Paper Group ANR 410
Learning a Directional Soft Lane Affordance Model for Road Scenes Using Self-Supervision. OpenHI2 – Open source histopathological image platform. Balance Between Efficient and Effective Learning: Dense2Sparse Reward Shaping for Robot Manipulation with Environment Uncertainty. CounterExample Guided Neural Synthesis. Detection of Thin Boundaries bet …
Learning a Directional Soft Lane Affordance Model for Road Scenes Using Self-Supervision
| Title | Learning a Directional Soft Lane Affordance Model for Road Scenes Using Self-Supervision |
| Authors | Robin Karlsson, Erik Sjoberg |
| Abstract | Humans navigate complex environments in an organized yet flexible manner, adapting to the context and implicit social rules. Understanding these naturally learned patterns of behavior is essential for applications such as autonomous vehicles. However, algorithmically defining these implicit rules of human behavior remains difficult. This work proposes a novel self-supervised method for training a probabilistic network model to estimate the regions humans are most likely to drive in as well as a multimodal representation of the inferred direction of travel at each point. The model is trained on individual human trajectories conditioned on a representation of the driving environment. The model is shown to successfully generalize to new road scenes, demonstrating potential for real-world application as a prior for socially acceptable driving behavior in challenging or ambiguous scenarios which are poorly handled by explicit traffic rules. |
| Tasks | Autonomous Vehicles |
| Published | 2020-02-17 |
| URL | https://arxiv.org/abs/2002.11477v1 |
| https://arxiv.org/pdf/2002.11477v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-directional-soft-lane-affordance |
| Repo | |
| Framework | |
OpenHI2 – Open source histopathological image platform
| Title | OpenHI2 – Open source histopathological image platform |
| Authors | Pargorn Puttapirat, Haichuan Zhang, Jingyi Deng, Yuxin Dong, Jiangbo Shi, Hongyu He, Zeyu Gao, Chunbao Wang, Xiangrong Zhang, Chen Li |
| Abstract | Transition from conventional to digital pathology requires a new category of biomedical informatic infrastructure which could facilitate delicate pathological routine. Pathological diagnoses are sensitive to many external factors and is known to be subjective. Only systems that can meet strict requirements in pathology would be able to run along pathological routines and eventually digitized the study area, and the developed platform should comply with existing pathological routines and international standards. Currently, there are a number of available software tools which can perform histopathological tasks including virtual slide viewing, annotating, and basic image analysis, however, none of them can serve as a digital platform for pathology. Here we describe OpenHI2, an enhanced version Open Histopathological Image platform which is capable of supporting all basic pathological tasks and file formats; ready to be deployed in medical institutions on a standard server environment or cloud computing infrastructure. In this paper, we also describe the development decisions for the platform and propose solutions to overcome technical challenges so that OpenHI2 could be used as a platform for histopathological images. Further addition can be made to the platform since each component is modularized and fully documented. OpenHI2 is free, open-source, and available at https://gitlab.com/BioAI/OpenHI. |
| Tasks | |
| Published | 2020-01-15 |
| URL | https://arxiv.org/abs/2001.05158v1 |
| https://arxiv.org/pdf/2001.05158v1.pdf | |
| PWC | https://paperswithcode.com/paper/openhi2-open-source-histopathological-image |
| Repo | |
| Framework | |
Balance Between Efficient and Effective Learning: Dense2Sparse Reward Shaping for Robot Manipulation with Environment Uncertainty
| Title | Balance Between Efficient and Effective Learning: Dense2Sparse Reward Shaping for Robot Manipulation with Environment Uncertainty |
| Authors | Yongle Luo, Kun Dong, Lili Zhao, Zhiyong Sun, Chao Zhou, Bo Song |
| Abstract | Efficient and effective learning is one of the ultimate goals of the deep reinforcement learning (DRL), although the compromise has been made in most of the time, especially for the application of robot manipulations. Learning is always expensive for robot manipulation tasks and the learning effectiveness could be affected by the system uncertainty. In order to solve above challenges, in this study, we proposed a simple but powerful reward shaping method, namely Dense2Sparse. It combines the advantage of fast convergence of dense reward and the noise isolation of the sparse reward, to achieve a balance between learning efficiency and effectiveness, which makes it suitable for robot manipulation tasks. We evaluated our Dense2Sparse method with a series of ablation experiments using the state representation model with system uncertainty. The experiment results show that the Dense2Sparse method obtained higher expected reward compared with the ones using standalone dense reward or sparse reward, and it also has a superior tolerance of system uncertainty. |
