Paper Group ANR 977
Static Activation Function Normalization. Meta-Learning for Black-box Optimization. Graph Message Passing with Cross-location Attentions for Long-term ILI Prediction. Will this Course Increase or Decrease Your GPA? Towards Grade-aware Course Recommendation. Evolving Plasticity for Autonomous Learning under Changing Environmental Conditions. Dataflo …
Static Activation Function Normalization
| Title | Static Activation Function Normalization |
| Authors | Pierre H. Richemond, Yike Guo |
| Abstract | Recent seminal work at the intersection of deep neural networks practice and random matrix theory has linked the convergence speed and robustness of these networks with the combination of random weight initialization and nonlinear activation function in use. Building on those principles, we introduce a process to transform an existing activation function into another one with better properties. We term such transform \emph{static activation normalization}. More specifically we focus on this normalization applied to the ReLU unit, and show empirically that it significantly promotes convergence robustness, maximum training depth, and anytime performance. We verify these claims by examining empirical eigenvalue distributions of networks trained with those activations. Our static activation normalization provides a first step towards giving benefits similar in spirit to schemes like batch normalization, but without computational cost. |
| Tasks | |
| Published | 2019-05-03 |
| URL | https://arxiv.org/abs/1905.01369v1 |
| https://arxiv.org/pdf/1905.01369v1.pdf | |
| PWC | https://paperswithcode.com/paper/static-activation-function-normalization |
| Repo | |
| Framework | |
Meta-Learning for Black-box Optimization
| Title | Meta-Learning for Black-box Optimization |
| Authors | Vishnu TV, Pankaj Malhotra, Jyoti Narwariya, Lovekesh Vig, Gautam Shroff |
| Abstract | Recently, neural networks trained as optimizers under the “learning to learn” or meta-learning framework have been shown to be effective for a broad range of optimization tasks including derivative-free black-box function optimization. Recurrent neural networks (RNNs) trained to optimize a diverse set of synthetic non-convex differentiable functions via gradient descent have been effective at optimizing derivative-free black-box functions. In this work, we propose RNN-Opt: an approach for learning RNN-based optimizers for optimizing real-parameter single-objective continuous functions under limited budget constraints. Existing approaches utilize an observed improvement based meta-learning loss function for training such models. We propose training RNN-Opt by using synthetic non-convex functions with known (approximate) optimal values by directly using discounted regret as our meta-learning loss function. We hypothesize that a regret-based loss function mimics typical testing scenarios, and would therefore lead to better optimizers compared to optimizers trained only to propose queries that improve over previous queries. Further, RNN-Opt incorporates simple yet effective enhancements during training and inference procedures to deal with the following practical challenges: i) Unknown range of possible values for the black-box function to be optimized, and ii) Practical and domain-knowledge based constraints on the input parameters. We demonstrate the efficacy of RNN-Opt in comparison to existing methods on several synthetic as well as standard benchmark black-box functions along with an anonymized industrial constrained optimization problem. |
| Tasks | Meta-Learning |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.06901v2 |
| https://arxiv.org/pdf/1907.06901v2.pdf | |
| PWC | https://paperswithcode.com/paper/meta-learning-for-black-box-optimization |
| Repo | |
| Framework | |
Graph Message Passing with Cross-location Attentions for Long-term ILI Prediction
| Title | Graph Message Passing with Cross-location Attentions for Long-term ILI Prediction |
| Authors | Songgaojun Deng, Shusen Wang, Huzefa Rangwala, Lijing Wang, Yue Ning |
| Abstract | Forecasting influenza-like illness (ILI) is of prime importance to epidemiologists and health-care providers. Early prediction of epidemic outbreaks plays a pivotal role in disease intervention and control. Most existing work has either limited long-term prediction performance or lacks a comprehensive ability to capture spatio-temporal dependencies in data. Accurate and early disease forecasting models would markedly improve both epidemic prevention and managing the onset of an epidemic. In this paper, we design a cross-location attention based graph neural network (Cola-GNN) for learning time series embeddings and location aware attentions. We propose a graph message passing framework to combine learned feature embeddings and an attention matrix to model disease propagation over time. We compare the proposed method with state-of-the-art statistical approaches and deep learning models on real-world epidemic-related datasets from United States and Japan. The proposed method shows strong predictive performance and leads to interpretable results for long-term epidemic predictions. |
