October 17, 2019

2821 words 14 mins read

Paper Group ANR 916

Learning Saliency Prediction From Sparse Fixation Pixel Map. Understanding Autoencoders with Information Theoretic Concepts. Dynamic-structured Semantic Propagation Network. On the Relative Expressiveness of Bayesian and Neural Networks. Multi-agent Deep Reinforcement Learning with Extremely Noisy Observations. FD-GAN: Face-demorphing generative ad …

Learning Saliency Prediction From Sparse Fixation Pixel Map


Title	Learning Saliency Prediction From Sparse Fixation Pixel Map
Authors	Shanghua Xiao
Abstract	Ground truth for saliency prediction datasets consists of two types of map data: fixation pixel map which records the human eye movements on sample images, and fixation blob map generated by performing gaussian blurring on the corresponding fixation pixel map. Current saliency approaches perform prediction by directly pixel-wise regressing the input image into saliency map with fixation blob as ground truth, yet learning saliency from fixation pixel map is not explored. In this work, we propose a first-of-its-kind approach of learning saliency prediction from sparse fixation pixel map, and a novel loss function for training from such sparse fixation. We utilize clustering to extract sparse fixation pixel from the raw fixation pixel map, and add a max-pooling transformation on the output to avoid false penalty between sparse outputs and labels caused by nearby but non-overlapping saliency pixels when calculating loss. This approach provides a novel perspective for achieving saliency prediction. We evaluate our approach over multiple benchmark datasets, and achieve competitive performance in terms of multiple metrics comparing with state-of-the-art saliency methods.
Tasks	Saliency Prediction
Published	2018-09-03
URL	http://arxiv.org/abs/1809.00644v1
PDF	http://arxiv.org/pdf/1809.00644v1.pdf
PWC	https://paperswithcode.com/paper/learning-saliency-prediction-from-sparse
Repo
Framework

Understanding Autoencoders with Information Theoretic Concepts


Title	Understanding Autoencoders with Information Theoretic Concepts
Authors	Shujian Yu, Jose C. Principe
Abstract	Despite their great success in practical applications, there is still a lack of theoretical and systematic methods to analyze deep neural networks. In this paper, we illustrate an advanced information theoretic methodology to understand the dynamics of learning and the design of autoencoders, a special type of deep learning architectures that resembles a communication channel. By generalizing the information plane to any cost function, and inspecting the roles and dynamics of different layers using layer-wise information quantities, we emphasize the role that mutual information plays in quantifying learning from data. We further suggest and also experimentally validate, for mean square error training, three fundamental properties regarding the layer-wise flow of information and intrinsic dimensionality of the bottleneck layer, using respectively the data processing inequality and the identification of a bifurcation point in the information plane that is controlled by the given data. Our observations have a direct impact on the optimal design of autoencoders, the design of alternative feedforward training methods, and even in the problem of generalization.
Tasks
Published	2018-03-30
URL	https://arxiv.org/abs/1804.00057v3
PDF	https://arxiv.org/pdf/1804.00057v3.pdf
PWC	https://paperswithcode.com/paper/understanding-autoencoders-with-information
Repo
Framework