| Tasks | |
| Published | 2020-03-05 |
| URL | https://arxiv.org/abs/2003.02740v1 |
| https://arxiv.org/pdf/2003.02740v1.pdf | |
| PWC | https://paperswithcode.com/paper/balance-between-efficient-and-effective |
| Repo | |
| Framework | |
CounterExample Guided Neural Synthesis
| Title | CounterExample Guided Neural Synthesis |
| Authors | Elizabeth Polgreen, Ralph Abboud, Daniel Kroening |
| Abstract | Program synthesis is the generation of a program from a specification. Correct synthesis is difficult, and methods that provide formal guarantees suffer from scalability issues. On the other hand, neural networks are able to generate programs from examples quickly but are unable to guarantee that the program they output actually meets the logical specification. In this work we combine neural networks with formal reasoning: using the latter to convert a logical specification into a sequence of examples that guides the neural network towards a correct solution, and to guarantee that any solution returned satisfies the formal specification. We apply our technique to synthesising loop invariants and compare the performance to existing solvers that use SMT and existing techniques that use neural networks. Our results show that the formal reasoning based guidance improves the performance of the neural network substantially, nearly doubling the number of benchmarks it can solve. |
| Tasks | Program Synthesis |
| Published | 2020-01-25 |
| URL | https://arxiv.org/abs/2001.09245v1 |
| https://arxiv.org/pdf/2001.09245v1.pdf | |
| PWC | https://paperswithcode.com/paper/counterexample-guided-neural-synthesis |
| Repo | |
| Framework | |
Detection of Thin Boundaries between Different Types of Anomalies in Outlier Detection using Enhanced Neural Networks
| Title | Detection of Thin Boundaries between Different Types of Anomalies in Outlier Detection using Enhanced Neural Networks |
| Authors | Rasoul Kiani, Amin Keshavarzi, Mahdi Bohlouli |
| Abstract | Outlier detection has received special attention in various fields, mainly for those dealing with machine learning and artificial intelligence. As strong outliers, anomalies are divided into the point, contextual and collective outliers. The most important challenges in outlier detection include the thin boundary between the remote points and natural area, the tendency of new data and noise to mimic the real data, unlabelled datasets and different definitions for outliers in different applications. Considering the stated challenges, we defined new types of anomalies called Collective Normal Anomaly and Collective Point Anomaly in order to improve a much better detection of the thin boundary between different types of anomalies. Basic domain-independent methods are introduced to detect these defined anomalies in both unsupervised and supervised datasets. The Multi-Layer Perceptron Neural Network is enhanced using the Genetic Algorithm to detect newly defined anomalies with higher precision so as to ensure a test error less than that calculated for the conventional Multi-Layer Perceptron Neural Network. Experimental results on benchmark datasets indicated reduced error of anomaly detection process in comparison to baselines. |
| Tasks | Anomaly Detection, Outlier Detection |
| Published | 2020-01-24 |
| URL | https://arxiv.org/abs/2001.09209v1 |
| https://arxiv.org/pdf/2001.09209v1.pdf | |
| PWC | https://paperswithcode.com/paper/detection-of-thin-boundaries-between |
| Repo | |
| Framework | |
Deep Learning in Memristive Nanowire Networks
| Title | Deep Learning in Memristive Nanowire Networks |
| Authors | Jack D. Kendall, Ross D. Pantone, Juan C. Nino |
| Abstract | Analog crossbar architectures for accelerating neural network training and inference have made tremendous progress over the past several years. These architectures are ideal for dense layers with fewer than roughly a thousand neurons. However, for large sparse layers, crossbar architectures are highly inefficient. A new hardware architecture, dubbed the MN3 (Memristive Nanowire Neural Network), was recently described as an efficient architecture for simulating very wide, sparse neural network layers, on the order of millions of neurons per layer. The MN3 utilizes a high-density memristive nanowire mesh to efficiently connect large numbers of silicon neurons with modifiable weights. Here, in order to explore the MN3’s ability to function as a deep neural network, we describe one algorithm for training deep MN3 models and benchmark simulations of the architecture on two deep learning tasks. We utilize a simple piecewise linear memristor model, since we seek to demonstrate that training is, in principle, possible for randomized nanowire architectures. In future work, we intend on utilizing more realistic memristor models, and we will adapt the presented algorithm appropriately. We show that the MN3 is capable of performing composition, gradient propagation, and weight updates, which together allow it to function as a deep neural network. We show that a simulated multilayer perceptron (MLP), built from MN3 networks, can obtain a 1.61% error rate on the popular MNIST dataset, comparable to equivalently sized software-based network. This work represents, to the authors’ knowledge, the first randomized nanowire architecture capable of reproducing the backpropagation algorithm. |
