Paper Group ANR 260
SkelNetOn 2019: Dataset and Challenge on Deep Learning for Geometric Shape Understanding. TBQ($σ$): Improving Efficiency of Trace Utilization for Off-Policy Reinforcement Learning. 3D Dense Separated Convolution Module for Volumetric Image Analysis. CCMI : Classifier based Conditional Mutual Information Estimation. Towards a Quantum-Like Cognitive …
SkelNetOn 2019: Dataset and Challenge on Deep Learning for Geometric Shape Understanding
| Title | SkelNetOn 2019: Dataset and Challenge on Deep Learning for Geometric Shape Understanding |
| Authors | Ilke Demir, Camilla Hahn, Kathryn Leonard, Geraldine Morin, Dana Rahbani, Athina Panotopoulou, Amelie Fondevilla, Elena Balashova, Bastien Durix, Adam Kortylewski |
| Abstract | We present SkelNetOn 2019 Challenge and Deep Learning for Geometric Shape Understanding workshop to utilize existing and develop novel deep learning architectures for shape understanding. We observed that unlike traditional segmentation and detection tasks, geometry understanding is still a new area for deep learning techniques. SkelNetOn aims to bring together researchers from different domains to foster learning methods on global shape understanding tasks. We aim to improve and evaluate the state-of-the-art shape understanding approaches, and to serve as reference benchmarks for future research. Similar to other challenges in computer vision, SkelNetOn proposes three datasets and corresponding evaluation methodologies; all coherently bundled in three competitions with a dedicated workshop co-located with CVPR 2019 conference. In this paper, we describe and analyze characteristics of datasets, define the evaluation criteria of the public competitions, and provide baselines for each task. |
| Tasks | |
| Published | 2019-03-21 |
| URL | https://arxiv.org/abs/1903.09233v3 |
| https://arxiv.org/pdf/1903.09233v3.pdf | |
| PWC | https://paperswithcode.com/paper/skelneton-2019-dataset-and-challenge-on-deep |
| Repo | |
| Framework | |
TBQ($σ$): Improving Efficiency of Trace Utilization for Off-Policy Reinforcement Learning
| Title | TBQ($σ$): Improving Efficiency of Trace Utilization for Off-Policy Reinforcement Learning |
| Authors | Longxiang Shi, Shijian Li, Longbing Cao, Long Yang, Gang Pan |
| Abstract | Off-policy reinforcement learning with eligibility traces is challenging because of the discrepancy between target policy and behavior policy. One common approach is to measure the difference between two policies in a probabilistic way, such as importance sampling and tree-backup. However, existing off-policy learning methods based on probabilistic policy measurement are inefficient when utilizing traces under a greedy target policy, which is ineffective for control problems. The traces are cut immediately when a non-greedy action is taken, which may lose the advantage of eligibility traces and slow down the learning process. Alternatively, some non-probabilistic measurement methods such as General Q($\lambda$) and Naive Q($\lambda$) never cut traces, but face convergence problems in practice. To address the above issues, this paper introduces a new method named TBQ($\sigma$), which effectively unifies the tree-backup algorithm and Naive Q($\lambda$). By introducing a new parameter $\sigma$ to illustrate the \emph{degree} of utilizing traces, TBQ($\sigma$) creates an effective integration of TB($\lambda$) and Naive Q($\lambda$) and continuous role shift between them. The contraction property of TB($\sigma$) is theoretically analyzed for both policy evaluation and control settings. We also derive the online version of TBQ($\sigma$) and give the convergence proof. We empirically show that, for $\epsilon\in(0,1]$ in $\epsilon$-greedy policies, there exists some degree of utilizing traces for $\lambda\in[0,1]$, which can improve the efficiency in trace utilization for off-policy reinforcement learning, to both accelerate the learning process and improve the performance. |
| Tasks | |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.07237v1 |
| https://arxiv.org/pdf/1905.07237v1.pdf | |
| PWC | https://paperswithcode.com/paper/tbq-improving-efficiency-of-trace-utilization |
| Repo | |
| Framework | |
3D Dense Separated Convolution Module for Volumetric Image Analysis
| Title | 3D Dense Separated Convolution Module for Volumetric Image Analysis |
| Authors | Lei Qu, Changfeng Wu, Liang Zou |