| Tasks | Time Series |
| Published | 2019-12-21 |
| URL | https://arxiv.org/abs/1912.10202v2 |
| https://arxiv.org/pdf/1912.10202v2.pdf | |
| PWC | https://paperswithcode.com/paper/graph-message-passing-with-cross-location |
| Repo | |
| Framework | |
Will this Course Increase or Decrease Your GPA? Towards Grade-aware Course Recommendation
| Title | Will this Course Increase or Decrease Your GPA? Towards Grade-aware Course Recommendation |
| Authors | Sara Morsy, George Karypis |
| Abstract | In order to help undergraduate students towards successfully completing their degrees, developing tools that can assist students during the course selection process is a significant task in the education domain. The optimal set of courses for each student should include courses that help him/her graduate in a timely fashion and for which he/she is well-prepared for so as to get a good grade in. To this end, we propose two different grade-aware course recommendation approaches to recommend to each student his/her optimal set of courses. The first approach ranks the courses by using an objective function that differentiates between courses that are expected to increase or decrease a student’s GPA. The second approach combines the grades predicted by grade prediction methods with the rankings produced by course recommendation methods to improve the final course rankings. To obtain the course rankings in the first approach, we adapt two widely-used representation learning techniques to learn the optimal temporal ordering between courses. Our experiments on a large dataset obtained from the University of Minnesota that includes students from 23 different majors show that the grade-aware course recommendation methods can do better on recommending more courses in which the students are expected to perform well and recommending fewer courses in which they are expected not to perform well in than grade-unaware course recommendation methods. |
| Tasks | Representation Learning |
| Published | 2019-04-22 |
| URL | http://arxiv.org/abs/1904.11798v1 |
| http://arxiv.org/pdf/1904.11798v1.pdf | |
| PWC | https://paperswithcode.com/paper/will-this-course-increase-or-decrease-your |
| Repo | |
| Framework | |
Evolving Plasticity for Autonomous Learning under Changing Environmental Conditions
| Title | Evolving Plasticity for Autonomous Learning under Changing Environmental Conditions |
| Authors | Anil Yaman, Giovanni Iacca, Decebal Constantin Mocanu, Matt Coler, George Fletcher, Mykola Pechenizkiy |
| Abstract | A fundamental aspect of learning in biological neural networks (BNNs) is the plasticity property which allows them to modify their configurations during their lifetime. Hebbian learning is a biologically plausible mechanism for modeling the plasticity property based on the local activation of neurons. In this work, we employ genetic algorithms to evolve local learning rules, from Hebbian perspective, to produce autonomous learning under changing environmental conditions. Our evolved synaptic plasticity rules are capable of performing synaptic updates in distributed and self-organized fashion, based only on the binary activation states of neurons, and a reinforcement signal received from the environment. We demonstrate the learning and adaptation capabilities of the ANNs modified by the evolved plasticity rules on a foraging task in a continuous learning settings. Our results show that evolved plasticity rules are highly efficient at adapting the ANNs to task under changing environmental conditions. |
| Tasks | |
| Published | 2019-04-02 |
| URL | https://arxiv.org/abs/1904.01709v2 |
| https://arxiv.org/pdf/1904.01709v2.pdf | |
| PWC | https://paperswithcode.com/paper/evolving-plasticity-for-autonomous-learning |
| Repo | |
| Framework | |
Dataflow-based Joint Quantization of Weights and Activations for Deep Neural Networks
| Title | Dataflow-based Joint Quantization of Weights and Activations for Deep Neural Networks |
| Authors | Xue Geng, Jie Fu, Bin Zhao, Jie Lin, Mohamed M. Sabry Aly, Christopher Pal, Vijay Chandrasekhar |
