Paper Group ANR 32
Autowarp: Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders. Interactive Binary Image Segmentation with Edge Preservation. Content-based Propagation of User Markings for Interactive Segmentation of Patterned Images. Understanding and Improving Deep Neural Network for Activity Recognition. Homogeneous Feature Transfe …
Autowarp: Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders
| Title | Autowarp: Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders |
| Authors | Abubakar Abid, James Zou |
| Abstract | Measuring similarities between unlabeled time series trajectories is an important problem in domains as diverse as medicine, astronomy, finance, and computer vision. It is often unclear what is the appropriate metric to use because of the complex nature of noise in the trajectories (e.g. different sampling rates or outliers). Domain experts typically hand-craft or manually select a specific metric, such as dynamic time warping (DTW), to apply on their data. In this paper, we propose Autowarp, an end-to-end algorithm that optimizes and learns a good metric given unlabeled trajectories. We define a flexible and differentiable family of warping metrics, which encompasses common metrics such as DTW, Euclidean, and edit distance. Autowarp then leverages the representation power of sequence autoencoders to optimize for a member of this warping distance family. The output is a metric which is easy to interpret and can be robustly learned from relatively few trajectories. In systematic experiments across different domains, we show that Autowarp often outperforms hand-crafted trajectory similarity metrics. |
| Tasks | Time Series |
| Published | 2018-10-23 |
| URL | http://arxiv.org/abs/1810.10107v1 |
| http://arxiv.org/pdf/1810.10107v1.pdf | |
| PWC | https://paperswithcode.com/paper/autowarp-learning-a-warping-distance-from |
| Repo | |
| Framework | |
Interactive Binary Image Segmentation with Edge Preservation
| Title | Interactive Binary Image Segmentation with Edge Preservation |
| Authors | Jianfeng Zhang, Liezhuo Zhang, Yuankai Teng, Xiaoping Zhang, Song Wang, Lili Ju |
| Abstract | Binary image segmentation plays an important role in computer vision and has been widely used in many applications such as image and video editing, object extraction, and photo composition. In this paper, we propose a novel interactive binary image segmentation method based on the Markov Random Field (MRF) framework and the fast bilateral solver (FBS) technique. Specifically, we employ the geodesic distance component to build the unary term. To ensure both computation efficiency and effective responsiveness for interactive segmentation, superpixels are used in computing geodesic distances instead of pixels. Furthermore, we take a bilateral affinity approach for the pairwise term in order to preserve edge information and denoise. Through the alternating direction strategy, the MRF energy minimization problem is divided into two subproblems, which then can be easily solved by steepest gradient descent (SGD) and FBS respectively. Experimental results on the VGG interactive image segmentation dataset show that the proposed algorithm outperforms several state-of-the-art ones, and in particular, it can achieve satisfactory edge-smooth segmentation results even when the foreground and background color appearances are quite indistinctive. |
| Tasks | Interactive Segmentation, Semantic Segmentation |
| Published | 2018-09-10 |
| URL | http://arxiv.org/abs/1809.03334v1 |
| http://arxiv.org/pdf/1809.03334v1.pdf | |
| PWC | https://paperswithcode.com/paper/interactive-binary-image-segmentation-with |
| Repo | |
| Framework | |
Content-based Propagation of User Markings for Interactive Segmentation of Patterned Images
| Title | Content-based Propagation of User Markings for Interactive Segmentation of Patterned Images |
| Authors | Vedrana Andersen Dahl, Camilla Himmelstrup Trinderup, Monica Jane Emerson, Anders Bjorholm Dahl |
| Abstract | Efficient and easy segmentation of images and volumes is of great practical importance. Segmentation problems which motivate our approach originate from imaging commonly used in materials science and medicine. We formulate image segmentation as a probabilistic pixel classification problem, and we apply segmentation as a step towards characterising image content. Our method allows the user to define structures of interest by interactively marking a subset of pixels. Thanks to the real-time feedback, the user can place new markings strategically, depending on the current outcome. The final pixel classification may be obtained from a very modest user input. An important ingredient of our method is a graph that encodes image content. This graph is built in an unsupervised manner during initialisation, and is based on clustering of image features. Since we combine a limited amount of user-labelled data with the clustering information obtained from the unlabelled parts of the image, our method fits in the general framework of semi-supervised learning. We demonstrate how this can be a very efficient approach to segmentation through pixel classification. |
