Paper Group ANR 714
CRRN: Multi-Scale Guided Concurrent Reflection Removal Network. MBA: Mini-Batch AUC Optimization. Packaging and Sharing Machine Learning Models via the Acumos AI Open Platform. On the Limitations of Unsupervised Bilingual Dictionary Induction. Efficient Discovery of Heterogeneous Treatment Effects in Randomized Experiments via Anomalous Pattern Det …
CRRN: Multi-Scale Guided Concurrent Reflection Removal Network
| Title | CRRN: Multi-Scale Guided Concurrent Reflection Removal Network |
| Authors | Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, Alex C. Kot |
| Abstract | Removing the undesired reflections from images taken through the glass is of broad application to various computer vision tasks. Non-learning based methods utilize different handcrafted priors such as the separable sparse gradients caused by different levels of blurs, which often fail due to their limited description capability to the properties of real-world reflections. In this paper, we propose the Concurrent Reflection Removal Network (CRRN) to tackle this problem in a unified framework. Our proposed network integrates image appearance information and multi-scale gradient information with human perception inspired loss function, and is trained on a new dataset with 3250 reflection images taken under diverse real-world scenes. Extensive experiments on a public benchmark dataset show that the proposed method performs favorably against state-of-the-art methods. |
| Tasks | |
| Published | 2018-05-30 |
| URL | http://arxiv.org/abs/1805.11802v1 |
| http://arxiv.org/pdf/1805.11802v1.pdf | |
| PWC | https://paperswithcode.com/paper/crrn-multi-scale-guided-concurrent-reflection |
| Repo | |
| Framework | |
MBA: Mini-Batch AUC Optimization
| Title | MBA: Mini-Batch AUC Optimization |
| Authors | San Gultekin, Avishek Saha, Adwait Ratnaparkhi, John Paisley |
| Abstract | Area under the receiver operating characteristics curve (AUC) is an important metric for a wide range of signal processing and machine learning problems, and scalable methods for optimizing AUC have recently been proposed. However, handling very large datasets remains an open challenge for this problem. This paper proposes a novel approach to AUC maximization, based on sampling mini-batches of positive/negative instance pairs and computing U-statistics to approximate a global risk minimization problem. The resulting algorithm is simple, fast, and learning-rate free. We show that the number of samples required for good performance is independent of the number of pairs available, which is a quadratic function of the positive and negative instances. Extensive experiments show the practical utility of the proposed method. |
| Tasks | |
| Published | 2018-05-29 |
| URL | http://arxiv.org/abs/1805.11221v2 |
| http://arxiv.org/pdf/1805.11221v2.pdf | |
| PWC | https://paperswithcode.com/paper/mba-mini-batch-auc-optimization |
| Repo | |
| Framework | |
Packaging and Sharing Machine Learning Models via the Acumos AI Open Platform
| Title | Packaging and Sharing Machine Learning Models via the Acumos AI Open Platform |
| Authors | Shuai Zhao, Manoop Talasila, Guy Jacobson, Cristian Borcea, Syed Anwar Aftab, John F Murray |
| Abstract | Applying Machine Learning (ML) to business applications for automation usually faces difficulties when integrating diverse ML dependencies and services, mainly because of the lack of a common ML framework. In most cases, the ML models are developed for applications which are targeted for specific business domain use cases, leading to duplicated effort, and making reuse impossible. This paper presents Acumos, an open platform capable of packaging ML models into portable containerized microservices which can be easily shared via the platform’s catalog, and can be integrated into various business applications. We present a case study of packaging sentiment analysis and classification ML models via the Acumos platform, permitting easy sharing with others. We demonstrate that the Acumos platform reduces the technical burden on application developers when applying machine learning models to their business applications. Furthermore, the platform allows the reuse of readily available ML microservices in various business domains. |
| Tasks | Sentiment Analysis |
| Published | 2018-10-16 |
| URL | http://arxiv.org/abs/1810.07159v1 |
| http://arxiv.org/pdf/1810.07159v1.pdf | |
| PWC | https://paperswithcode.com/paper/packaging-and-sharing-machine-learning-models |
| Repo | |
| Framework | |
On the Limitations of Unsupervised Bilingual Dictionary Induction
| Title | On the Limitations of Unsupervised Bilingual Dictionary Induction |
