April 2, 2020

3051 words 15 mins read

Paper Group ANR 191

Realizing Pixel-Level Semantic Learning in Complex Driving Scenes based on Only One Annotated Pixel per Class. Optimal Structured Principal Subspace Estimation: Metric Entropy and Minimax Rates. Weakly Supervised Semantic Segmentation of Satellite Images for Land Cover Mapping – Challenges and Opportunities. Solving Raven’s Progressive Matrices wi …

Realizing Pixel-Level Semantic Learning in Complex Driving Scenes based on Only One Annotated Pixel per Class


Title	Realizing Pixel-Level Semantic Learning in Complex Driving Scenes based on Only One Annotated Pixel per Class
Authors	Xi Li, Huimin Ma, Sheng Yi, Yanxian Chen
Abstract	Semantic segmentation tasks based on weakly supervised condition have been put forward to achieve a lightweight labeling process. For simple images that only include a few categories, researches based on image-level annotations have achieved acceptable performance. However, when facing complex scenes, since image contains a large amount of classes, it becomes difficult to learn visual appearance based on image tags. In this case, image-level annotations are not effective in providing information. Therefore, we set up a new task in which only one annotated pixel is provided for each category. Based on the more lightweight and informative condition, a three step process is built for pseudo labels generation, which progressively implement optimal feature representation for each category, image inference and context-location based refinement. In particular, since high-level semantics and low-level imaging feature have different discriminative ability for each class under driving scenes, we divide each category into “object” or “scene” and then provide different operations for the two types separately. Further, an alternate iterative structure is established to gradually improve segmentation performance, which combines CNN-based inter-image common semantic learning and imaging prior based intra-image modification process. Experiments on Cityscapes dataset demonstrate that the proposed method provides a feasible way to solve weakly supervised semantic segmentation task under complex driving scenes.
Tasks	Semantic Segmentation, Weakly-Supervised Semantic Segmentation
Published	2020-03-10
URL	https://arxiv.org/abs/2003.04671v1
PDF	https://arxiv.org/pdf/2003.04671v1.pdf
PWC	https://paperswithcode.com/paper/realizing-pixel-level-semantic-learning-in
Repo
Framework

Optimal Structured Principal Subspace Estimation: Metric Entropy and Minimax Rates


Title	Optimal Structured Principal Subspace Estimation: Metric Entropy and Minimax Rates
Authors	T. Tony Cai, Hongzhe Li, Rong Ma
Abstract	Driven by a wide range of applications, many principal subspace estimation problems have been studied individually under different structural constraints. This paper presents a unified framework for the statistical analysis of a general structured principal subspace estimation problem which includes as special cases non-negative PCA/SVD, sparse PCA/SVD, subspace constrained PCA/SVD, and spectral clustering. General minimax lower and upper bounds are established to characterize the interplay between the information-geometric complexity of the structural set for the principal subspaces, the signal-to-noise ratio (SNR), and the dimensionality. The results yield interesting phase transition phenomena concerning the rates of convergence as a function of the SNRs and the fundamental limit for consistent estimation. Applying the general results to the specific settings yields the minimax rates of convergence for those problems, including the previous unknown optimal rates for non-negative PCA/SVD, sparse SVD and subspace constrained PCA/SVD.
Tasks
Published	2020-02-18
URL	https://arxiv.org/abs/2002.07624v2
PDF	https://arxiv.org/pdf/2002.07624v2.pdf
PWC	https://paperswithcode.com/paper/optimal-structured-principal-subspace
Repo
Framework

Weakly Supervised Semantic Segmentation of Satellite Images for Land Cover Mapping – Challenges and Opportunities