| Tasks | Interactive Segmentation, Semantic Segmentation |
| Published | 2018-09-06 |
| URL | http://arxiv.org/abs/1809.02226v1 |
| http://arxiv.org/pdf/1809.02226v1.pdf | |
| PWC | https://paperswithcode.com/paper/content-based-propagation-of-user-markings |
| Repo | |
| Framework | |
Understanding and Improving Deep Neural Network for Activity Recognition
| Title | Understanding and Improving Deep Neural Network for Activity Recognition |
| Authors | Li Xue, Si Xiandong, Nie Lanshun, Li Jiazhen, Ding Renjie, Zhan Dechen, Chu Dianhui |
| Abstract | Activity recognition has become a popular research branch in the field of pervasive computing in recent years. A large number of experiments can be obtained that activity sensor-based data’s characteristic in activity recognition is variety, volume, and velocity. Deep learning technology, together with its various models, is one of the most effective ways of working on activity data. Nevertheless, there is no clear understanding of why it performs so well or how to make it more effective. In order to solve this problem, first, we applied convolution neural network on Human Activity Recognition Using Smart phones Data Set. Second, we realized the visualization of the sensor-based activity’s data features extracted from the neural network. Then we had in-depth analysis of the visualization of features, explored the relationship between activity and features, and analyzed how Neural Networks identify activity based on these features. After that, we extracted the significant features related to the activities and sent the features to the DNN-based fusion model, which improved the classification rate to 96.1%. This is the first work to our knowledge that visualizes abstract sensor-based activity data features. Based on the results, the method proposed in the paper promises to realize the accurate classification of sensor- based activity recognition. |
| Tasks | Activity Recognition, Human Activity Recognition |
| Published | 2018-05-18 |
| URL | http://arxiv.org/abs/1805.07020v1 |
| http://arxiv.org/pdf/1805.07020v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-and-improving-deep-neural |
| Repo | |
| Framework | |
Homogeneous Feature Transfer and Heterogeneous Location Fine-tuning for Cross-City Property Appraisal Framework
| Title | Homogeneous Feature Transfer and Heterogeneous Location Fine-tuning for Cross-City Property Appraisal Framework |
| Authors | Yihan Guo, Shan Lin, Xiao Ma, Jay Bal, Chang-tsun Li |
| Abstract | Most existing real estate appraisal methods focus on building accuracy and reliable models from a given dataset but pay little attention to the extensibility of their trained model. As different cities usually contain a different set of location features (district names, apartment names), most existing mass appraisal methods have to train a new model from scratch for different cities or regions. As a result, these approaches require massive data collection for each city and the total training time for a multi-city property appraisal system will be extremely long. Besides, some small cities may not have enough data for training a robust appraisal model. To overcome these limitations, we develop a novel Homogeneous Feature Transfer and Heterogeneous Location Fine-tuning (HFT+HLF) cross-city property appraisal framework. By transferring partial neural network learning from a source city and fine-tuning on the small amount of location information of a target city, our semi-supervised model can achieve similar or even superior performance compared to a fully supervised Artificial neural network (ANN) method. |
| Tasks | |
| Published | 2018-12-11 |
| URL | http://arxiv.org/abs/1812.05486v1 |
| http://arxiv.org/pdf/1812.05486v1.pdf | |
| PWC | https://paperswithcode.com/paper/homogeneous-feature-transfer-and |
| Repo | |
| Framework | |
Interpretable Parallel Recurrent Neural Networks with Convolutional Attentions for Multi-Modality Activity Modeling
| Title | Interpretable Parallel Recurrent Neural Networks with Convolutional Attentions for Multi-Modality Activity Modeling |
| Authors | Kaixuan Chen, Lina Yao, Xianzhi Wang, Dalin Zhang, Tao Gu, Zhiwen Yu, Zheng Yang |
| Abstract | Multimodal features play a key role in wearable sensor-based human activity recognition (HAR). Selecting the most salient features adaptively is a promising way to maximize the effectiveness of multimodal sensor data. In this regard, we propose a “collect fully and select wisely” principle as well as an interpretable parallel recurrent model with convolutional attentions to improve the recognition performance. We first collect modality features and the relations between each pair of features to generate activity frames, and then introduce an attention mechanism to select the most prominent regions from activity frames precisely. The selected frames not only maximize the utilization of valid features but also reduce the number of features to be computed effectively. We further analyze the accuracy and interpretability of the proposed model based on extensive experiments. The results show that our model achieves competitive performance on two benchmarked datasets and works well in real life scenarios. |
