networked publics’ express their opinions and engage in debate. Offensive comments and personal attacks can inhibit participation in these spaces. Automated content moderation aims to overcome this problem using machine learning classifiers trained on large corpora of texts manually annotated for offence. While such systems could help encourage more civil debate, they must navigate inherently normatively contestable boundaries, and are subject to the idiosyncratic norms of the human raters who provide the training data. An important objective for platforms implementing such measures might be to ensure that they are not unduly biased towards or against particular norms of offence. This paper provides some exploratory methods by which the normative biases of algorithmic content moderation systems can be measured, by way of a case study using an existing dataset of comments labelled for offence. We train classifiers on comments labelled by different demographic subsets (men and women) to understand how differences in conceptions of offence between these groups might affect the performance of the resulting models on various test sets. We conclude by discussing some of the ethical choices facing the implementers of algorithmic moderation systems, given various desired levels of diversity of viewpoints amongst discussion participants. \|
Tasks
Published	2017-07-05
URL	http://arxiv.org/abs/1707.01477v1
PDF	http://arxiv.org/pdf/1707.01477v1.pdf
PWC	https://paperswithcode.com/paper/like-trainer-like-bot-inheritance-of-bias-in
Repo	https://github.com/sociam/liketrainer
Framework	none

SigNet: Convolutional Siamese Network for Writer Independent Offline Signature Verification


Title	SigNet: Convolutional Siamese Network for Writer Independent Offline Signature Verification
Authors	Sounak Dey, Anjan Dutta, J. Ignacio Toledo, Suman K. Ghosh, Josep Llados, Umapada Pal
Abstract	Offline signature verification is one of the most challenging tasks in biometrics and document forensics. Unlike other verification problems, it needs to model minute but critical details between genuine and forged signatures, because a skilled falsification might often resembles the real signature with small deformation. This verification task is even harder in writer independent scenarios which is undeniably fiscal for realistic cases. In this paper, we model an offline writer independent signature verification task with a convolutional Siamese network. Siamese networks are twin networks with shared weights, which can be trained to learn a feature space where similar observations are placed in proximity. This is achieved by exposing the network to a pair of similar and dissimilar observations and minimizing the Euclidean distance between similar pairs while simultaneously maximizing it between dissimilar pairs. Experiments conducted on cross-domain datasets emphasize the capability of our network to model forgery in different languages (scripts) and handwriting styles. Moreover, our designed Siamese network, named SigNet, exceeds the state-of-the-art results on most of the benchmark signature datasets, which paves the way for further research in this direction.
Tasks
Published	2017-07-07
URL	http://arxiv.org/abs/1707.02131v2
PDF	http://arxiv.org/pdf/1707.02131v2.pdf
PWC	https://paperswithcode.com/paper/signet-convolutional-siamese-network-for
Repo	https://github.com/hlamba28/Offline-Signature-Verification-using-Siamese-Network
Framework	none

FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis


Title	FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis
Authors	Nitika Verma, Edmond Boyer, Jakob Verbeek
Abstract	Convolutional neural networks (CNNs) have massively impacted visual recognition in 2D images, and are now ubiquitous in state-of-the-art approaches. CNNs do not easily extend, however, to data that are not represented by regular grids, such as 3D shape meshes or other graph-structured data, to which traditional local convolution operators do not directly apply. To address this problem, we propose a novel graph-convolution operator to establish correspondences between filter weights and graph neighborhoods with arbitrary connectivity. The key novelty of our approach is that these correspondences are dynamically computed from features learned by the network, rather than relying on predefined static coordinates over the graph as in previous work. We obtain excellent experimental results that significantly improve over previous state-of-the-art shape correspondence results. This shows that our approach can learn effective shape representations from raw input coordinates, without relying on shape descriptors.
Tasks	3D Shape Analysis
Published	2017-06-16
URL	http://arxiv.org/abs/1706.05206v2
PDF	http://arxiv.org/pdf/1706.05206v2.pdf
PWC	https://paperswithcode.com/paper/feastnet-feature-steered-graph-convolutions
Repo	https://github.com/nitika-verma/FeaStNet
Framework	tf

Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation


Title	Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation
Authors	Arslan Chaudhry, Puneet K. Dokania, Philip H. S. Torr
Abstract	We propose an approach to discover class-specific pixels for the weakly-supervised semantic segmentation task. We show that properly combining saliency and attention maps allows us to obtain reliable cues capable of significantly boosting the performance. First, we propose a simple yet powerful hierarchical approach to discover the class-agnostic salient regions, obtained using a salient object detector, which otherwise would be ignored. Second, we use fully convolutional attention maps to reliably localize the class-specific regions in a given image. We combine these two cues to discover class-specific pixels which are then used as an approximate ground truth for training a CNN. While solving the weakly supervised semantic segmentation task, we ensure that the image-level classification task is also solved in order to enforce the CNN to assign at least one pixel to each object present in the image. Experimentally, on the PASCAL VOC12 val and test sets, we obtain the mIoU of 60.8% and 61.9%, achieving the performance gains of 5.1% and 5.2% compared to the published state-of-the-art results. The code is made publicly available.
Tasks	Semantic Segmentation, Weakly-Supervised Semantic Segmentation
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05821v1
PDF	http://arxiv.org/pdf/1707.05821v1.pdf
PWC	https://paperswithcode.com/paper/discovering-class-specific-pixels-for-weakly
Repo	https://github.com/arslan-chaudhry/dcsp_segmentation
Framework	tf

Learning to Compose Task-Specific Tree Structures


Title	Learning to Compose Task-Specific Tree Structures
Authors	Jihun Choi, Kang Min Yoo, Sang-goo Lee
Abstract	For years, recursive neural networks (RvNNs) have been shown to be suitable for representing text into fixed-length vectors and achieved good performance on several natural language processing tasks. However, the main drawback of RvNNs is that they require structured input, which makes data preparation and model implementation hard. In this paper, we propose Gumbel Tree-LSTM, a novel tree-structured long short-term memory architecture that learns how to compose task-specific tree structures only from plain text data efficiently. Our model uses Straight-Through Gumbel-Softmax estimator to decide the parent node among candidates dynamically and to calculate gradients of the discrete decision. We evaluate the proposed model on natural language inference and sentiment analysis, and show that our model outperforms or is at least comparable to previous models. We also find that our model converges significantly faster than other models.
Tasks	Natural Language Inference, Sentiment Analysis
Published	2017-07-10
URL	http://arxiv.org/abs/1707.02786v4
PDF	http://arxiv.org/pdf/1707.02786v4.pdf
PWC	https://paperswithcode.com/paper/learning-to-compose-task-specific-tree
Repo	https://github.com/jihunchoi/unsupervised-treelstm
Framework	pytorch

Learning Gradient Descent: Better Generalization and Longer Horizons


Title	Learning Gradient Descent: Better Generalization and Longer Horizons
Authors	Kaifeng Lv, Shunhua Jiang, Jian Li
Abstract	Training deep neural networks is a highly nontrivial task, involving carefully selecting appropriate training algorithms, scheduling step sizes and tuning other hyperparameters. Trying different combinations can be quite labor-intensive and time consuming. Recently, researchers have tried to use deep learning algorithms to exploit the landscape of the loss function of the training problem of interest, and learn how to optimize over it in an automatic way. In this paper, we propose a new learning-to-learn model and some useful and practical tricks. Our optimizer outperforms generic, hand-crafted optimization algorithms and state-of-the-art learning-to-learn optimizers by DeepMind in many tasks. We demonstrate the effectiveness of our algorithms on a number of tasks, including deep MLPs, CNNs, and simple LSTMs.
Tasks
Published	2017-03-10
URL	http://arxiv.org/abs/1703.03633v3
PDF	http://arxiv.org/pdf/1703.03633v3.pdf
PWC	https://paperswithcode.com/paper/learning-gradient-descent-better
Repo	https://github.com/daskol/paper-reviews
Framework	none

Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World


Title	Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World
Authors	Josh Tobin, Rachel Fong, Alex Ray, Jonas Schneider, Wojciech Zaremba, Pieter Abbeel
Abstract	Bridging the ‘reality gap’ that separates simulated robotics from experiments on hardware could accelerate robotic research through improved data availability. This paper explores domain randomization, a simple technique for training models on simulated images that transfer to real images by randomizing rendering in the simulator. With enough variability in the simulator, the real world may appear to the model as just another variation. We focus on the task of object localization, which is a stepping stone to general robotic manipulation skills. We find that it is possible to train a real-world object detector that is accurate to $1.5$cm and robust to distractors and partial occlusions using only data from a simulator with non-realistic random textures. To demonstrate the capabilities of our detectors, we show they can be used to perform grasping in a cluttered environment. To our knowledge, this is the first successful transfer of a deep neural network trained only on simulated RGB images (without pre-training on real images) to the real world for the purpose of robotic control.
Tasks	Object Localization
Published	2017-03-20
URL	http://arxiv.org/abs/1703.06907v1
PDF	http://arxiv.org/pdf/1703.06907v1.pdf
PWC	https://paperswithcode.com/paper/domain-randomization-for-transferring-deep
Repo	https://github.com/matwilso/rock_detector
Framework	tf

Perceptual Adversarial Networks for Image-to-Image Transformation


Title	Perceptual Adversarial Networks for Image-to-Image Transformation
Authors	Chaoyue Wang, Chang Xu, Chaohui Wang, Dacheng Tao
Abstract	In this paper, we propose a principled Perceptual Adversarial Networks (PAN) for image-to-image transformation tasks. Unlike existing application-specific algorithms, PAN provides a generic framework of learning mapping relationship between paired images (Fig. 1), such as mapping a rainy image to its de-rained counterpart, object edges to its photo, semantic labels to a scenes image, etc. The proposed PAN consists of two feed-forward convolutional neural networks (CNNs), the image transformation network T and the discriminative network D. Through combining the generative adversarial loss and the proposed perceptual adversarial loss, these two networks can be trained alternately to solve image-to-image transformation tasks. Among them, the hidden layers and output of the discriminative network D are upgraded to continually and automatically discover the discrepancy between the transformed image and the corresponding ground-truth. Simultaneously, the image transformation network T is trained to minimize the discrepancy explored by the discriminative network D. Through the adversarial training process, the image transformation network T will continually narrow the gap between transformed images and ground-truth images. Experiments evaluated on several image-to-image transformation tasks (e.g., image de-raining, image inpainting, etc.) show that the proposed PAN outperforms many related state-of-the-art methods.
Tasks	Image Inpainting
Published	2017-06-28
URL	http://arxiv.org/abs/1706.09138v2
PDF	http://arxiv.org/pdf/1706.09138v2.pdf
PWC	https://paperswithcode.com/paper/perceptual-adversarial-networks-for-image-to
Repo	https://github.com/DLHacks/pix2pix_PAN
Framework	pytorch