| Authors | Anders Søgaard, Sebastian Ruder, Ivan Vulić |
| Abstract | Unsupervised machine translation—i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora—seems impossible, but nevertheless, Lample et al. (2018) recently proposed a fully unsupervised machine translation (MT) model. The model relies heavily on an adversarial, unsupervised alignment of word embedding spaces for bilingual dictionary induction (Conneau et al., 2018), which we examine here. Our results identify the limitations of current unsupervised MT: unsupervised bilingual dictionary induction performs much worse on morphologically rich languages that are not dependent marking, when monolingual corpora from different domains or different embedding algorithms are used. We show that a simple trick, exploiting a weak supervision signal from identical words, enables more robust induction, and establish a near-perfect correlation between unsupervised bilingual dictionary induction performance and a previously unexplored graph similarity metric. |
| Tasks | Graph Similarity, Machine Translation, Unsupervised Machine Translation |
| Published | 2018-05-09 |
| URL | http://arxiv.org/abs/1805.03620v1 |
| http://arxiv.org/pdf/1805.03620v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-limitations-of-unsupervised-bilingual |
| Repo | |
| Framework | |
Efficient Discovery of Heterogeneous Treatment Effects in Randomized Experiments via Anomalous Pattern Detection
| Title | Efficient Discovery of Heterogeneous Treatment Effects in Randomized Experiments via Anomalous Pattern Detection |
| Authors | Edward McFowland III, Sriram Somanchi, Daniel B. Neill |
| Abstract | In the recent literature on estimating heterogeneous treatment effects, each proposed method makes its own set of restrictive assumptions about the intervention’s effects and which subpopulations to explicitly estimate. Moreover, the majority of the literature provides no mechanism to identify which subpopulations are the most affected–beyond manual inspection–and provides little guarantee on the correctness of the identified subpopulations. Therefore, we propose Treatment Effect Subset Scan (TESS), a new method for discovering which subpopulation in a randomized experiment is most significantly affected by a treatment. We frame this challenge as a pattern detection problem where we efficiently maximize a nonparametric scan statistic over subpopulations. Furthermore, we identify the subpopulation which experiences the largest distributional change as a result of the intervention, while making minimal assumptions about the intervention’s effects or the underlying data generating process. In addition to the algorithm, we demonstrate that the asymptotic Type I and II error can be controlled, and provide sufficient conditions for detection consistency–i.e., exact identification of the affected subpopulation. Finally, we validate the efficacy of the method by discovering heterogeneous treatment effects in simulations and in real-world data from a well-known program evaluation study. |
| Tasks | |
| Published | 2018-03-24 |
| URL | http://arxiv.org/abs/1803.09159v2 |
| http://arxiv.org/pdf/1803.09159v2.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-discovery-of-heterogeneous |
| Repo | |
| Framework | |
Re-Identification with Consistent Attentive Siamese Networks
| Title | Re-Identification with Consistent Attentive Siamese Networks |
| Authors | Meng Zheng, Srikrishna Karanam, Ziyan Wu, Richard J. Radke |
| Abstract | We propose a new deep architecture for person re-identification (re-id). While re-id has seen much recent progress, spatial localization and view-invariant representation learning for robust cross-view matching remain key, unsolved problems. We address these questions by means of a new attention-driven Siamese learning architecture, called the Consistent Attentive Siamese Network. Our key innovations compared to existing, competing methods include (a) a flexible framework design that produces attention with only identity labels as supervision, (b) explicit mechanisms to enforce attention consistency among images of the same person, and (c) a new Siamese framework that integrates attention and attention consistency, producing principled supervisory signals as well as the first mechanism that can explain the reasoning behind the Siamese framework’s predictions. We conduct extensive evaluations on the CUHK03-NP, DukeMTMC-ReID, and Market-1501 datasets and report competitive performance. |
| Tasks | Person Re-Identification, Representation Learning |
| Published | 2018-11-19 |