| Tasks | Activity Recognition, Human Activity Recognition |
| Published | 2018-05-17 |
| URL | http://arxiv.org/abs/1805.07233v1 |
| http://arxiv.org/pdf/1805.07233v1.pdf | |
| PWC | https://paperswithcode.com/paper/interpretable-parallel-recurrent-neural |
| Repo | |
| Framework | |
Fast and Accurate Person Re-Identification with RMNet
| Title | Fast and Accurate Person Re-Identification with RMNet |
| Authors | Evgeny Izutov |
| Abstract | In this paper we introduce a new neural network architecture designed to use in embedded vision applications. It merges the best working practices of network architectures like MobileNets and ResNets to our named RMNet architecture. We also focus on key moments of building mobile architectures to carry out in the limited computation budget. Additionally, to demonstrate the effectiveness of our architecture we evaluate the RMNet backbone on Person Re-identification task. The proposed approach is in top 3 of state of the art solutions on Market-1501 challenge, however our method significantly outperforms them by the inference speed. |
| Tasks | Person Re-Identification |
| Published | 2018-12-06 |
| URL | http://arxiv.org/abs/1812.02465v1 |
| http://arxiv.org/pdf/1812.02465v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-accurate-person-re-identification |
| Repo | |
| Framework | |
Feature Representation Analysis of Deep Convolutional Neural Network using Two-stage Feature Transfer -An Application for Diffuse Lung Disease Classification-
| Title | Feature Representation Analysis of Deep Convolutional Neural Network using Two-stage Feature Transfer -An Application for Diffuse Lung Disease Classification- |
| Authors | Aiga Suzuki, Hidenori Sakanashi, Shoji Kido, Hayaru Shouno |
| Abstract | Transfer learning is a machine learning technique designed to improve generalization performance by using pre-trained parameters obtained from other learning tasks. For image recognition tasks, many previous studies have reported that, when transfer learning is applied to deep neural networks, performance improves, despite having limited training data. This paper proposes a two-stage feature transfer learning method focusing on the recognition of textural medical images. During the proposed method, a model is successively trained with massive amounts of natural images, some textural images, and the target images. We applied this method to the classification task of textural X-ray computed tomography images of diffuse lung diseases. In our experiment, the two-stage feature transfer achieves the best performance compared to a from-scratch learning and a conventional single-stage feature transfer. We also investigated the robustness of the target dataset, based on size. Two-stage feature transfer shows better robustness than the other two learning methods. Moreover, we analyzed the feature representations obtained from DLDs imagery inputs for each feature transfer models using a visualization method. We showed that the two-stage feature transfer obtains both edge and textural features of DLDs, which does not occur in conventional single-stage feature transfer models. |
| Tasks | Lung Disease Classification, Transfer Learning |
| Published | 2018-10-15 |
| URL | http://arxiv.org/abs/1810.06282v1 |
| http://arxiv.org/pdf/1810.06282v1.pdf | |
| PWC | https://paperswithcode.com/paper/feature-representation-analysis-of-deep |
| Repo | |
| Framework | |
Semi-Supervised Online Structure Learning for Composite Event Recognition
| Title | Semi-Supervised Online Structure Learning for Composite Event Recognition |
| Authors | Evangelos Michelioudakis, Alexander Artikis, Georgios Paliouras |
| Abstract | Online structure learning approaches, such as those stemming from Statistical Relational Learning, enable the discovery of complex relations in noisy data streams. However, these methods assume the existence of fully-labelled training data, which is unrealistic for most real-world applications. We present a novel approach for completing the supervision of a semi-supervised structure learning task. We incorporate graph-cut minimisation, a technique that derives labels for unlabelled data, based on their distance to their labelled counterparts. In order to adapt graph-cut minimisation to first order logic, we employ a suitable structural distance for measuring the distance between sets of logical atoms. The labelling process is achieved online (single-pass) by means of a caching mechanism and the Hoeffding bound, a statistical tool to approximate globally-optimal decisions from locally-optimal ones. We evaluate our approach on the task of composite event recognition by using a benchmark dataset for human activity recognition, as well as a real dataset for maritime monitoring. The evaluation suggests that our approach can effectively complete the missing labels and eventually, improve the accuracy of the underlying structure learning system. |