| Tasks | |
| Published | 2020-03-03 |
| URL | https://arxiv.org/abs/2003.02642v1 |
| https://arxiv.org/pdf/2003.02642v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-in-memristive-nanowire-networks |
| Repo | |
| Framework | |
Recognizing Affiliation: Using Behavioural Traces to Predict the Quality of Social Interactions in Online Games
| Title | Recognizing Affiliation: Using Behavioural Traces to Predict the Quality of Social Interactions in Online Games |
| Authors | Julian Frommel, Valentin Sagl, Ansgar E. Depping, Colby Johanson, Matthew K. Miller, Regan L. Mandryk |
| Abstract | Online social interactions in multiplayer games can be supportive and positive or toxic and harmful; however, few methods can easily assess interpersonal interaction quality in games. We use behavioural traces to predict affiliation between dyadic strangers, facilitated through their social interactions in an online gaming setting. We collected audio, video, in-game, and self-report data from 23 dyads, extracted 75 features, trained Random Forest and Support Vector Machine models, and evaluated their performance predicting binary (high/low) as well as continuous affiliation toward a partner. The models can predict both binary and continuous affiliation with up to 79.1% accuracy (F1) and 20.1% explained variance (R2) on unseen data, with features based on verbal communication demonstrating the highest potential. Our findings can inform the design of multiplayer games and game communities, and guide the development of systems for matchmaking and mitigating toxic behaviour in online games. |
| Tasks | |
| Published | 2020-03-06 |
| URL | https://arxiv.org/abs/2003.03438v1 |
| https://arxiv.org/pdf/2003.03438v1.pdf | |
| PWC | https://paperswithcode.com/paper/recognizing-affiliation-using-behavioural |
| Repo | |
| Framework | |
Learning credit assignment
| Title | Learning credit assignment |
| Authors | Chan Li, Haiping Huang |
| Abstract | Deep learning has achieved impressive prediction accuracies in a variety of scientific and industrial domains. However, the nested non-linear feature of deep learning makes the learning highly non-transparent, i.e., it is still unknown how the learning coordinates a huge number of parameters to achieve a decision making. To explain this hierarchical credit assignment, we propose a mean-field learning model by assuming that an ensemble of sub-networks, rather than a single network, are trained for a classification task. Surprisingly, our model reveals that apart from some deterministic synaptic weights connecting two neurons at neighboring layers, there exist a large number of connections that can be absent, and other connections can allow for a broad distribution of their weight values. Therefore, synaptic connections can be classified into three categories: very important ones, unimportant ones, and those of variability that may partially encode nuisance factors. Therefore, our model learns the credit assignment leading to the decision, and predicts an ensemble of sub-networks that can accomplish the same task, thereby providing insights toward understanding the macroscopic behavior of deep learning through the lens of distinct roles of synaptic weights. |
| Tasks | Decision Making |
| Published | 2020-01-10 |
| URL | https://arxiv.org/abs/2001.03354v1 |
| https://arxiv.org/pdf/2001.03354v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-credit-assignment |
| Repo | |
| Framework | |
Unsupervised Cross-Modal Audio Representation Learning from Unstructured Multilingual Text
| Title | Unsupervised Cross-Modal Audio Representation Learning from Unstructured Multilingual Text |
| Authors | Alexander Schindler, Sergiu Gordea, Peter Knees |
| Abstract | We present an approach to unsupervised audio representation learning. Based on a triplet neural network architecture, we harnesses semantically related cross-modal information to estimate audio track-relatedness. By applying Latent Semantic Indexing (LSI) we embed corresponding textual information into a latent vector space from which we derive track relatedness for online triplet selection. This LSI topic modelling facilitates fine-grained selection of similar and dissimilar audio-track pairs to learn the audio representation using a Convolution Recurrent Neural Network (CRNN). By this we directly project the semantic context of the unstructured text modality onto the learned representation space of the audio modality without deriving structured ground-truth annotations from it. We evaluate our approach on the Europeana Sounds collection and show how to improve search in digital audio libraries by harnessing the multilingual meta-data provided by numerous European digital libraries. We show that our approach is invariant to the variety of annotation styles as well as to the different languages of this collection. The learned representations perform comparable to the baseline of handcrafted features, respectively exceeding this baseline in similarity retrieval precision at higher cut-offs with only 15% of the baseline’s feature vector length. |