| URL | http://arxiv.org/abs/1811.07487v4 |
| http://arxiv.org/pdf/1811.07487v4.pdf | |
| PWC | https://paperswithcode.com/paper/re-identification-with-consistent-attentive |
| Repo | |
| Framework | |
Evaluating approaches for supervised semantic labeling
| Title | Evaluating approaches for supervised semantic labeling |
| Authors | Natalia Ruemmele, Yuriy Tyshetskiy, Alex Collins |
| Abstract | Relational data sources are still one of the most popular ways to store enterprise or Web data, however, the issue with relational schema is the lack of a well-defined semantic description. A common ontology provides a way to represent the meaning of a relational schema and can facilitate the integration of heterogeneous data sources within a domain. Semantic labeling is achieved by mapping attributes from the data sources to the classes and properties in the ontology. We formulate this problem as a multi-class classification problem where previously labeled data sources are used to learn rules for labeling new data sources. The majority of existing approaches for semantic labeling have focused on data integration challenges such as naming conflicts and semantic heterogeneity. In addition, machine learning approaches typically have issues around class imbalance, lack of labeled instances and relative importance of attributes. To address these issues, we develop a new machine learning model with engineered features as well as two deep learning models which do not require extensive feature engineering. We evaluate our new approaches with the state-of-the-art. |
| Tasks | Feature Engineering |
| Published | 2018-01-29 |
| URL | http://arxiv.org/abs/1801.09788v1 |
| http://arxiv.org/pdf/1801.09788v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-approaches-for-supervised-semantic |
| Repo | |
| Framework | |
Random Polyhedral Scenes: An Image Generator for Active Vision System Experiments
| Title | Random Polyhedral Scenes: An Image Generator for Active Vision System Experiments |
| Authors | Markus D. Solbach, Stephen Voland, Jeff Edmonds, John K. Tsotsos |
| Abstract | We present a Polyhedral Scene Generator system which creates a random scene based on a few user parameters, renders the scene from random view points and creates a dataset containing the renderings and corresponding annotation files. We hope that this generator will enable research on how a program could parse a scene if it had multiple viewpoints to consider. For ambiguous scenes, typically people move their head or change their position to see the scene from different angles as well as seeing how it changes while they move; this research field is called active perception. The random scene generator presented is designed to support research in this field by generating images of scenes with known complexity characteristics and with verifiable properties with respect to the distribution of features across a population. Thus, it is well-suited for research in active perception without the requirement of a live 3D environment and mobile sensing agent, including comparative performance evaluations. The system is publicly available at https://polyhedral.eecs.yorku.ca. |
| Tasks | |
| Published | 2018-03-27 |
| URL | http://arxiv.org/abs/1803.10100v1 |
| http://arxiv.org/pdf/1803.10100v1.pdf | |
| PWC | https://paperswithcode.com/paper/random-polyhedral-scenes-an-image-generator |
| Repo | |
| Framework | |
Conditional Video Generation Using Action-Appearance Captions
| Title | Conditional Video Generation Using Action-Appearance Captions |
| Authors | Shohei Yamamoto, Antonio Tejero-de-Pablos, Yoshitaka Ushiku, Tatsuya Harada |
| Abstract | The field of automatic video generation has received a boost thanks to the recent Generative Adversarial Networks (GANs). However, most existing methods cannot control the contents of the generated video using a text caption, losing their usefulness to a large extent. This particularly affects human videos due to their great variety of actions and appearances. This paper presents Conditional Flow and Texture GAN (CFT-GAN), a GAN-based video generation method from action-appearance captions. We propose a novel way of generating video by encoding a caption (e.g., “a man in blue jeans is playing golf”) in a two-stage generation pipeline. Our CFT-GAN uses such caption to generate an optical flow (action) and a texture (appearance) for each frame. As a result, the output video reflects the content specified in the caption in a plausible way. Moreover, to train our method, we constructed a new dataset for human video generation with captions. We evaluated the proposed method qualitatively and quantitatively via an ablation study and a user study. The results demonstrate that CFT-GAN is able to successfully generate videos containing the action and appearances indicated in the captions. |