| Tasks | Activity Recognition, Human Activity Recognition, Relational Reasoning |
| Published | 2018-03-01 |
| URL | http://arxiv.org/abs/1803.00546v2 |
| http://arxiv.org/pdf/1803.00546v2.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-online-structure-learning-for |
| Repo | |
| Framework | |
Sparse Three-parameter Restricted Indian Buffet Process for Understanding International Trade
| Title | Sparse Three-parameter Restricted Indian Buffet Process for Understanding International Trade |
| Authors | Melanie F. Pradier, Viktor Stojkoski, Zoran Utkovski, Ljupco Kocarev, Fernando Perez-Cruz |
| Abstract | This paper presents a Bayesian nonparametric latent feature model specially suitable for exploratory analysis of high-dimensional count data. We perform a non-negative doubly sparse matrix factorization that has two main advantages: not only we are able to better approximate the row input distributions, but the inferred topics are also easier to interpret. By combining the three-parameter and restricted Indian buffet processes into a single prior, we increase the model flexibility, allowing for a full spectrum of sparse solutions in the latent space. We demonstrate the usefulness of our approach in the analysis of countries’ economic structure. Compared to other approaches, empirical results show our model’s ability to give easy-to-interpret information and better capture the underlying sparsity structure of data. |
| Tasks | |
| Published | 2018-06-29 |
| URL | http://arxiv.org/abs/1806.11518v1 |
| http://arxiv.org/pdf/1806.11518v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-three-parameter-restricted-indian |
| Repo | |
| Framework | |
Stochastic Negative Mining for Learning with Large Output Spaces
| Title | Stochastic Negative Mining for Learning with Large Output Spaces |
| Authors | Sashank J. Reddi, Satyen Kale, Felix Yu, Dan Holtmann-Rice, Jiecao Chen, Sanjiv Kumar |
| Abstract | We consider the problem of retrieving the most relevant labels for a given input when the size of the output space is very large. Retrieval methods are modeled as set-valued classifiers which output a small set of classes for each input, and a mistake is made if the label is not in the output set. Despite its practical importance, a statistically principled, yet practical solution to this problem is largely missing. To this end, we first define a family of surrogate losses and show that they are calibrated and convex under certain conditions on the loss parameters and data distribution, thereby establishing a statistical and analytical basis for using these losses. Furthermore, we identify a particularly intuitive class of loss functions in the aforementioned family and show that they are amenable to practical implementation in the large output space setting (i.e. computation is possible without evaluating scores of all labels) by developing a technique called Stochastic Negative Mining. We also provide generalization error bounds for the losses in the family. Finally, we conduct experiments which demonstrate that Stochastic Negative Mining yields benefits over commonly used negative sampling approaches. |
| Tasks | |
| Published | 2018-10-16 |
| URL | http://arxiv.org/abs/1810.07076v1 |
| http://arxiv.org/pdf/1810.07076v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-negative-mining-for-learning-with |
| Repo | |
| Framework | |
Retrieval-Enhanced Adversarial Training for Neural Response Generation
| Title | Retrieval-Enhanced Adversarial Training for Neural Response Generation |
| Authors | Qingfu Zhu, Lei Cui, Weinan Zhang, Furu Wei, Ting Liu |
| Abstract | Dialogue systems are usually built on either generation-based or retrieval-based approaches, yet they do not benefit from the advantages of different models. In this paper, we propose a Retrieval-Enhanced Adversarial Training (REAT) method for neural response generation. Distinct from existing approaches, the REAT method leverages an encoder-decoder framework in terms of an adversarial training paradigm, while taking advantage of N-best response candidates from a retrieval-based system to construct the discriminator. An empirical study on a large scale public available benchmark dataset shows that the REAT method significantly outperforms the vanilla Seq2Seq model as well as the conventional adversarial training approach. |
| Tasks | |
| Published | 2018-09-12 |
| URL | https://arxiv.org/abs/1809.04276v2 |
| https://arxiv.org/pdf/1809.04276v2.pdf | |
| PWC | https://paperswithcode.com/paper/retrieval-enhanced-adversarial-training-for |
| Repo | |
| Framework | |
Iteratively Trained Interactive Segmentation
| Title | Iteratively Trained Interactive Segmentation |