| Abstract | With the thriving of deep learning, 3D Convolutional Neural Networks have become a popular choice in volumetric image analysis due to their impressive 3D contexts mining ability. However, the 3D convolutional kernels will introduce a significant increase in the amount of trainable parameters. Considering the training data is often limited in biomedical tasks, a tradeoff has to be made between model size and its representational power. To address this concern, in this paper, we propose a novel 3D Dense Separated Convolution (3D-DSC) module to replace the original 3D convolutional kernels. The 3D-DSC module is constructed by a series of densely connected 1D filters. The decomposition of 3D kernel into 1D filters reduces the risk of over-fitting by removing the redundancy of 3D kernels in a topologically constrained manner, while providing the infrastructure for deepening the network. By further introducing nonlinear layers and dense connections between 1D filters, the network’s representational power can be significantly improved while maintaining a compact architecture. We demonstrate the superiority of 3D-DSC on volumetric image classification and segmentation, which are two challenging tasks often encountered in biomedical image computing. |
| Tasks | Image Classification |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.08608v1 |
| https://arxiv.org/pdf/1905.08608v1.pdf | |
| PWC | https://paperswithcode.com/paper/190508608 |
| Repo | |
| Framework | |
CCMI : Classifier based Conditional Mutual Information Estimation
| Title | CCMI : Classifier based Conditional Mutual Information Estimation |
| Authors | Sudipto Mukherjee, Himanshu Asnani, Sreeram Kannan |
| Abstract | Conditional Mutual Information (CMI) is a measure of conditional dependence between random variables X and Y, given another random variable Z. It can be used to quantify conditional dependence among variables in many data-driven inference problems such as graphical models, causal learning, feature selection and time-series analysis. While k-nearest neighbor (kNN) based estimators as well as kernel-based methods have been widely used for CMI estimation, they suffer severely from the curse of dimensionality. In this paper, we leverage advances in classifiers and generative models to design methods for CMI estimation. Specifically, we introduce an estimator for KL-Divergence based on the likelihood ratio by training a classifier to distinguish the observed joint distribution from the product distribution. We then show how to construct several CMI estimators using this basic divergence estimator by drawing ideas from conditional generative models. We demonstrate that the estimates from our proposed approaches do not degrade in performance with increasing dimension and obtain significant improvement over the widely used KSG estimator. Finally, as an application of accurate CMI estimation, we use our best estimator for conditional independence testing and achieve superior performance than the state-of-the-art tester on both simulated and real data-sets. |
| Tasks | Feature Selection, Time Series, Time Series Analysis |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.01824v1 |
| https://arxiv.org/pdf/1906.01824v1.pdf | |
| PWC | https://paperswithcode.com/paper/ccmi-classifier-based-conditional-mutual |
| Repo | |
| Framework | |
Towards a Quantum-Like Cognitive Architecture for Decision-Making
| Title | Towards a Quantum-Like Cognitive Architecture for Decision-Making |
| Authors | Catarina Moreira, Lauren Fell, Shahram Dehdashti, Peter Bruza, Andreas Wichert |
| Abstract | We propose an alternative and unifying framework for decision-making that, by using quantum mechanics, provides more generalised cognitive and decision models with the ability to represent more information than classical models. This framework can accommodate and predict several cognitive biases reported in Lieder & Griffiths without heavy reliance on heuristics nor on assumptions of the computational resources of the mind. |
| Tasks | Decision Making |
| Published | 2019-05-11 |
| URL | https://arxiv.org/abs/1905.05176v1 |
| https://arxiv.org/pdf/1905.05176v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-a-quantum-like-cognitive-architecture |
| Repo | |
| Framework | |
Computational complexity of learning algebraic varieties
| Title | Computational complexity of learning algebraic varieties |
| Authors | Oliver Gäfvert |
| Abstract | We analyze the complexity of fitting a variety, coming from a class of varieties, to a configuration of points in $\Bbb C^n$. The complexity measure, called the algebraic complexity, computes the Euclidean Distance Degree (EDdegree) of a certain variety called the hypothesis variety as the number of points in the configuration increases. For the problem of fitting an $(n-1)$-sphere to a configuration of $m$ points in $\Bbb C^n$, we give a closed formula of the algebraic complexity of the hypothesis variety as $m$ grows for the case of $n=1$. For the case $n>1$ we conjecture a generalization of this formula supported by numerical experiments. |