| Tasks | Optical Flow Estimation, Video Generation |
| Published | 2018-12-04 |
| URL | http://arxiv.org/abs/1812.01261v2 |
| http://arxiv.org/pdf/1812.01261v2.pdf | |
| PWC | https://paperswithcode.com/paper/conditional-video-generation-using-action |
| Repo | |
| Framework | |
Geometric Scattering for Graph Data Analysis
| Title | Geometric Scattering for Graph Data Analysis |
| Authors | Feng Gao, Guy Wolf, Matthew Hirn |
| Abstract | We explore the generalization of scattering transforms from traditional (e.g., image or audio) signals to graph data, analogous to the generalization of ConvNets in geometric deep learning, and the utility of extracted graph features in graph data analysis. In particular, we focus on the capacity of these features to retain informative variability and relations in the data (e.g., between individual graphs, or in aggregate), while relating our construction to previous theoretical results that establish the stability of similar transforms to families of graph deformations. We demonstrate the application the our geometric scattering features in graph classification of social network data, and in data exploration of biochemistry data. |
| Tasks | Graph Classification, Image Classification |
| Published | 2018-10-07 |
| URL | http://arxiv.org/abs/1810.03068v2 |
| http://arxiv.org/pdf/1810.03068v2.pdf | |
| PWC | https://paperswithcode.com/paper/geometric-scattering-for-graph-data-analysis |
| Repo | |
| Framework | |
Weakly supervised learning of indoor geometry by dual warping
| Title | Weakly supervised learning of indoor geometry by dual warping |
| Authors | Pulak Purkait, Ujwal Bonde, Christopher Zach |
| Abstract | A major element of depth perception and 3D understanding is the ability to predict the 3D layout of a scene and its contained objects for a novel pose. Indoor environments are particularly suitable for novel view prediction, since the set of objects in such environments is relatively restricted. In this work we address the task of 3D prediction especially for indoor scenes by leveraging only weak supervision. In the literature 3D scene prediction is usually solved via a 3D voxel grid. However, such methods are limited to estimating rather coarse 3D voxel grids, since predicting entire voxel spaces has large computational costs. Hence, our method operates in image-space rather than in voxel space, and the task of 3D estimation essentially becomes a depth image completion problem. We propose a novel approach to easily generate training data containing depth maps with realistic occlusions, and subsequently train a network for completing those occluded regions. Using multiple publicly available dataset~\cite{song2017semantic,Silberman:ECCV12} we benchmark our method against existing approaches and are able to obtain superior performance. We further demonstrate the flexibility of our method by presenting results for new view synthesis of RGB-D images. |
| Tasks | |
| Published | 2018-08-10 |
| URL | http://arxiv.org/abs/1808.03609v1 |
| http://arxiv.org/pdf/1808.03609v1.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-learning-of-indoor-geometry |
| Repo | |
| Framework | |
Complementary Segmentation of Primary Video Objects with Reversible Flows
| Title | Complementary Segmentation of Primary Video Objects with Reversible Flows |
| Authors | Jia Li, Junjie Wu, Anlin Zheng, Yafei Song, Yu Zhang, Xiaowu Chen |
| Abstract | Segmenting primary objects in a video is an important yet challenging problem in computer vision, as it exhibits various levels of foreground/background ambiguities. To reduce such ambiguities, we propose a novel formulation via exploiting foreground and background context as well as their complementary constraint. Under this formulation, a unified objective function is further defined to encode each cue. For implementation, we design a Complementary Segmentation Network (CSNet) with two separate branches, which can simultaneously encode the foreground and background information along with joint spatial constraints. The CSNet is trained on massive images with manually annotated salient objects in an end-to-end manner. By applying CSNet on each video frame, the spatial foreground and background maps can be initialized. To enforce temporal consistency effectively and efficiently, we divide each frame into superpixels and construct neighborhood reversible flow that reflects the most reliable temporal correspondences between superpixels in far-away frames. With such flow, the initialized foregroundness and backgroundness can be propagated along the temporal dimension so that primary video objects gradually pop-out and distractors are well suppressed. Extensive experimental results on three video datasets show that the proposed approach achieves impressive performance in comparisons with 18 state-of-the-art models. |