McKernel: A Library for Approximate Kernel Expansions in Log-linear Time


Title	McKernel: A Library for Approximate Kernel Expansions in Log-linear Time
Authors	Joachim D. Curtó, Irene C. Zarza, Feng Yang, Alexander J. Smola, Fernando De La Torre, Chong-Wah Ngo, Luc Van Gool
Abstract	Kernel Methods Next Generation (KMNG) introduces a framework to use kernel approximates in the mini-batch setting with SGD Optimizer as an alternative to Deep Learning. McKernel is a C++ library for KMNG ML Large-scale. It contains a CPU optimized implementation of the Fastfood algorithm that allows the computation of approximated kernel expansions in log-linear time. The algorithm requires to compute the product of Walsh Hadamard Transform (WHT) matrices. A cache friendly SIMD Fast Walsh Hadamard Transform (FWHT) that achieves compelling speed and outperforms current state-of-the-art methods has been developed. McKernel allows to obtain non-linear classification combining Fastfood and a linear classifier.
Tasks
Published	2017-02-27
URL	http://arxiv.org/abs/1702.08159v9
PDF	http://arxiv.org/pdf/1702.08159v9.pdf
PWC	https://paperswithcode.com/paper/mckernel-a-library-for-approximate-kernel
Repo	https://github.com/curto2/mckernel
Framework	none

Ask the Right Questions: Active Question Reformulation with Reinforcement Learning


Title	Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
Authors	Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Wojciech Gajewski, Andrea Gesmundo, Neil Houlsby, Wei Wang
Abstract	We frame Question Answering (QA) as a Reinforcement Learning task, an approach that we call Active Question Answering. We propose an agent that sits between the user and a black box QA system and learns to reformulate questions to elicit the best possible answers. The agent probes the system with, potentially many, natural language reformulations of an initial question and aggregates the returned evidence to yield the best answer. The reformulation system is trained end-to-end to maximize answer quality using policy gradient. We evaluate on SearchQA, a dataset of complex questions extracted from Jeopardy!. The agent outperforms a state-of-the-art base model, playing the role of the environment, and other benchmarks. We also analyze the language that the agent has learned while interacting with the question answering system. We find that successful question reformulations look quite different from natural language paraphrases. The agent is able to discover non-trivial reformulation strategies that resemble classic information retrieval techniques such as term re-weighting (tf-idf) and stemming.
Tasks	Information Retrieval, Question Answering
Published	2017-05-22
URL	http://arxiv.org/abs/1705.07830v3
PDF	http://arxiv.org/pdf/1705.07830v3.pdf
PWC	https://paperswithcode.com/paper/ask-the-right-questions-active-question
Repo	https://github.com/google/active-qa
Framework	tf

Towards Deeper Understanding of Variational Autoencoding Models


Title	Towards Deeper Understanding of Variational Autoencoding Models
Authors	Shengjia Zhao, Jiaming Song, Stefano Ermon
Abstract	We propose a new family of optimization criteria for variational auto-encoding models, generalizing the standard evidence lower bound. We provide conditions under which they recover the data distribution and learn latent features, and formally show that common issues such as blurry samples and uninformative latent features arise when these conditions are not met. Based on these new insights, we propose a new sequential VAE model that can generate sharp samples on the LSUN image dataset based on pixel-wise reconstruction loss, and propose an optimization criterion that encourages unsupervised learning of informative latent features.
Tasks
Published	2017-02-28
URL	http://arxiv.org/abs/1702.08658v1
PDF	http://arxiv.org/pdf/1702.08658v1.pdf
PWC	https://paperswithcode.com/paper/towards-deeper-understanding-of-variational
Repo	https://github.com/ShengjiaZhao/Generalized-PixelVAE
Framework	tf

Diabetic Retinopathy Detection via Deep Convolutional Networks for Discriminative Localization and Visual Explanation


Title	Diabetic Retinopathy Detection via Deep Convolutional Networks for Discriminative Localization and Visual Explanation
Authors	Zhiguang Wang, Jianbo Yang
Abstract	We proposed a deep learning method for interpretable diabetic retinopathy (DR) detection. The visual-interpretable feature of the proposed method is achieved by adding the regression activation map (RAM) after the global averaging pooling layer of the convolutional networks (CNN). With RAM, the proposed model can localize the discriminative regions of an retina image to show the specific region of interest in terms of its severity level. We believe this advantage of the proposed deep learning model is highly desired for DR detection because in practice, users are not only interested with high prediction performance, but also keen to understand the insights of DR detection and why the adopted learning model works. In the experiments conducted on a large scale of retina image dataset, we show that the proposed CNN model can achieve high performance on DR detection compared with the state-of-the-art while achieving the merits of providing the RAM to highlight the salient regions of the input image.
Tasks	Diabetic Retinopathy Detection
Published	2017-03-31
URL	https://arxiv.org/abs/1703.10757v3
PDF	https://arxiv.org/pdf/1703.10757v3.pdf
PWC	https://paperswithcode.com/paper/diabetic-retinopathy-detection-via-deep
Repo	https://github.com/cauchyturing/kaggle_diabetic_RAM
Framework	none