Title	Weakly Supervised Semantic Segmentation of Satellite Images for Land Cover Mapping – Challenges and Opportunities
Authors	Michael Schmitt, Jonathan Prexl, Patrick Ebel, Lukas Liebel, Xiao Xiang Zhu
Abstract	Fully automatic large-scale land cover mapping belongs to the core challenges addressed by the remote sensing community. Usually, the basis of this task is formed by (supervised) machine learning models. However, in spite of recent growth in the availability of satellite observations, accurate training data remains comparably scarce. On the other hand, numerous global land cover products exist and can be accessed often free-of-charge. Unfortunately, these maps are typically of a much lower resolution than modern day satellite imagery. Besides, they always come with a significant amount of noise, as they cannot be considered ground truth, but are products of previous (semi-)automatic prediction tasks. Therefore, this paper seeks to make a case for the application of weakly supervised learning strategies to get the most out of available data sources and achieve progress in high-resolution large-scale land cover mapping. Challenges and opportunities are discussed based on the SEN12MS dataset, for which also some baseline results are shown. These baselines indicate that there is still a lot of potential for dedicated approaches designed to deal with remote sensing-specific forms of weak supervision.
Tasks	Semantic Segmentation, Weakly-Supervised Semantic Segmentation
Published	2020-02-19
URL	https://arxiv.org/abs/2002.08254v1
PDF	https://arxiv.org/pdf/2002.08254v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-semantic-segmentation-of-1
Repo
Framework

Solving Raven’s Progressive Matrices with Multi-Layer Relation Networks


Title	Solving Raven’s Progressive Matrices with Multi-Layer Relation Networks
Authors	Marius Jahrens, Thomas Martinetz
Abstract	Raven’s Progressive Matrices are a benchmark originally designed to test the cognitive abilities of humans. It has recently been adapted to test relational reasoning in machine learning systems. For this purpose the so-called Procedurally Generated Matrices dataset was set up, which is so far one of the most difficult relational reasoning benchmarks. Here we show that deep neural networks are capable of solving this benchmark, reaching an accuracy of 98.0 percent over the previous state-of-the-art of 62.6 percent by combining Wild Relation Networks with Multi-Layer Relation Networks and introducing Magnitude Encoding, an encoding scheme designed for late fusion architectures.
Tasks	Relational Reasoning
Published	2020-03-25
URL	https://arxiv.org/abs/2003.11608v1
PDF	https://arxiv.org/pdf/2003.11608v1.pdf
PWC	https://paperswithcode.com/paper/solving-raven-s-progressive-matrices-with
Repo
Framework

Analytical Equations based Prediction Approach for PM2.5 using Artificial Neural Network


Title	Analytical Equations based Prediction Approach for PM2.5 using Artificial Neural Network
Authors	Jalpa Shah, Biswajit Mishra
Abstract	Particulate matter pollution is one of the deadliest types of air pollution worldwide due to its significant impacts on the global environment and human health. Particulate Matter (PM2.5) is one of the important particulate pollutants to measure the Air Quality Index (AQI). The conventional instruments used by the air quality monitoring stations to monitor PM2.5 are costly, bulkier, time-consuming, and power-hungry. Furthermore, due to limited data availability and non-scalability, these stations cannot provide high spatial and temporal resolution in real-time. To overcome the disadvantages of existing methodology this article presents analytical equations based prediction approach for PM2.5 using an Artificial Neural Network (ANN). Since the derived analytical equations for the prediction can be computed using a Wireless Sensor Node (WSN) or low-cost processing tool, it demonstrates the usefulness of the proposed approach. Moreover, the study related to correlation among the PM2.5 and other pollutants is performed to select the appropriate predictors. The large authenticate data set of Central Pollution Control Board (CPCB) online station, India is used for the proposed approach. The RMSE and coefficient of determination (R2) obtained for the proposed prediction approach using eight predictors are 1.7973 ug/m3 and 0.9986 respectively. While the proposed approach results show RMSE of 7.5372 ug/m3 and R2 of 0.9708 using three predictors. Therefore, the results demonstrate that the proposed approach is one of the promising approaches for monitoring PM2.5 without power-hungry gas sensors and bulkier analyzers.
Tasks
Published	2020-02-26
URL	https://arxiv.org/abs/2002.11416v1
PDF	https://arxiv.org/pdf/2002.11416v1.pdf
PWC	https://paperswithcode.com/paper/analytical-equations-based-prediction
Repo
Framework

Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise


Title	Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise
Authors	Maxim Kaledin, Eric Moulines, Alexey Naumov, Vladislav Tadic, Hoi-To Wai
Abstract	Linear two-timescale stochastic approximation (SA) scheme is an important class of algorithms which has become popular in reinforcement learning (RL), particularly for the policy evaluation problem. Recently, a number of works have been devoted to establishing the finite time analysis of the scheme, especially under the Markovian (non-i.i.d.) noise settings that are ubiquitous in practice. In this paper, we provide a finite-time analysis for linear two timescale SA. Our bounds show that there is no discrepancy in the convergence rate between Markovian and martingale noise, only the constants are affected by the mixing time of the Markov chain. With an appropriate step size schedule, the transient term in the expected error bound is $o(1/k^c)$ and the steady-state term is ${\cal O}(1/k)$, where $c>1$ and $k$ is the iteration number. Furthermore, we present an asymptotic expansion of the expected error with a matching lower bound of $\Omega(1/k)$. A simple numerical experiment is presented to support our theory.
Tasks
Published	2020-02-04
URL	https://arxiv.org/abs/2002.01268v1
PDF	https://arxiv.org/pdf/2002.01268v1.pdf
PWC	https://paperswithcode.com/paper/finite-time-analysis-of-linear-two-timescale
Repo
Framework

Action Recognition and State Change Prediction in a Recipe Understanding Task Using a Lightweight Neural Network Model


Title	Action Recognition and State Change Prediction in a Recipe Understanding Task Using a Lightweight Neural Network Model
Authors	Qing Wan, Yoonsuck Choe
Abstract	Consider a natural language sentence describing a specific step in a food recipe. In such instructions, recognizing actions (such as press, bake, etc.) and the resulting changes in the state of the ingredients (shape molded, custard cooked, temperature hot, etc.) is a challenging task. One way to cope with this challenge is to explicitly model a simulator module that applies actions to entities and predicts the resulting outcome (Bosselut et al. 2018). However, such a model can be unnecessarily complex. In this paper, we propose a simplified neural network model that separates action recognition and state change prediction, while coupling the two through a novel loss function. This allows learning to indirectly influence each other. Our model, although simpler, achieves higher state change prediction performance (67% average accuracy for ours vs. 55% in (Bosselut et al. 2018)) and takes fewer samples to train (10K ours vs. 65K+ by (Bosselut et al. 2018)).
Tasks
Published	2020-01-23
URL	https://arxiv.org/abs/2001.08665v1
PDF	https://arxiv.org/pdf/2001.08665v1.pdf
PWC	https://paperswithcode.com/paper/action-recognition-and-state-change
Repo
Framework

Accelerating supply chains with Ant Colony Optimization across range of hardware solutions


Title	Accelerating supply chains with Ant Colony Optimization across range of hardware solutions
Authors	Ivars Dzalbs, Tatiana Kalganova
Abstract	Ant Colony algorithm has been applied to various optimization problems, however most of the previous work on scaling and parallelism focuses on Travelling Salesman Problems (TSPs). Although, useful for benchmarks and new idea comparison, the algorithmic dynamics does not always transfer to complex real-life problems, where additional meta-data is required during solution construction. This paper looks at real-life outbound supply chain problem using Ant Colony Optimization (ACO) and its scaling dynamics with two parallel ACO architectures - Independent Ant Colonies (IAC) and Parallel Ants (PA). Results showed that PA was able to reach a higher solution quality in fewer iterations as the number of parallel instances increased. Furthermore, speed performance was measured across three different hardware solutions - 16 core CPU, 68 core Xeon Phi and up to 4 Geforce GPUs. State of the art, ACO vectorization techniques such as SS-Roulette were implemented using C++ and CUDA. Although excellent for TSP, it was concluded that for the given supply chain problem GPUs are not suitable due to meta-data access footprint required. Furthermore, compared to their sequential counterpart, vectorized CPU AVX2 implementation achieved 25.4x speedup on CPU while Xeon Phi with its AVX512 instruction set reached 148x on PA with Vectorized (PAwV). PAwV is therefore able to scale at least up to 1024 parallel instances on the supply chain network problem solved.
Tasks
Published	2020-01-22
URL	https://arxiv.org/abs/2001.08102v1
PDF	https://arxiv.org/pdf/2001.08102v1.pdf
PWC	https://paperswithcode.com/paper/accelerating-supply-chains-with-ant-colony
Repo
Framework

Rigorous State Evolution Analysis for Approximate Message Passing with Side Information