| Tasks | |
| Published | 2019-10-08 |
| URL | https://arxiv.org/abs/1910.03305v2 |
| https://arxiv.org/pdf/1910.03305v2.pdf | |
| PWC | https://paperswithcode.com/paper/computational-complexity-in-algebraic |
| Repo | |
| Framework | |
Decomposing Textual Information For Style Transfer
| Title | Decomposing Textual Information For Style Transfer |
| Authors | Ivan P. Yamshchikov, Viacheslav Shibaev, Aleksander Nagaev, Jürgen Jost, Alexey Tikhonov |
| Abstract | This paper focuses on latent representations that could effectively decompose different aspects of textual information. Using a framework of style transfer for texts, we propose several empirical methods to assess information decomposition quality. We validate these methods with several state-of-the-art textual style transfer methods. Higher quality of information decomposition corresponds to higher performance in terms of bilingual evaluation understudy (BLEU) between output and human-written reformulations. |
| Tasks | Style Transfer |
| Published | 2019-09-26 |
| URL | https://arxiv.org/abs/1909.12928v1 |
| https://arxiv.org/pdf/1909.12928v1.pdf | |
| PWC | https://paperswithcode.com/paper/decomposing-textual-information-for-style |
| Repo | |
| Framework | |
Noisy, sparse, nonlinear: Navigating the Bermuda Triangle of physical inference with deep filtering
| Title | Noisy, sparse, nonlinear: Navigating the Bermuda Triangle of physical inference with deep filtering |
| Authors | Carl Poelking, Yehia Amar, Alexei Lapkin, Lucy Colwell |
| Abstract | Capturing the microscopic interactions that determine molecular reactivity poses a challenge across the physical sciences. Even a basic understanding of the underlying reaction mechanisms can substantially accelerate materials and compound design, including the development of new catalysts or drugs. Given the difficulties routinely faced by both experimental and theoretical investigations that aim to improve our mechanistic understanding of a reaction, recent advances have focused on data-driven routes to derive structure-property relationships directly from high-throughput screens. However, even these high-quality, high-volume data are noisy, sparse and biased – placing them in a regime where machine-learning is extremely challenging. Here we show that a statistical approach based on deep filtering of nonlinear feature networks results in physicochemical models that are more robust, transparent and generalize better than standard machine-learning architectures. Using diligent descriptor design and data post-processing, we exemplify the approach using both literature and fresh data on asymmetric catalytic hydrogenation, Palladium-catalyzed cross-coupling reactions, and drug-drug synergy. We illustrate how the sparse models uncovered by the filtering help us formulate physicochemical reaction ``pharmacophores’', investigate experimental bias and derive strategies for mechanism detection and classification. | |
| Tasks | |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1912.04345v1 |
| https://arxiv.org/pdf/1912.04345v1.pdf | |
| PWC | https://paperswithcode.com/paper/noisy-sparse-nonlinear-navigating-the-bermuda |
| Repo | |
| Framework | |
Large Scale Product Categorization using Structured and Unstructured Attributes
| Title | Large Scale Product Categorization using Structured and Unstructured Attributes |
| Authors | Abhinandan Krishnan, Abilash Amarthaluri |
| Abstract | Product categorization using text data for eCommerce is a very challenging extreme classification problem with several thousands of classes and several millions of products to classify. Even though multi-class text classification is a well studied problem both in academia and industry, most approaches either deal with treating product content as a single pile of text, or only consider a few product attributes for modelling purposes. Given the variety of products sold on popular eCommerce platforms, it is hard to consider all available product attributes as part of the modeling exercise, considering that products possess their own unique set of attributes based on category. In this paper, we compare hierarchical models to flat models and show that in specific cases, flat models perform better. We explore two Deep Learning based models that extract features from individual pieces of unstructured data from each product and then combine them to create a product signature. We also propose a novel idea of using structured attributes and their values together in an unstructured fashion along with convolutional filters such that the ordering of the attributes and the differing attributes by product categories no longer becomes a modelling challenge. This approach is also more robust to the presence of faulty product attribute names and values and can elegantly generalize to use both closed list and open list attributes. |