STRIPS Planning in Infinite Domains


Title	STRIPS Planning in Infinite Domains
Authors	Caelan Reed Garrett, Tomás Lozano-Pérez, Leslie Pack Kaelbling
Abstract	Many robotic planning applications involve continuous actions with highly non-linear constraints, which cannot be modeled using modern planners that construct a propositional representation. We introduce STRIPStream: an extension of the STRIPS language which can model these domains by supporting the specification of blackbox generators to handle complex constraints. The outputs of these generators interact with actions through possibly infinite streams of objects and static predicates. We provide two algorithms which both reduce STRIPStream problems to a sequence of finite-domain planning problems. The representation and algorithms are entirely domain independent. We demonstrate our framework on simple illustrative domains, and then on a high-dimensional, continuous robotic task and motion planning domain.
Tasks	Motion Planning
Published	2017-01-01
URL	http://arxiv.org/abs/1701.00287v2
PDF	http://arxiv.org/pdf/1701.00287v2.pdf
PWC	https://paperswithcode.com/paper/strips-planning-in-infinite-domains
Repo	https://github.com/jingxixu/pddlstream
Framework	none

FiLM: Visual Reasoning with a General Conditioning Layer


Title	FiLM: Visual Reasoning with a General Conditioning Layer
Authors	Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin, Aaron Courville
Abstract	We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, feature-wise affine transformation based on conditioning information. We show that FiLM layers are highly effective for visual reasoning - answering image-related questions which require a multi-step, high-level process - a task which has proven difficult for standard deep learning methods that do not explicitly model reasoning. Specifically, we show on visual reasoning tasks that FiLM layers 1) halve state-of-the-art error for the CLEVR benchmark, 2) modulate features in a coherent manner, 3) are robust to ablations and architectural modifications, and 4) generalize well to challenging, new data from few examples or even zero-shot.
Tasks	Visual Reasoning
Published	2017-09-22
URL	http://arxiv.org/abs/1709.07871v2
PDF	http://arxiv.org/pdf/1709.07871v2.pdf
PWC	https://paperswithcode.com/paper/film-visual-reasoning-with-a-general
Repo	https://github.com/ethanjperez/film
Framework	pytorch

PonyGE2: Grammatical Evolution in Python


Title	PonyGE2: Grammatical Evolution in Python
Authors	Michael Fenton, James McDermott, David Fagan, Stefan Forstenlechner, Michael O’Neill, Erik Hemberg
Abstract	Grammatical Evolution (GE) is a population-based evolutionary algorithm, where a formal grammar is used in the genotype to phenotype mapping process. PonyGE2 is an open source implementation of GE in Python, developed at UCD’s Natural Computing Research and Applications group. It is intended as an advertisement and a starting-point for those new to GE, a reference for students and researchers, a rapid-prototyping medium for our own experiments, and a Python workout. As well as providing the characteristic genotype to phenotype mapping of GE, a search algorithm engine is also provided. A number of sample problems and tutorials on how to use and adapt PonyGE2 have been developed.
Tasks
Published	2017-03-24
URL	http://arxiv.org/abs/1703.08535v2
PDF	http://arxiv.org/pdf/1703.08535v2.pdf
PWC	https://paperswithcode.com/paper/ponyge2-grammatical-evolution-in-python
Repo	https://github.com/abogdanova/SwarmGE
Framework	none