Title	Rigorous State Evolution Analysis for Approximate Message Passing with Side Information
Authors	Hangjin Liu, Cynthia Rush, Dror Baron
Abstract	A common goal in many research areas is to reconstruct an unknown signal x from noisy linear measurements. Approximate message passing (AMP) is a class of low-complexity algorithms that can be used for efficiently solving such high-dimensional regression tasks. Often, it is the case that side information (SI) is available during reconstruction. For this reason, a novel algorithmic framework that incorporates SI into AMP, referred to as approximate message passing with side information (AMP-SI), has been recently introduced. In this work, we provide rigorous performance guarantees for AMP-SI when there are statistical dependencies between the signal and SI pairs and the entries of the measurement matrix are independent and identically distributed Gaussian. The AMP-SI performance is shown to be provably tracked by a scalar iteration referred to as state evolution. Moreover, we provide numerical examples that demonstrate empirically that the SE can predict the AMP-SI mean square error accurately.
Tasks
Published	2020-03-25
URL	https://arxiv.org/abs/2003.11964v1
PDF	https://arxiv.org/pdf/2003.11964v1.pdf
PWC	https://paperswithcode.com/paper/rigorous-state-evolution-analysis-for
Repo
Framework

Learning Structured Distributions From Untrusted Batches: Faster and Simpler


Title	Learning Structured Distributions From Untrusted Batches: Faster and Simpler
Authors	Sitan Chen, Jerry Li, Ankur Moitra
Abstract	We revisit the problem of learning from untrusted batches introduced by Qiao and Valiant [QV17]. Recently, Jain and Orlitsky [JO19] gave a simple semidefinite programming approach based on the cut-norm that achieves essentially information-theoretically optimal error in polynomial time. Concurrently, Chen et al. [CLM19] considered a variant of the problem where $\mu$ is assumed to be structured, e.g. log-concave, monotone hazard rate, $t$-modal, etc. In this case, it is possible to achieve the same error with sample complexity sublinear in $n$, and they exhibited a quasi-polynomial time algorithm for doing so using Haar wavelets. In this paper, we find an appealing way to synthesize the techniques of [JO19] and [CLM19] to give the best of both worlds: an algorithm which runs in polynomial time and can exploit structure in the underlying distribution to achieve sublinear sample complexity. Along the way, we simplify the approach of [JO19] by avoiding the need for SDP rounding and giving a more direct interpretation of it through the lens of soft filtering, a powerful recent technique in high-dimensional robust estimation.
Tasks
Published	2020-02-24
URL	https://arxiv.org/abs/2002.10435v1
PDF	https://arxiv.org/pdf/2002.10435v1.pdf
PWC	https://paperswithcode.com/paper/learning-structured-distributions-from
Repo
Framework

Quantum-like Structure in Multidimensional Relevance Judgements


Title	Quantum-like Structure in Multidimensional Relevance Judgements
Authors	Sagar Uprety, Prayag Tiwari, Shahram Dehdashti, Lauren Fell, Dawei Song, Peter Bruza, Massimo Melucci
Abstract	A large number of studies in cognitive science have revealed that probabilistic outcomes of certain human decisions do not agree with the axioms of classical probability theory. The field of Quantum Cognition provides an alternative probabilistic model to explain such paradoxical findings. It posits that cognitive systems have an underlying quantum-like structure, especially in decision-making under uncertainty. In this paper, we hypothesise that relevance judgement, being a multidimensional, cognitive concept, can be used to probe the quantum-like structure for modelling users’ cognitive states in information seeking. Extending from an experiment protocol inspired by the Stern-Gerlach experiment in Quantum Physics, we design a crowd-sourced user study to show violation of the Kolmogorovian probability axioms as a proof of the quantum-like structure, and provide a comparison between a quantum probabilistic model and a Bayesian model for predictions of relevance.
Tasks	Decision Making, Decision Making Under Uncertainty
Published	2020-01-20
URL	https://arxiv.org/abs/2001.07075v1
PDF	https://arxiv.org/pdf/2001.07075v1.pdf
PWC	https://paperswithcode.com/paper/quantum-like-structure-in-multidimensional
Repo
Framework