Dynamic-structured Semantic Propagation Network


Title	Dynamic-structured Semantic Propagation Network
Authors	Xiaodan Liang, Hongfei Zhou, Eric Xing
Abstract	Semantic concept hierarchy is still under-explored for semantic segmentation due to the inefficiency and complicated optimization of incorporating structural inference into dense prediction. This lack of modeling semantic correlations also makes prior works must tune highly-specified models for each task due to the label discrepancy across datasets. It severely limits the generalization capability of segmentation models for open set concept vocabulary and annotation utilization. In this paper, we propose a Dynamic-Structured Semantic Propagation Network (DSSPN) that builds a semantic neuron graph by explicitly incorporating the semantic concept hierarchy into network construction. Each neuron represents the instantiated module for recognizing a specific type of entity such as a super-class (e.g. food) or a specific concept (e.g. pizza). During training, DSSPN performs the dynamic-structured neuron computation graph by only activating a sub-graph of neurons for each image in a principled way. A dense semantic-enhanced neural block is proposed to propagate the learned knowledge of all ancestor neurons into each fine-grained child neuron for feature evolving. Another merit of such semantic explainable structure is the ability of learning a unified model concurrently on diverse datasets by selectively activating different neuron sub-graphs for each annotation at each step. Extensive experiments on four public semantic segmentation datasets (i.e. ADE20K, COCO-Stuff, Cityscape and Mapillary) demonstrate the superiority of our DSSPN over state-of-the-art segmentation models. Moreoever, we demonstrate a universal segmentation model that is jointly trained on diverse datasets can surpass the performance of the common fine-tuning scheme for exploiting multiple domain knowledge.
Tasks	Semantic Segmentation
Published	2018-03-16
URL	http://arxiv.org/abs/1803.06067v1
PDF	http://arxiv.org/pdf/1803.06067v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-structured-semantic-propagation
Repo
Framework

On the Relative Expressiveness of Bayesian and Neural Networks


Title	On the Relative Expressiveness of Bayesian and Neural Networks
Authors	Arthur Choi, Ruocheng Wang, Adnan Darwiche
Abstract	A neural network computes a function. A central property of neural networks is that they are “universal approximators:” for a given continuous function, there exists a neural network that can approximate it arbitrarily well, given enough neurons (and some additional assumptions). In contrast, a Bayesian network is a model, but each of its queries can be viewed as computing a function. In this paper, we identify some key distinctions between the functions computed by neural networks and those by marginal Bayesian network queries, showing that the former are more expressive than the latter. Moreover, we propose a simple augmentation to Bayesian networks (a testing operator), which enables their marginal queries to become “universal approximators.”
Tasks
Published	2018-12-21
URL	http://arxiv.org/abs/1812.08957v1
PDF	http://arxiv.org/pdf/1812.08957v1.pdf
PWC	https://paperswithcode.com/paper/on-the-relative-expressiveness-of-bayesian
Repo
Framework

Multi-agent Deep Reinforcement Learning with Extremely Noisy Observations


Title	Multi-agent Deep Reinforcement Learning with Extremely Noisy Observations
Authors	Ozsel Kilinc, Giovanni Montana
Abstract	Multi-agent reinforcement learning systems aim to provide interacting agents with the ability to collaboratively learn and adapt to the behaviour of other agents. In many real-world applications, the agents can only acquire a partial view of the world. Here we consider a setting whereby most agents’ observations are also extremely noisy, hence only weakly correlated to the true state of the environment. Under these circumstances, learning an optimal policy becomes particularly challenging, even in the unrealistic case that an agent’s policy can be made conditional upon all other agents’ observations. To overcome these difficulties, we propose a multi-agent deep deterministic policy gradient algorithm enhanced by a communication medium (MADDPG-M), which implements a two-level, concurrent learning mechanism. An agent’s policy depends on its own private observations as well as those explicitly shared by others through a communication medium. At any given point in time, an agent must decide whether its private observations are sufficiently informative to be shared with others. However, our environments provide no explicit feedback informing an agent whether a communication action is beneficial, rather the communication policies must also be learned through experience concurrently to the main policies. Our experimental results demonstrate that the algorithm performs well in six highly non-stationary environments of progressively higher complexity, and offers substantial performance gains compared to the baselines.
Tasks	Multi-agent Reinforcement Learning
Published	2018-12-03
URL	http://arxiv.org/abs/1812.00922v1
PDF	http://arxiv.org/pdf/1812.00922v1.pdf
PWC	https://paperswithcode.com/paper/multi-agent-deep-reinforcement-learning-with
Repo
Framework

FD-GAN: Face-demorphing generative adversarial network for restoring accomplice’s facial image


