Paper Group AWR 43
Constrained Bayesian Optimization for Automatic Chemical Design. Recurrent Filter Learning for Visual Tracking. Probabilistic Matrix Factorization for Automated Machine Learning. Efficient Antihydrogen Detection in Antimatter Physics by Deep Learning. Engineering fast multilevel support vector machines. An All-in-One Network for Dehazing and Beyond …
Constrained Bayesian Optimization for Automatic Chemical Design
| Title | Constrained Bayesian Optimization for Automatic Chemical Design |
| Authors | Ryan-Rhys Griffiths, José Miguel Hernández-Lobato |
| Abstract | Automatic Chemical Design is a framework for generating novel molecules with optimized properties. The original scheme, featuring Bayesian optimization over the latent space of a variational autoencoder, suffers from the pathology that it tends to produce invalid molecular structures. First, we demonstrate empirically that this pathology arises when the Bayesian optimization scheme queries latent points far away from the data on which the variational autoencoder has been trained. Secondly, by reformulating the search procedure as a constrained Bayesian optimization problem, we show that the effects of this pathology can be mitigated, yielding marked improvements in the validity of the generated molecules. We posit that constrained Bayesian optimization is a good approach for solving this class of training set mismatch in many generative tasks involving Bayesian optimization over the latent space of a variational autoencoder. |
| Tasks | |
| Published | 2017-09-16 |
| URL | https://arxiv.org/abs/1709.05501v6 |
| https://arxiv.org/pdf/1709.05501v6.pdf | |
| PWC | https://paperswithcode.com/paper/constrained-bayesian-optimization-for |
| Repo | https://github.com/Ryan-Rhys/Constrained-Bayesian-Optimisation-for-Automatic-Chemical-Design |
| Framework | none |
Recurrent Filter Learning for Visual Tracking
| Title | Recurrent Filter Learning for Visual Tracking |
| Authors | Tianyu Yang, Antoni B. Chan |
| Abstract | Recently using convolutional neural networks (CNNs) has gained popularity in visual tracking, due to its robust feature representation of images. Recent methods perform online tracking by fine-tuning a pre-trained CNN model to the specific target object using stochastic gradient descent (SGD) back-propagation, which is usually time-consuming. In this paper, we propose a recurrent filter generation methods for visual tracking. We directly feed the target’s image patch to a recurrent neural network (RNN) to estimate an object-specific filter for tracking. As the video sequence is a spatiotemporal data, we extend the matrix multiplications of the fully-connected layers of the RNN to a convolution operation on feature maps, which preserves the target’s spatial structure and also is memory-efficient. The tracked object in the subsequent frames will be fed into the RNN to adapt the generated filters to appearance variations of the target. Note that once the off-line training process of our network is finished, there is no need to fine-tune the network for specific objects, which makes our approach more efficient than methods that use iterative fine-tuning to online learn the target. Extensive experiments conducted on widely used benchmarks, OTB and VOT, demonstrate encouraging results compared to other recent methods. |
| Tasks | Visual Tracking |
| Published | 2017-08-13 |
| URL | http://arxiv.org/abs/1708.03874v1 |
| http://arxiv.org/pdf/1708.03874v1.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-filter-learning-for-visual-tracking |
| Repo | https://github.com/skyoung/RFL |
| Framework | tf |
Probabilistic Matrix Factorization for Automated Machine Learning
| Title | Probabilistic Matrix Factorization for Automated Machine Learning |
| Authors | Nicolo Fusi, Rishit Sheth, Huseyn Melih Elibol |
| Abstract | In order to achieve state-of-the-art performance, modern machine learning techniques require careful data pre-processing and hyperparameter tuning. Moreover, given the ever increasing number of machine learning models being developed, model selection is becoming increasingly important. Automating the selection and tuning of machine learning pipelines consisting of data pre-processing methods and machine learning models, has long been one of the goals of the machine learning community. In this paper, we tackle this meta-learning task by combining ideas from collaborative filtering and Bayesian optimization. Using probabilistic matrix factorization techniques and acquisition functions from Bayesian optimization, we exploit experiments performed in hundreds of different datasets to guide the exploration of the space of possible pipelines. In our experiments, we show that our approach quickly identifies high-performing pipelines across a wide range of datasets, significantly outperforming the current state-of-the-art. |
| Tasks | Meta-Learning, Model Selection |
| Published | 2017-05-15 |
| URL | http://arxiv.org/abs/1705.05355v2 |
| http://arxiv.org/pdf/1705.05355v2.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-matrix-factorization-for |
| Repo | https://github.com/minerito/global_ai_night |
| Framework | none |