| Tasks | Representation Learning |
| Published | 2020-03-27 |
| URL | https://arxiv.org/abs/2003.12265v1 |
| https://arxiv.org/pdf/2003.12265v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-cross-modal-audio-representation |
| Repo | |
| Framework | |
Multi-View Optimization of Local Feature Geometry
| Title | Multi-View Optimization of Local Feature Geometry |
| Authors | Mihai Dusmanu, Johannes L. Schönberger, Marc Pollefeys |
| Abstract | In this work, we address the problem of refining the geometry of local image features from multiple views without known scene or camera geometry. Current approaches to local feature detection are inherently limited in their keypoint localization accuracy because they only operate on a single view. This limitation has a negative impact on downstream tasks such as Structure-from-Motion, where inaccurate keypoints lead to large errors in triangulation and camera localization. Our proposed method naturally complements the traditional feature extraction and matching paradigm. We first estimate local geometric transformations between tentative matches and then optimize the keypoint locations over multiple views jointly according to a non-linear least squares formulation. Throughout a variety of experiments, we show that our method consistently improves the triangulation and camera localization performance for both hand-crafted and learned local features. |
| Tasks | Camera Localization |
| Published | 2020-03-18 |
| URL | https://arxiv.org/abs/2003.08348v1 |
| https://arxiv.org/pdf/2003.08348v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-optimization-of-local-feature |
| Repo | |
| Framework | |
Interpreting Machine Learning Malware Detectors Which Leverage N-gram Analysis
| Title | Interpreting Machine Learning Malware Detectors Which Leverage N-gram Analysis |
| Authors | William Briguglio, Sherif Saad |
| Abstract | In cyberattack detection and prevention systems, cybersecurity analysts always prefer solutions that are as interpretable and understandable as rule-based or signature-based detection. This is because of the need to tune and optimize these solutions to mitigate and control the effect of false positives and false negatives. Interpreting machine learning models is a new and open challenge. However, it is expected that an interpretable machine learning solution will be domain-specific. For instance, interpretable solutions for machine learning models in healthcare are different than solutions in malware detection. This is because the models are complex, and most of them work as a black-box. Recently, the increased ability for malware authors to bypass antimalware systems has forced security specialists to look to machine learning for creating robust detection systems. If these systems are to be relied on in the industry, then, among other challenges, they must also explain their predictions. The objective of this paper is to evaluate the current state-of-the-art ML models interpretability techniques when applied to ML-based malware detectors. We demonstrate interpretability techniques in practice and evaluate the effectiveness of existing interpretability techniques in the malware analysis domain. |
| Tasks | Interpretable Machine Learning, Malware Detection |
| Published | 2020-01-27 |
| URL | https://arxiv.org/abs/2001.10916v1 |
| https://arxiv.org/pdf/2001.10916v1.pdf | |
| PWC | https://paperswithcode.com/paper/interpreting-machine-learning-malware-1 |
| Repo | |
| Framework | |
Permute to Train: A New Dimension to Training Deep Neural Networks
| Title | Permute to Train: A New Dimension to Training Deep Neural Networks |
| Authors | Yushi Qiu, Reiji Suda |
| Abstract | We show that Deep Neural Networks (DNNs) can be efficiently trained by permuting neuron connections. We introduce a new family of methods to train DNNs called Permute to Train (P2T). Two implementations of P2T are presented: Stochastic Gradient Permutation and Lookahead Permutation. The former computes permutation based on gradient, and the latter depends on another optimizer to derive the permutation. We empirically show that our proposed method, despite only swapping randomly weighted connections, achieves comparable accuracy to that of Adam on MNIST, Fashion-MNIST, and CIFAR-10 datasets. It opens up possibilities for new ways to train and regularize DNNs. |
| Tasks | |
| Published | 2020-03-05 |
| URL | https://arxiv.org/abs/2003.02570v3 |
| https://arxiv.org/pdf/2003.02570v3.pdf | |
| PWC | https://paperswithcode.com/paper/permute-to-train-a-new-dimension-to-training |
| Repo | |
| Framework | |
G2MF-WA: Geometric Multi-Model Fitting with Weakly Annotated Data
| Title | G2MF-WA: Geometric Multi-Model Fitting with Weakly Annotated Data |
| Authors | Chao Zhang, Xuequan Lu, Katsuya Hotta, Xi Yang |