Title	FD-GAN: Face-demorphing generative adversarial network for restoring accomplice’s facial image
Authors	Fei Peng, Le-bing Zhang, Min Long
Abstract	Face morphing attack is proved to be a serious threat to the existing face recognition systems. Although a few face morphing detection methods have been put forward, the face morphing accomplice’s facial restoration remains a challenging problem. In this paper, a face de-morphing generative adversarial network (FD-GAN) is proposed to restore the accomplice’s facial image. It utilizes a symmetric dual network architecture and two levels of restoration losses to separate the identity feature of the morphing accomplice. By exploiting the captured facial image (containing the criminal’s identity) from the face recognition system and the morphed image stored in the e-passport system (containing both criminal and accomplice’s identities), the FD-GAN can effectively restore the accomplice’s facial image. Experimental results and analysis demonstrate the effectiveness of the proposed scheme. It has great potential to be implemented for detecting the face morphing accomplice in a real identity verification scenario.
Tasks	Face Recognition
Published	2018-11-19
URL	http://arxiv.org/abs/1811.07665v2
PDF	http://arxiv.org/pdf/1811.07665v2.pdf
PWC	https://paperswithcode.com/paper/fd-gan-face-demorphing-generative-adversarial
Repo
Framework

Learning to Decode 7T-like MR Image Reconstruction from 3T MR Images


Title	Learning to Decode 7T-like MR Image Reconstruction from 3T MR Images
Authors	Aditya Sharma, Prabhjot Kaur, Aditya Nigam, Arnav Bhavsar
Abstract	Increasing demand for high field magnetic resonance (MR) scanner indicates the need for high-quality MR images for accurate medical diagnosis. However, cost constraints, instead, motivate a need for algorithms to enhance images from low field scanners. We propose an approach to process the given low field (3T) MR image slices to reconstruct the corresponding high field (7T-like) slices. Our framework involves a novel architecture of a merged convolutional autoencoder with a single encoder and multiple decoders. Specifically, we employ three decoders with random initializations, and the proposed training approach involves selection of a particular decoder in each weight-update iteration for back propagation. We demonstrate that the proposed algorithm outperforms some related contemporary methods in terms of performance and reconstruction time.
Tasks	Image Reconstruction, Medical Diagnosis
Published	2018-06-18
URL	http://arxiv.org/abs/1806.06886v1
PDF	http://arxiv.org/pdf/1806.06886v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-decode-7t-like-mr-image
Repo
Framework

Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions


Title	Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions
Authors	Konda Reddy Mopuri, Phani Krishna Uppala, R. Venkatesh Babu
Abstract	Deep learning models are susceptible to input specific noise, called adversarial perturbations. Moreover, there exist input-agnostic noise, called Universal Adversarial Perturbations (UAP) that can affect inference of the models over most input samples. Given a model, there exist broadly two approaches to craft UAPs: (i) data-driven: that require data, and (ii) data-free: that do not require data samples. Data-driven approaches require actual samples from the underlying data distribution and craft UAPs with high success (fooling) rate. However, data-free approaches craft UAPs without utilizing any data samples and therefore result in lesser success rates. In this paper, for data-free scenarios, we propose a novel approach that emulates the effect of data samples with class impressions in order to craft UAPs using data-driven objectives. Class impression for a given pair of category and model is a generic representation (in the input space) of the samples belonging to that category. Further, we present a neural network based generative model that utilizes the acquired class impressions to learn crafting UAPs. Experimental evaluation demonstrates that the learned generative model, (i) readily crafts UAPs via simple feed-forwarding through neural network layers, and (ii) achieves state-of-the-art success rates for data-free scenario and closer to that for data-driven setting without actually utilizing any data samples.
Tasks
Published	2018-08-03
URL	http://arxiv.org/abs/1808.01153v1
PDF	http://arxiv.org/pdf/1808.01153v1.pdf
PWC	https://paperswithcode.com/paper/ask-acquire-and-attack-data-free-uap
Repo
Framework