| Tasks | Product Categorization, Text Classification |
| Published | 2019-03-01 |
| URL | http://arxiv.org/abs/1903.04254v1 |
| http://arxiv.org/pdf/1903.04254v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-product-categorization-using |
| Repo | |
| Framework | |
A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching
| Title | A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching |
| Authors | Jiaqi Yang, Ke Xian, Peng Wang, Yanning Zhang |
| Abstract | Seeking consistent point-to-point correspondences between 3D rigid data (point clouds, meshes, or depth maps) is a fundamental problem in 3D computer vision. While a number of correspondence selection methods have been proposed in recent years, their advantages and shortcomings remain unclear regarding different applications and perturbations. To fill this gap, this paper gives a comprehensive evaluation of nine state-of-the-art 3D correspondence grouping methods. A good correspondence grouping algorithm is expected to retrieve as many as inliers from initial feature matches, giving a rise in both precision and recall as well as facilitating accurate transformation estimation. Toward this rule, we deploy experiments on three benchmarks with different application contexts including shape retrieval, 3D object recognition, and point cloud registration together with various perturbations such as noise, point density variation, clutter, occlusion, partial overlap, different scales of initial correspondences, and different combinations of keypoint detectors and descriptors. The rich variety of application scenarios and nuisances result in different spatial distributions and inlier ratios of initial feature correspondences, thus enabling a thorough evaluation. Based on the outcomes, we give a summary of the traits, merits, and demerits of evaluated approaches and indicate some potential future research directions. |
| Tasks | 3D Object Recognition, Object Recognition, Point Cloud Registration |
| Published | 2019-07-05 |
| URL | https://arxiv.org/abs/1907.02890v1 |
| https://arxiv.org/pdf/1907.02890v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-performance-evaluation-of-correspondence |
| Repo | |
| Framework | |
Driving Decision and Control for Autonomous Lane Change based on Deep Reinforcement Learning
| Title | Driving Decision and Control for Autonomous Lane Change based on Deep Reinforcement Learning |
| Authors | Tianyu Shi, Pin Wang, Xuxin Cheng, Ching-Yao Chan, Ding Huang |
| Abstract | We apply Deep Q-network (DQN) with the consideration of safety during the task for deciding whether to conduct the maneuver. Furthermore, we design two similar Deep Q learning frameworks with quadratic approximator for deciding how to select a comfortable gap and just follow the preceding vehicle. Finally, a polynomial lane change trajectory is generated and Pure Pursuit Control is implemented for path tracking. We demonstrate the effectiveness of this framework in simulation, from both the decision-making and control layers. The proposed architecture also has the potential to be extended to other autonomous driving scenarios. |
| Tasks | Autonomous Driving, Decision Making, Q-Learning |
| Published | 2019-04-23 |
| URL | https://arxiv.org/abs/1904.10171v2 |
| https://arxiv.org/pdf/1904.10171v2.pdf | |
| PWC | https://paperswithcode.com/paper/driving-decision-and-control-for-autonomous |
| Repo | |
| Framework | |
Pi-PE: A Pipeline for Pulmonary Embolism Detection using Sparsely Annotated 3D CT Images
| Title | Pi-PE: A Pipeline for Pulmonary Embolism Detection using Sparsely Annotated 3D CT Images |
| Authors | Deepta Rajan, David Beymer, Shafiqul Abedin, Ehsan Dehghan |