| Abstract | This paper addresses a challenging problem - how to reduce energy consumption without incurring performance drop when deploying deep neural networks (DNNs) at the inference stage. In order to alleviate the computation and storage burdens, we propose a novel dataflow-based joint quantization approach with the hypothesis that a fewer number of quantization operations would incur less information loss and thus improve the final performance. It first introduces a quantization scheme with efficient bit-shifting and rounding operations to represent network parameters and activations in low precision. Then it restructures the network architectures to form unified modules for optimization on the quantized model. Extensive experiments on ImageNet and KITTI validate the effectiveness of our model, demonstrating that state-of-the-art results for various tasks can be achieved by this quantized model. Besides, we designed and synthesized an RTL model to measure the hardware costs among various quantization methods. For each quantization operation, it reduces area cost by about 15 times and energy consumption by about 9 times, compared to a strong baseline. |
| Tasks | Quantization |
| Published | 2019-01-04 |
| URL | http://arxiv.org/abs/1901.02064v1 |
| http://arxiv.org/pdf/1901.02064v1.pdf | |
| PWC | https://paperswithcode.com/paper/dataflow-based-joint-quantization-of-weights |
| Repo | |
| Framework | |
U4D: Unsupervised 4D Dynamic Scene Understanding
| Title | U4D: Unsupervised 4D Dynamic Scene Understanding |
| Authors | Armin Mustafa, Chris Russell, Adrian Hilton |
| Abstract | We introduce the first approach to solve the challenging problem of unsupervised 4D visual scene understanding for complex dynamic scenes with multiple interacting people from multi-view video. Our approach simultaneously estimates a detailed model that includes a per-pixel semantically and temporally coherent reconstruction, together with instance-level segmentation exploiting photo-consistency, semantic and motion information. We further leverage recent advances in 3D pose estimation to constrain the joint semantic instance segmentation and 4D temporally coherent reconstruction. This enables per person semantic instance segmentation of multiple interacting people in complex dynamic scenes. Extensive evaluation of the joint visual scene understanding framework against state-of-the-art methods on challenging indoor and outdoor sequences demonstrates a significant (approx 40%) improvement in semantic segmentation, reconstruction and scene flow accuracy. |
| Tasks | 3D Pose Estimation, Instance Segmentation, Pose Estimation, Scene Understanding, Semantic Segmentation |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.09905v1 |
| https://arxiv.org/pdf/1907.09905v1.pdf | |
| PWC | https://paperswithcode.com/paper/u4d-unsupervised-4d-dynamic-scene |
| Repo | |
| Framework | |
RepGN:Object Detection with Relational Proposal Graph Network
| Title | RepGN:Object Detection with Relational Proposal Graph Network |
| Authors | Xingjian Du, Xuan Shi, Risheng Huang |
| Abstract | Region based object detectors achieve the state-of-the-art performance, but few consider to model the relation of proposals. In this paper, we explore the idea of modeling the relationships among the proposals for object detection from the graph learning perspective. Specifically, we present relational proposal graph network (RepGN) which is defined on object proposals and the semantic and spatial relation modeled as the edge. By integrating our RepGN module into object detectors, the relation and context constraints will be introduced to the feature extraction of regions and bounding boxes regression and classification. Besides, we propose a novel graph-cut based pooling layer for hierarchical coarsening of the graph, which empowers the RepGN module to exploit the inter-regional correlation and scene description in a hierarchical manner. We perform extensive experiments on COCO object detection dataset and show promising results. |
| Tasks | Object Detection |
| Published | 2019-04-18 |
| URL | http://arxiv.org/abs/1904.08959v1 |
| http://arxiv.org/pdf/1904.08959v1.pdf | |
| PWC | https://paperswithcode.com/paper/repgnobject-detection-with-relational |
| Repo | |
| Framework | |
Human Gait Symmetry Assessment using a Depth Camera and Mirrors
| Title | Human Gait Symmetry Assessment using a Depth Camera and Mirrors |
| Authors | Trong-Nguyen Nguyen, Huu-Hung Huynh, Jean Meunier |
| Abstract | This paper proposes a reliable approach for human gait symmetry assessment using a depth camera and two mirrors. The input of our system is a sequence of 3D point clouds which are formed from a setup including a Time-of-Flight (ToF) depth camera and two mirrors. A cylindrical histogram is estimated for describing the posture in each point cloud. The sequence of such histograms is then separated into two sequences of sub-histograms representing two half-bodies. A cross-correlation technique is finally applied to provide values describing gait symmetry indices. The evaluation was performed on 9 different gait types to demonstrate the ability of our approach in assessing gait symmetry. A comparison between our system and related methods, that employ different input data types, is also provided. |