CLAUDETTE: an Automated Detector of Potentially Unfair Clauses in Online Terms of Service


Title	CLAUDETTE: an Automated Detector of Potentially Unfair Clauses in Online Terms of Service
Authors	Marco Lippi, Przemyslaw Palka, Giuseppe Contissa, Francesca Lagioia, Hans-Wolfgang Micklitz, Giovanni Sartor, Paolo Torroni
Abstract	Terms of service of on-line platforms too often contain clauses that are potentially unfair to the consumer. We present an experimental study where machine learning is employed to automatically detect such potentially unfair clauses. Results show that the proposed system could provide a valuable tool for lawyers and consumers alike.
Tasks
Published	2018-05-03
URL	http://arxiv.org/abs/1805.01217v2
PDF	http://arxiv.org/pdf/1805.01217v2.pdf
PWC	https://paperswithcode.com/paper/claudette-an-automated-detector-of
Repo
Framework

Can Neural Networks Understand Logical Entailment?


Title	Can Neural Networks Understand Logical Entailment?
Authors	Richard Evans, David Saxton, David Amos, Pushmeet Kohli, Edward Grefenstette
Abstract	We introduce a new dataset of logical entailments for the purpose of measuring models’ ability to capture and exploit the structure of logical expressions against an entailment prediction task. We use this task to compare a series of architectures which are ubiquitous in the sequence-processing literature, in addition to a new model class—PossibleWorldNets—which computes entailment as a “convolution over possible worlds”. Results show that convolutional networks present the wrong inductive bias for this class of problems relative to LSTM RNNs, tree-structured neural networks outperform LSTM RNNs due to their enhanced ability to exploit the syntax of logic, and PossibleWorldNets outperform all benchmarks.
Tasks
Published	2018-02-23
URL	http://arxiv.org/abs/1802.08535v1
PDF	http://arxiv.org/pdf/1802.08535v1.pdf
PWC	https://paperswithcode.com/paper/can-neural-networks-understand-logical
Repo
Framework

Semi-supervised dual graph regularized dictionary learning


Title	Semi-supervised dual graph regularized dictionary learning
Authors	Khanh-Hung Tran, Fred-Maurice Ngole-Mboula, Jean-Luc Starck
Abstract	In this paper, we propose a semi-supervised dictionary learning method that uses both the information in labelled and unlabelled data and jointly trains a linear classifier embedded on the sparse codes. The manifold structure of the data in the sparse code space is preserved using the same approach as the Locally Linear Embedding method (LLE). This enables one to enforce the predictive power of the unlabelled data sparse codes. We show that our approach provides significant improvements over other methods. The results can be further improved by training a simple nonlinear classifier as SVM on the sparse codes.
Tasks	Dictionary Learning
Published	2018-12-11
URL	http://arxiv.org/abs/1812.04456v1
PDF	http://arxiv.org/pdf/1812.04456v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-dual-graph-regularized
Repo
Framework

The Statistical Model for Ticker, an Adaptive Single-Switch Text-Entry Method for Visually Impaired Users


Title	The Statistical Model for Ticker, an Adaptive Single-Switch Text-Entry Method for Visually Impaired Users
Authors	Emli-Mari Nel, Per Ola Kristensson, David J. C. MacKay
Abstract	This paper presents the statistical model for Ticker [1], a novel probabilistic stereophonic single-switch text entry method for visually-impaired users with motor disabilities who rely on single-switch scanning systems to communicate. All terminology and notation are defined in [1].
Tasks
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07777v1
PDF	http://arxiv.org/pdf/1804.07777v1.pdf
PWC	https://paperswithcode.com/paper/the-statistical-model-for-ticker-an-adaptive
Repo
Framework

A Bayesian model for sparse graphs with flexible degree distribution and overlapping community structure