GIM: Gaussian Isolation Machines


Title	GIM: Gaussian Isolation Machines
Authors	Guy Amit, Ishai Rosenberg, Moshe Levy, Ron Bitton, Asaf Shabtai, Yuval Elovici
Abstract	In many cases, neural network classifiers are likely to be exposed to input data that is outside of their training distribution data. Samples from outside the distribution may be classified as an existing class with high probability by softmax-based classifiers; such incorrect classifications affect the performance of the classifiers and the applications/systems that depend on them. Previous research aimed at distinguishing training distribution data from out-of-distribution data (OOD) has proposed detectors that are external to the classification method. We present Gaussian isolation machine (GIM), a novel hybrid (generative-discriminative) classifier aimed at solving the problem arising when OOD data is encountered. The GIM is based on a neural network and utilizes a new loss function that imposes a distribution on each of the trained classes in the neural network’s output space, which can be approximated by a Gaussian. The proposed GIM’s novelty lies in its discriminative performance and generative capabilities, a combination of characteristics not usually seen in a single classifier. The GIM achieves state-of-the-art classification results on image recognition and sentiment analysis benchmarking datasets and can also deal with OOD inputs.
Tasks	Sentiment Analysis
Published	2020-02-06
URL	https://arxiv.org/abs/2002.02176v2
PDF	https://arxiv.org/pdf/2002.02176v2.pdf
PWC	https://paperswithcode.com/paper/neural-network-representation-control
Repo
Framework

Instant recovery of shape from spectrum via latent space connections


Title	Instant recovery of shape from spectrum via latent space connections
Authors	Riccardo Marin, Arianna Rampini, Umberto Castellani, Emanuele Rodolà, Maks Ovsjanikov, Simone Melzi
Abstract	We introduce the first learning-based method for recovering shapes from Laplacian spectra. Given an auto-encoder, our model takes the form of a cycle-consistent module to map latent vectors to sequences of eigenvalues. This module provides an efficient and effective linkage between spectrum and geometry of a given shape. Our data-driven approach replaces the need for ad-hoc regularizers required by prior methods, while providing more accurate results at a fraction of the computational cost. Our learning model applies without modifications across different dimensions (2D and 3D shapes alike), representations (meshes, contours and point clouds), as well as across different shape classes, and admits arbitrary resolution of the input spectrum without affecting complexity. The increased flexibility allows us to provide a proxy to differentiable eigendecomposition and to address notoriously difficult tasks in 3D vision and geometry processing within a unified framework, including shape generation from spectrum, mesh super-resolution, shape exploration, style transfer, spectrum estimation from point clouds, segmentation transfer and point-to-point matching.
Tasks	Style Transfer, Super-Resolution
Published	2020-03-14
URL	https://arxiv.org/abs/2003.06523v2
PDF	https://arxiv.org/pdf/2003.06523v2.pdf
PWC	https://paperswithcode.com/paper/instant-recovery-of-shape-from-spectrum-via
Repo
Framework

ML4H Abstract Track 2019


Title	ML4H Abstract Track 2019
Authors	Matthew B. A. McDermott, Emily Alsentzer, Sam Finlayson, Michael Oberst, Fabian Falck, Tristan Naumann, Brett K. Beaulieu-Jones, Adrian V. Dalca
Abstract	A collection of the accepted abstracts for the Machine Learning for Health (ML4H) workshop at NeurIPS 2019. This index is not complete, as some accepted abstracts chose to opt-out of inclusion.
Tasks
Published	2020-02-05
URL	https://arxiv.org/abs/2002.01584v1
PDF	https://arxiv.org/pdf/2002.01584v1.pdf
PWC	https://paperswithcode.com/paper/ml4h-abstract-track-2019
Repo
Framework

NLocalSAT: Boosting Local Search with Solution Prediction


Title	NLocalSAT: Boosting Local Search with Solution Prediction
Authors	Wenjie Zhang, Zeyu Sun, Qihao Zhu, Ge Li, Shaowei Cai, Yingfei Xiong, Lu Zhang
Abstract	The boolean satisfiability problem is a famous NP-complete problem in computer science. An effective way for this problem is the stochastic local search (SLS). However, in this method, the initialization is assigned in a random manner, which impacts the effectiveness of SLS solvers. To address this problem, we propose NLocalSAT. NLocalSAT combines SLS with a solution prediction model, which boosts SLS by changing initialization assignments with a neural network. We evaluated NLocalSAT on five SLS solvers (CCAnr, Sparrow, CPSparrow, YalSAT, and probSAT) with problems in the random track of SAT Competition 2018. The experimental results show that solvers with NLocalSAT achieve 27%~62% improvement over the original SLS solvers.
Tasks
Published	2020-01-26
URL	https://arxiv.org/abs/2001.09398v1
PDF	https://arxiv.org/pdf/2001.09398v1.pdf
PWC	https://paperswithcode.com/paper/nlocalsat-boosting-local-search-with-solution
Repo
Framework