| Tasks | |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.07422v1 |
| https://arxiv.org/pdf/1908.07422v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-gait-symmetry-assessment-using-a-depth |
| Repo | |
| Framework | |
Real-time Segmentation and Facial Skin Tones Grading
| Title | Real-time Segmentation and Facial Skin Tones Grading |
| Authors | Ling Luo, Dingyu Xue, Xinglong Feng, Yichun Yu, Peng Wang |
| Abstract | Modern approaches for semantic segmention usually pay too much attention to the accuracy of the model, and therefore it is strongly recommended to introduce cumbersome backbones, which brings heavy computation burden and memory footprint. To alleviate this problem, we propose an efficient segmentation method based on deep convolutional neural networks (DCNNs) for the task of hair and facial skin segmentation, which achieving remarkable trade-off between speed and performance on three benchmark datasets. As far as we know, the accuracy of skin tones classification is usually unsatisfactory due to the influence of external environmental factors such as illumination and background noise. Therefore, we use the segmentated face to obtain a specific face area, and further exploit the color moment algorithm to extract its color features. Specifically, for a 224 x 224 standard input, using our high-resolution spatial detail information and low-resolution contextual information fusion network (HLNet), we achieve 90.73% Pixel Accuracy on Figaro1k dataset at over 16 FPS in the case of CPU environment. Additional experiments on CamVid dataset further confirm the universality of the proposed model. We further use masked color moment for skin tones grade evaluation and approximate 80% classification accuracy demonstrate the feasibility of the proposed scheme.Code is available at https://github.com/JACKYLUO1991/Face-skin-hair-segmentaiton-and-skin-color-evaluation. |
| Tasks | |
| Published | 2019-12-30 |
| URL | https://arxiv.org/abs/1912.12888v2 |
| https://arxiv.org/pdf/1912.12888v2.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-segmentation-and-facial-skin-tones |
| Repo | |
| Framework | |
Deep Learning: a new definition of artificial neuron with double weight
| Title | Deep Learning: a new definition of artificial neuron with double weight |
| Authors | Adriano Baldeschi, Raffaella Margutti, Adam Miller |
| Abstract | Deep learning is a subset of a broader family of machine learning methods based on learning data representations. These models are inspired by human biological nervous systems, even if there are various differences pertaining to the structural and functional properties of biological brains. The elementary constituents of deep learning models are neurons, which can be considered as functions that receive inputs and produce an output that is a weighted sum of the inputs fed through an activation function. Several models of neurons were proposed in the course of the years that are all based on learnable parameters called weights. In this paper we present a new type of artificial neuron, the double-weight neuron,characterized by additional learnable weights that lead to a more complex and accurate system. We tested a feed-forward and convolutional neural network consisting of double-weight neurons on the MNIST dataset, and we tested a convolution network on the CIFAR-10 dataset. For MNIST we find a $\approx 4%$ and $\approx 1%$ improved classification accuracy, respectively, when compared to a standard feed-forward and convolutional neural network built with the same sets of hyperparameters. For CIFAR-10 we find a $\approx 12%$ improved classification accuracy. We thus conclude that this novel artificial neuron can be considered as a valuable alternative to common ones. |
| Tasks | |
| Published | 2019-05-11 |
| URL | https://arxiv.org/abs/1905.04545v2 |
| https://arxiv.org/pdf/1905.04545v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-a-new-definition-of-artificial |
| Repo | |
| Framework | |
Video Question Generation via Cross-Modal Self-Attention Networks Learning
| Title | Video Question Generation via Cross-Modal Self-Attention Networks Learning |
| Authors | Yu-Siang Wang, Hung-Ting Su, Chen-Hsi Chang, Zhe-Yu Liu, Winston H. Hsu |