Title	A Bayesian model for sparse graphs with flexible degree distribution and overlapping community structure
Authors	Juho Lee, Lancelot F. James, Seungjin Choi, François Caron
Abstract	We consider a non-projective class of inhomogeneous random graph models with interpretable parameters and a number of interesting asymptotic properties. Using the results of Bollob'as et al. [2007], we show that i) the class of models is sparse and ii) depending on the choice of the parameters, the model is either scale-free, with power-law exponent greater than 2, or with an asymptotic degree distribution which is power-law with exponential cut-off. We propose an extension of the model that can accommodate an overlapping community structure. Scalable posterior inference can be performed due to the specific choice of the link probability. We present experiments on five different real-world networks with up to 100,000 nodes and edges, showing that the model can provide a good fit to the degree distribution and recovers well the latent community structure.
Tasks
Published	2018-10-03
URL	http://arxiv.org/abs/1810.01778v1
PDF	http://arxiv.org/pdf/1810.01778v1.pdf
PWC	https://paperswithcode.com/paper/a-bayesian-model-for-sparse-graphs-with
Repo
Framework

Improving Cytoarchitectonic Segmentation of Human Brain Areas with Self-supervised Siamese Networks


Title	Improving Cytoarchitectonic Segmentation of Human Brain Areas with Self-supervised Siamese Networks
Authors	Hannah Spitzer, Kai Kiwitz, Katrin Amunts, Stefan Harmeling, Timo Dickscheid
Abstract	Cytoarchitectonic parcellations of the human brain serve as anatomical references in multimodal atlas frameworks. They are based on analysis of cell-body stained histological sections and the identification of borders between brain areas. The de-facto standard involves a semi-automatic, reproducible border detection, but does not scale with high-throughput imaging in large series of sections at microscopical resolution. Automatic parcellation, however, is extremely challenging due to high variation in the data, and the need for a large field of view at microscopic resolution. The performance of a recently proposed Convolutional Neural Network model that addresses this problem especially suffers from the naturally limited amount of expert annotations for training. To circumvent this limitation, we propose to pre-train neural networks on a self-supervised auxiliary task, predicting the 3D distance between two patches sampled from the same brain. Compared to a random initialization, fine-tuning from these networks results in significantly better segmentations. We show that the self-supervised model has implicitly learned to distinguish several cortical brain areas – a strong indicator that the proposed auxiliary task is appropriate for cytoarchitectonic mapping.
Tasks
Published	2018-06-13
URL	http://arxiv.org/abs/1806.05104v1
PDF	http://arxiv.org/pdf/1806.05104v1.pdf
PWC	https://paperswithcode.com/paper/improving-cytoarchitectonic-segmentation-of
Repo
Framework

How Bad is Good enough: Noisy annotations for instrument pose estimation


Title	How Bad is Good enough: Noisy annotations for instrument pose estimation
Authors	David Kügler, Anirban Mukhopadhyay
Abstract	Though analysis of Medical Images by Deep Learning achieves unprecedented results across various applications, the effect of \emph{noisy training annotations} is rarely studied in a systematic manner. In Medical Image Analysis, most reports addressing this question concentrate on studying segmentation performance of deep learning classifiers. The absence of continuous ground truth annotations in these studies limits the value of conclusions for applications, where regression is the primary method of choice. In the application of surgical instrument pose estimation, where precision has a direct clinical impact on patient outcome, studying the effect of \emph{noisy annotations} on deep learning pose estimation techniques is of supreme importance. Real x-ray images are inadequate for this evaluation due to the unavailability of ground truth annotations. We circumvent this problem by generating synthetic radiographs, where the ground truth pose is known and therefore the pose estimation error made by the medical-expert can be estimated from experiments. Furthermore, this study shows the property of deep neural networks to learn dominant signals from noisy annotations with sufficient data in a regression setting.
Tasks	Pose Estimation
Published	2018-06-20
URL	http://arxiv.org/abs/1806.07836v1
PDF	http://arxiv.org/pdf/1806.07836v1.pdf
PWC	https://paperswithcode.com/paper/how-bad-is-good-enough-noisy-annotations-for
Repo
Framework