Efficient Antihydrogen Detection in Antimatter Physics by Deep Learning
| Title | Efficient Antihydrogen Detection in Antimatter Physics by Deep Learning |
| Authors | Peter Sadowski, Balint Radics, Ananya, Yasunori Yamazaki, Pierre Baldi |
| Abstract | Antihydrogen is at the forefront of antimatter research at the CERN Antiproton Decelerator. Experiments aiming to test the fundamental CPT symmetry and antigravity effects require the efficient detection of antihydrogen annihilation events, which is performed using highly granular tracking detectors installed around an antimatter trap. Improving the efficiency of the antihydrogen annihilation detection plays a central role in the final sensitivity of the experiments. We propose deep learning as a novel technique to analyze antihydrogen annihilation data, and compare its performance with a traditional track and vertex reconstruction method. We report that the deep learning approach yields significant improvement, tripling event coverage while simultaneously improving performance by over 5% in terms of Area Under Curve (AUC). |
| Tasks | |
| Published | 2017-06-06 |
| URL | http://arxiv.org/abs/1706.01826v1 |
| http://arxiv.org/pdf/1706.01826v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-antihydrogen-detection-in |
| Repo | https://github.com/bayesianGirl/Antihydrogen-Detection-by-Deep-Learning |
| Framework | pytorch |
Engineering fast multilevel support vector machines
| Title | Engineering fast multilevel support vector machines |
| Authors | E. Sadrfaridpour, T. Razzaghi, I. Safro |
| Abstract | The computational complexity of solving nonlinear support vector machine (SVM) is prohibitive on large-scale data. In particular, this issue becomes very sensitive when the data represents additional difficulties such as highly imbalanced class sizes. Typically, nonlinear kernels produce significantly higher classification quality to linear kernels but introduce extra kernel and model parameters which requires computationally expensive fitting. This increases the quality but also reduces the performance dramatically. We introduce a generalized fast multilevel framework for regular and weighted SVM and discuss several versions of its algorithmic components that lead to a good trade-off between quality and time. Our framework is implemented using PETSc which allows an easy integration with scientific computing tasks. The experimental results demonstrate significant speed up compared to the state-of-the-art nonlinear SVM libraries. Reproducibility: our source code, documentation and parameters are available at https:// github.com/esadr/mlsvm. |
| Tasks | |
| Published | 2017-07-24 |
| URL | http://arxiv.org/abs/1707.07657v3 |
| http://arxiv.org/pdf/1707.07657v3.pdf | |
| PWC | https://paperswithcode.com/paper/engineering-fast-multilevel-support-vector |
| Repo | https://github.com/esadr/mlsvm |
| Framework | none |
An All-in-One Network for Dehazing and Beyond
| Title | An All-in-One Network for Dehazing and Beyond |
| Authors | Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, Dan Feng |
| Abstract | This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net). It is designed based on a re-formulated atmospheric scattering model. Instead of estimating the transmission matrix and the atmospheric light separately as most previous models did, AOD-Net directly generates the clean image through a light-weight CNN. Such a novel end-to-end design makes it easy to embed AOD-Net into other deep models, e.g., Faster R-CNN, for improving high-level task performance on hazy images. Experimental results on both synthesized and natural hazy image datasets demonstrate our superior performance than the state-of-the-art in terms of PSNR, SSIM and the subjective visual quality. Furthermore, when concatenating AOD-Net with Faster R-CNN and training the joint pipeline from end to end, we witness a large improvement of the object detection performance on hazy images. |
| Tasks | Image Dehazing, Object Detection |
| Published | 2017-07-20 |
| URL | http://arxiv.org/abs/1707.06543v1 |
| http://arxiv.org/pdf/1707.06543v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-all-in-one-network-for-dehazing-and-beyond |
| Repo | https://github.com/elras/desmokenet |
| Framework | caffe2 |
Evaluating prose style transfer with the Bible
| Title | Evaluating prose style transfer with the Bible |
| Authors | Keith Carlson, Allen Riddell, Daniel Rockmore |
| Abstract | In the prose style transfer task a system, provided with text input and a target prose style, produces output which preserves the meaning of the input text but alters the style. These systems require parallel data for evaluation of results and usually make use of parallel data for training. Currently, there are few publicly available corpora for this task. In this work, we identify a high-quality source of aligned, stylistically distinct text in different versions of the Bible. We provide a standardized split, into training, development and testing data, of the public domain versions in our corpus. This corpus is highly parallel since many Bible versions are included. Sentences are aligned due to the presence of chapter and verse numbers within all versions of the text. In addition to the corpus, we present the results, as measured by the BLEU and PINC metrics, of several models trained on our data which can serve as baselines for future research. While we present these data as a style transfer corpus, we believe that it is of unmatched quality and may be useful for other natural language tasks as well. |