| Abstract | We introduce a novel task, Video Question Generation (Video QG). A Video QG model automatically generates questions given a video clip and its corresponding dialogues. Video QG requires a range of skills – sentence comprehension, temporal relation, the interplay between vision and language, and the ability to ask meaningful questions. To address this, we propose a novel semantic rich cross-modal self-attention (SRCMSA) network to aggregate the multi-modal and diverse features. To be more precise, we enhance the video frames semantic by integrating the object-level information, and we jointly consider the cross-modal attention for the video question generation task. Excitingly, our proposed model remarkably improves the baseline from 7.58 to 14.48 in the BLEU-4 score on the TVQA dataset. Most of all, we arguably pave a novel path toward understanding the challenging video input and we provide detailed analysis in terms of diversity, which ushers the avenues for future investigations. |
| Tasks | Question Answering, Question Generation, Video Question Answering |
| Published | 2019-07-05 |
| URL | https://arxiv.org/abs/1907.03049v3 |
| https://arxiv.org/pdf/1907.03049v3.pdf | |
| PWC | https://paperswithcode.com/paper/video-question-generation-via-cross-modal |
| Repo | |
| Framework | |
A Multi-Agent Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning
| Title | A Multi-Agent Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning |
| Authors | Wesley Suttle, Zhuoran Yang, Kaiqing Zhang, Zhaoran Wang, Tamer Basar, Ji Liu |
| Abstract | This paper extends off-policy reinforcement learning to the multi-agent case in which a set of networked agents communicating with their neighbors according to a time-varying graph collaboratively evaluates and improves a target policy while following a distinct behavior policy. To this end, the paper develops a multi-agent version of emphatic temporal difference learning for off-policy policy evaluation, and proves convergence under linear function approximation. The paper then leverages this result, in conjunction with a novel multi-agent off-policy policy gradient theorem and recent work in both multi-agent on-policy and single-agent off-policy actor-critic methods, to develop and give convergence guarantees for a new multi-agent off-policy actor-critic algorithm. |
| Tasks | |
| Published | 2019-03-15 |
| URL | https://arxiv.org/abs/1903.06372v3 |
| https://arxiv.org/pdf/1903.06372v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-multi-agent-off-policy-actor-critic |
| Repo | |
| Framework | |
Meta-Surrogate Benchmarking for Hyperparameter Optimization
| Title | Meta-Surrogate Benchmarking for Hyperparameter Optimization |
| Authors | Aaron Klein, Zhenwen Dai, Frank Hutter, Neil Lawrence, Javier Gonzalez |
| Abstract | Despite the recent progress in hyperparameter optimization (HPO), available benchmarks that resemble real-world scenarios consist of a few and very large problem instances that are expensive to solve. This blocks researchers and practitioners not only from systematically running large-scale comparisons that are needed to draw statistically significant results but also from reproducing experiments that were conducted before. This work proposes a method to alleviate these issues by means of a meta-surrogate model for HPO tasks trained on off-line generated data. The model combines a probabilistic encoder with a multi-task model such that it can generate inexpensive and realistic tasks of the class of problems of interest. We demonstrate that benchmarking HPO methods on samples of the generative model allows us to draw more coherent and statistically significant conclusions that can be reached orders of magnitude faster than using the original tasks. We provide evidence of our findings for various HPO methods on a wide class of problems. |
| Tasks | Hyperparameter Optimization |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.12982v2 |
| https://arxiv.org/pdf/1905.12982v2.pdf | |
| PWC | https://paperswithcode.com/paper/meta-surrogate-benchmarking-for |
| Repo | |
| Framework | |
Identifying Visible Actions in Lifestyle Vlogs
| Title | Identifying Visible Actions in Lifestyle Vlogs |
| Authors | Oana Ignat, Laura Burdick, Jia Deng, Rada Mihalcea |
| Abstract | We consider the task of identifying human actions visible in online videos. We focus on the widely spread genre of lifestyle vlogs, which consist of videos of people performing actions while verbally describing them. Our goal is to identify if actions mentioned in the speech description of a video are visually present. We construct a dataset with crowdsourced manual annotations of visible actions, and introduce a multimodal algorithm that leverages information derived from visual and linguistic clues to automatically infer which actions are visible in a video. We demonstrate that our multimodal algorithm outperforms algorithms based only on one modality at a time. |
| Tasks | |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.04236v1 |
| https://arxiv.org/pdf/1906.04236v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-visible-actions-in-lifestyle |
| Repo | |
| Framework | |