| Authors | Sabarinath Mahadevan, Paul Voigtlaender, Bastian Leibe |
| Abstract | Deep learning requires large amounts of training data to be effective. For the task of object segmentation, manually labeling data is very expensive, and hence interactive methods are needed. Following recent approaches, we develop an interactive object segmentation system which uses user input in the form of clicks as the input to a convolutional network. While previous methods use heuristic click sampling strategies to emulate user clicks during training, we propose a new iterative training strategy. During training, we iteratively add clicks based on the errors of the currently predicted segmentation. We show that our iterative training strategy together with additional improvements to the network architecture results in improved results over the state-of-the-art. |
| Tasks | Interactive Segmentation, Semantic Segmentation |
| Published | 2018-05-11 |
| URL | http://arxiv.org/abs/1805.04398v1 |
| http://arxiv.org/pdf/1805.04398v1.pdf | |
| PWC | https://paperswithcode.com/paper/iteratively-trained-interactive-segmentation |
| Repo | |
| Framework | |
Multi-Agent Common Knowledge Reinforcement Learning
| Title | Multi-Agent Common Knowledge Reinforcement Learning |
| Authors | Christian A. Schroeder de Witt, Jakob N. Foerster, Gregory Farquhar, Philip H. S. Torr, Wendelin Boehmer, Shimon Whiteson |
| Abstract | Cooperative multi-agent reinforcement learning often requires decentralised policies, which severely limit the agents’ ability to coordinate their behaviour. In this paper, we show that common knowledge between agents allows for complex decentralised coordination. Common knowledge arises naturally in a large number of decentralised cooperative multi-agent tasks, for example, when agents can reconstruct parts of each others’ observations. Since agents an independently agree on their common knowledge, they can execute complex coordinated policies that condition on this knowledge in a fully decentralised fashion. We propose multi-agent common knowledge reinforcement learning (MACKRL), a novel stochastic actor-critic algorithm that learns a hierarchical policy tree. Higher levels in the hierarchy coordinate groups of agents by conditioning on their common knowledge, or delegate to lower levels with smaller subgroups but potentially richer common knowledge. The entire policy tree can be executed in a fully decentralised fashion. As the lowest policy tree level consists of independent policies for each agent, MACKRL reduces to independently learnt decentralised policies as a special case. We demonstrate that our method can exploit common knowledge for superior performance on complex decentralised coordination tasks, including a stochastic matrix game and challenging problems in StarCraft II unit micromanagement. |
| Tasks | Multi-agent Reinforcement Learning, Starcraft, Starcraft II |
| Published | 2018-10-27 |
| URL | https://arxiv.org/abs/1810.11702v8 |
| https://arxiv.org/pdf/1810.11702v8.pdf | |
| PWC | https://paperswithcode.com/paper/multi-agent-common-knowledge-reinforcement |
| Repo | |
| Framework | |
SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting
| Title | SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting |
| Authors | Yuhang Song, Chao Yang, Yeji Shen, Peng Wang, Qin Huang, C. -C. Jay Kuo |
| Abstract | In this paper, we focus on image inpainting task, aiming at recovering the missing area of an incomplete image given the context information. Recent development in deep generative models enables an efficient end-to-end framework for image synthesis and inpainting tasks, but existing methods based on generative models don’t exploit the segmentation information to constrain the object shapes, which usually lead to blurry results on the boundary. To tackle this problem, we propose to introduce the semantic segmentation information, which disentangles the inter-class difference and intra-class variation for image inpainting. This leads to much clearer recovered boundary between semantically different regions and better texture within semantically consistent segments. Our model factorizes the image inpainting process into segmentation prediction (SP-Net) and segmentation guidance (SG-Net) as two steps, which predict the segmentation labels in the missing area first, and then generate segmentation guided inpainting results. Experiments on multiple public datasets show that our approach outperforms existing methods in optimizing the image inpainting quality, and the interactive segmentation guidance provides possibilities for multi-modal predictions of image inpainting. |
| Tasks | Image Generation, Image Inpainting, Interactive Segmentation, Semantic Segmentation |
| Published | 2018-05-09 |
| URL | http://arxiv.org/abs/1805.03356v4 |
| http://arxiv.org/pdf/1805.03356v4.pdf | |
| PWC | https://paperswithcode.com/paper/spg-net-segmentation-prediction-and-guidance |
| Repo | |
| Framework | |