| Abstract | Pulmonary embolisms (PE) are known to be one of the leading causes for cardiac-related mortality. Due to inherent variabilities in how PE manifests and the cumbersome nature of manual diagnosis, there is growing interest in leveraging AI tools for detecting PE. In this paper, we build a two-stage detection pipeline that is accurate, computationally efficient, robust to variations in PE types and kernels used for CT reconstruction, and most importantly, does not require dense annotations. Given the challenges in acquiring expert annotations in large-scale datasets, our approach produces state-of-the-art results with very sparse emboli contours (at 10mm slice spacing), while using models with significantly lower number of parameters. We achieve AUC scores of 0.94 on the validation set and 0.85 on the test set of highly severe PEs. Using a large, real-world dataset characterized by complex PE types and patients from multiple hospitals, we present an elaborate empirical study and provide guidelines for designing highly generalizable pipelines. |
| Tasks | Pulmonary Embolism Detection |
| Published | 2019-10-05 |
| URL | https://arxiv.org/abs/1910.02175v3 |
| https://arxiv.org/pdf/1910.02175v3.pdf | |
| PWC | https://paperswithcode.com/paper/pi-pe-a-pipeline-for-pulmonary-embolism |
| Repo | |
| Framework | |
Unsupervised Minimax: Adversarial Curiosity, Generative Adversarial Networks, and Predictability Minimization
| Title | Unsupervised Minimax: Adversarial Curiosity, Generative Adversarial Networks, and Predictability Minimization |
| Authors | Juergen Schmidhuber |
| Abstract | I review unsupervised or self-supervised neural networks playing minimax games in game-theoretic settings. (i) Adversarial Curiosity (AC, 1990) is based on two such networks. One network learns to probabilistically generate outputs, the other learns to predict effects of the outputs. Each network minimizes the objective function maximized by the other. (ii) Generative Adversarial Networks (GANs, 2010-2014) are an application of AC where the effect of an output is 1 if the output is in a given set, and 0 otherwise. (iii) Predictability Minimization (PM, 1990s) models data distributions through a neural encoder that maximizes the objective function minimized by a neural predictor of the code components. We correct a previously published claim that PM is not based on a minimax game. |
| Tasks | |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04493v2 |
| https://arxiv.org/pdf/1906.04493v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-minimax-adversarial-curiosity |
| Repo | |
| Framework | |
Learning to Decipher Hate Symbols
| Title | Learning to Decipher Hate Symbols |
| Authors | Jing Qian, Mai ElSherief, Elizabeth Belding, William Yang Wang |
| Abstract | Existing computational models to understand hate speech typically frame the problem as a simple classification task, bypassing the understanding of hate symbols (e.g., 14 words, kigy) and their secret connotations. In this paper, we propose a novel task of deciphering hate symbols. To do this, we leverage the Urban Dictionary and collected a new, symbol-rich Twitter corpus of hate speech. We investigate neural network latent context models for deciphering hate symbols. More specifically, we study Sequence-to-Sequence models and show how they are able to crack the ciphers based on context. Furthermore, we propose a novel Variational Decipher and show how it can generalize better to unseen hate symbols in a more challenging testing setting. |
| Tasks | |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02418v1 |
| http://arxiv.org/pdf/1904.02418v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-decipher-hate-symbols |
| Repo | |
| Framework | |
Direct speech-to-speech translation with a sequence-to-sequence model
| Title | Direct speech-to-speech translation with a sequence-to-sequence model |
| Authors | Ye Jia, Ron J. Weiss, Fadi Biadsy, Wolfgang Macherey, Melvin Johnson, Zhifeng Chen, Yonghui Wu |
| Abstract | We present an attention-based sequence-to-sequence neural network which can directly translate speech from one language into speech in another language, without relying on an intermediate text representation. The network is trained end-to-end, learning to map speech spectrograms into target spectrograms in another language, corresponding to the translated content (in a different canonical voice). We further demonstrate the ability to synthesize translated speech using the voice of the source speaker. We conduct experiments on two Spanish-to-English speech translation datasets, and find that the proposed model slightly underperforms a baseline cascade of a direct speech-to-text translation model and a text-to-speech synthesis model, demonstrating the feasibility of the approach on this very challenging task. |
| Tasks | Speech Synthesis, Text-To-Speech Synthesis |
| Published | 2019-04-12 |
| URL | https://arxiv.org/abs/1904.06037v2 |
| https://arxiv.org/pdf/1904.06037v2.pdf | |
| PWC | https://paperswithcode.com/paper/direct-speech-to-speech-translation-with-a |
| Repo | |
| Framework | |