| Abstract | In this paper we attempt to address the problem of geometric multi-model fitting with resorting to a few weakly annotated (WA) data points, which has been sparsely studied so far. In weak annotating, most of the manual annotations are supposed to be correct yet inevitably mixed with incorrect ones. The WA data can be naturally obtained in an interactive way for specific tasks, for example, in the case of homography estimation, one can easily annotate points on the same plane/object with a single label by observing the image. Motivated by this, we propose a novel method to make full use of the WA data to boost the multi-model fitting performance. Specifically, a graph for model proposal sampling is first constructed using the WA data, given the prior that the WA data annotated with the same weak label has a high probability of being assigned to the same model. By incorporating this prior knowledge into the calculation of edge probabilities, vertices (i.e., data points) lie on/near the latent model are likely to connect together and further form a subset/cluster for effective proposals generation. With the proposals generated, the $\alpha$-expansion is adopted for labeling, and our method in return updates the proposals. This works in an iterative way. Extensive experiments validate our method and show that the proposed method produces noticeably better results than state-of-the-art techniques in most cases. |
| Tasks | Homography Estimation |
| Published | 2020-01-20 |
| URL | https://arxiv.org/abs/2001.06965v1 |
| https://arxiv.org/pdf/2001.06965v1.pdf | |
| PWC | https://paperswithcode.com/paper/g2mf-wa-geometric-multi-model-fitting-with |
| Repo | |
| Framework | |
Infinity Learning: Learning Markov Chains from Aggregate Steady-State Observations
| Title | Infinity Learning: Learning Markov Chains from Aggregate Steady-State Observations |
| Authors | Jianfei Gao, Mohamed A. Zahran, Amit Sheoran, Sonia Fahmy, Bruno Ribeiro |
| Abstract | We consider the task of learning a parametric Continuous Time Markov Chain (CTMC) sequence model without examples of sequences, where the training data consists entirely of aggregate steady-state statistics. Making the problem harder, we assume that the states we wish to predict are unobserved in the training data. Specifically, given a parametric model over the transition rates of a CTMC and some known transition rates, we wish to extrapolate its steady state distribution to states that are unobserved. A technical roadblock to learn a CTMC from its steady state has been that the chain rule to compute gradients will not work over the arbitrarily long sequences necessary to reach steady state —from where the aggregate statistics are sampled. To overcome this optimization challenge, we propose $\infty$-SGD, a principled stochastic gradient descent method that uses randomly-stopped estimators to avoid infinite sums required by the steady state computation, while learning even when only a subset of the CTMC states can be observed. We apply $\infty$-SGD to a real-world testbed and synthetic experiments showcasing its accuracy, ability to extrapolate the steady state distribution to unobserved states under unobserved conditions (heavy loads, when training under light loads), and succeeding in difficult scenarios where even a tailor-made extension of existing methods fails. |
| Tasks | |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04186v1 |
| https://arxiv.org/pdf/2002.04186v1.pdf | |
| PWC | https://paperswithcode.com/paper/infinity-learning-learning-markov-chains-from |
| Repo | |
| Framework | |
Private and Communication-Efficient Edge Learning: A Sparse Differential Gaussian-Masking Distributed SGD Approach
| Title | Private and Communication-Efficient Edge Learning: A Sparse Differential Gaussian-Masking Distributed SGD Approach |
| Authors | Xin Zhang, Minghong Fang, Jia Liu, Zhengyuan Zhu |
| Abstract | With rise of machine learning (ML) and the proliferation of smart mobile devices, recent years have witnessed a surge of interest in performing ML in wireless edge networks. In this paper, we consider the problem of jointly improving data privacy and communication efficiency of distributed edge learning, both of which are critical performance metrics in wireless edge network computing. Toward this end, we propose a new decentralized stochastic gradient method with sparse differential Gaussian-masked stochastic gradients (SDM-DSGD) for non-convex distributed edge learning. Our main contributions are three-fold: i) We theoretically establish the privacy and communication efficiency performance guarantee of our SDM-DSGD method, which outperforms all existing works; ii) We show that SDM-DSGD improves the fundamental training-privacy trade-off by {\em two orders of magnitude} compared with the state-of-the-art. iii) We reveal theoretical insights and offer practical design guidelines for the interactions between privacy preservation and communication efficiency, two conflicting performance goals. We conduct extensive experiments with a variety of learning models on MNIST and CIFAR-10 datasets to verify our theoretical findings. Collectively, our results contribute to the theory and algorithm design for distributed edge learning. |
| Tasks | |
| Published | 2020-01-12 |
| URL | https://arxiv.org/abs/2001.03836v4 |
| https://arxiv.org/pdf/2001.03836v4.pdf | |
| PWC | https://paperswithcode.com/paper/private-and-communication-efficient-edge |
| Repo | |
| Framework | |