| Tasks | Video Semantic Segmentation |
| Published | 2018-11-23 |
| URL | http://arxiv.org/abs/1811.09521v1 |
| http://arxiv.org/pdf/1811.09521v1.pdf | |
| PWC | https://paperswithcode.com/paper/complementary-segmentation-of-primary-video |
| Repo | |
| Framework | |
Learning in Memristive Neural Network Architectures using Analog Backpropagation Circuits
| Title | Learning in Memristive Neural Network Architectures using Analog Backpropagation Circuits |
| Authors | Olga Krestinskaya, Khaled Nabil Salama, Alex Pappachen James |
| Abstract | The on-chip implementation of learning algorithms would speed-up the training of neural networks in crossbar arrays. The circuit level design and implementation of backpropagation algorithm using gradient descent operation for neural network architectures is an open problem. In this paper, we proposed the analog backpropagation learning circuits for various memristive learning architectures, such as Deep Neural Network (DNN), Binary Neural Network (BNN), Multiple Neural Network (MNN), Hierarchical Temporal Memory (HTM) and Long-Short Term Memory (LSTM). The circuit design and verification is done using TSMC 180nm CMOS process models, and TiO2 based memristor models. The application level validations of the system are done using XOR problem, MNIST character and Yale face image databases |
| Tasks | |
| Published | 2018-08-31 |
| URL | http://arxiv.org/abs/1808.10631v1 |
| http://arxiv.org/pdf/1808.10631v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-in-memristive-neural-network |
| Repo | |
| Framework | |
Creatures great and SMAL: Recovering the shape and motion of animals from video
| Title | Creatures great and SMAL: Recovering the shape and motion of animals from video |
| Authors | Benjamin Biggs, Thomas Roddick, Andrew Fitzgibbon, Roberto Cipolla |
| Abstract | We present a system to recover the 3D shape and motion of a wide variety of quadrupeds from video. The system comprises a machine learning front-end which predicts candidate 2D joint positions, a discrete optimization which finds kinematically plausible joint correspondences, and an energy minimization stage which fits a detailed 3D model to the image. In order to overcome the limited availability of motion capture training data from animals, and the difficulty of generating realistic synthetic training images, the system is designed to work on silhouette data. The joint candidate predictor is trained on synthetically generated silhouette images, and at test time, deep learning methods or standard video segmentation tools are used to extract silhouettes from real data. The system is tested on animal videos from several species, and shows accurate reconstructions of 3D shape and pose. |
| Tasks | Motion Capture, Video Semantic Segmentation |
| Published | 2018-11-14 |
| URL | http://arxiv.org/abs/1811.05804v1 |
| http://arxiv.org/pdf/1811.05804v1.pdf | |
| PWC | https://paperswithcode.com/paper/creatures-great-and-smal-recovering-the-shape |
| Repo | |
| Framework | |
Sequential Learning of Principal Curves: Summarizing Data Streams on the Fly
| Title | Sequential Learning of Principal Curves: Summarizing Data Streams on the Fly |
| Authors | Benjamin Guedj, Le Li |
| Abstract | When confronted with massive data streams, summarizing data with dimension reduction methods such as PCA raises theoretical and algorithmic pitfalls. Principal curves act as a nonlinear generalization of PCA and the present paper proposes a novel algorithm to automatically and sequentially learn principal curves from data streams. We show that our procedure is supported by regret bounds with optimal sublinear remainder terms. A greedy local search implementation (called \texttt{slpc}, for Sequential Learning Principal Curves) that incorporates both sleeping experts and multi-armed bandit ingredients is presented, along with its regret computation and performance on synthetic and real-life data. |
| Tasks | Dimensionality Reduction |
| Published | 2018-05-18 |
| URL | https://arxiv.org/abs/1805.07418v2 |
| https://arxiv.org/pdf/1805.07418v2.pdf | |
| PWC | https://paperswithcode.com/paper/sequential-learning-of-principal-curves |
| Repo | |
| Framework | |