| Tasks | Style Transfer |
| Published | 2017-11-13 |
| URL | http://arxiv.org/abs/1711.04731v2 |
| http://arxiv.org/pdf/1711.04731v2.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-prose-style-transfer-with-the |
| Repo | https://github.com/keithecarlson/StyleTransferBibleData |
| Framework | tf |
Incremental 3D Line Segment Extraction from Semi-dense SLAM
| Title | Incremental 3D Line Segment Extraction from Semi-dense SLAM |
| Authors | Shida He, Xuebin Qin, Zichen Zhang, Martin Jagersand |
| Abstract | Although semi-dense Simultaneous Localization and Mapping (SLAM) has been becoming more popular over the last few years, there is a lack of efficient methods for representing and processing their large scale point clouds. In this paper, we propose using 3D line segments to simplify the point clouds generated by semi-dense SLAM. Specifically, we present a novel incremental approach for 3D line segment extraction. This approach reduces a 3D line segment fitting problem into two 2D line segment fitting problems and takes advantage of both images and depth maps. In our method, 3D line segments are fitted incrementally along detected edge segments via minimizing fitting errors on two planes. By clustering the detected line segments, the resulting 3D representation of the scene achieves a good balance between compactness and completeness. Our experimental results show that the 3D line segments generated by our method are highly accurate. As an application, we demonstrate that these line segments greatly improve the quality of 3D surface reconstruction compared to a feature point based baseline. |
| Tasks | Simultaneous Localization and Mapping |
| Published | 2017-08-10 |
| URL | http://arxiv.org/abs/1708.03275v3 |
| http://arxiv.org/pdf/1708.03275v3.pdf | |
| PWC | https://paperswithcode.com/paper/incremental-3d-line-segment-extraction-from |
| Repo | https://github.com/shidahe/semidense-lines |
| Framework | none |
Shortcut-Stacked Sentence Encoders for Multi-Domain Inference
| Title | Shortcut-Stacked Sentence Encoders for Multi-Domain Inference |
| Authors | Yixin Nie, Mohit Bansal |
| Abstract | We present a simple sequential sentence encoder for multi-domain natural language inference. Our encoder is based on stacked bidirectional LSTM-RNNs with shortcut connections and fine-tuning of word embeddings. The overall supervised model uses the above encoder to encode two input sentences into two vectors, and then uses a classifier over the vector combination to label the relationship between these two sentences as that of entailment, contradiction, or neural. Our Shortcut-Stacked sentence encoders achieve strong improvements over existing encoders on matched and mismatched multi-domain natural language inference (top non-ensemble single-model result in the EMNLP RepEval 2017 Shared Task (Nangia et al., 2017)). Moreover, they achieve the new state-of-the-art encoding result on the original SNLI dataset (Bowman et al., 2015). |
| Tasks | Natural Language Inference, Word Embeddings |
| Published | 2017-08-07 |
| URL | http://arxiv.org/abs/1708.02312v2 |
| http://arxiv.org/pdf/1708.02312v2.pdf | |
| PWC | https://paperswithcode.com/paper/shortcut-stacked-sentence-encoders-for-multi |
| Repo | https://github.com/KhenAharon/Deep-Learning-SNLI-Residual-Stacked-Encoders |
| Framework | pytorch |
Provably Accurate Double-Sparse Coding
| Title | Provably Accurate Double-Sparse Coding |
| Authors | Thanh V. Nguyen, Raymond K. W. Wong, Chinmay Hegde |
| Abstract | Sparse coding is a crucial subroutine in algorithms for various signal processing, deep learning, and other machine learning applications. The central goal is to learn an overcomplete dictionary that can sparsely represent a given input dataset. However, a key challenge is that storage, transmission, and processing of the learned dictionary can be untenably high if the data dimension is high. In this paper, we consider the double-sparsity model introduced by Rubinstein et al. (2010b) where the dictionary itself is the product of a fixed, known basis and a data-adaptive sparse component. First, we introduce a simple algorithm for double-sparse coding that can be amenable to efficient implementation via neural architectures. Second, we theoretically analyze its performance and demonstrate asymptotic sample complexity and running time benefits over existing (provable) approaches for sparse coding. To our knowledge, our work introduces the first computationally efficient algorithm for double-sparse coding that enjoys rigorous statistical guarantees. Finally, we support our analysis via several numerical experiments on simulated data, confirming that our method can indeed be useful in problem sizes encountered in practical applications. |
| Tasks | |
| Published | 2017-11-09 |
| URL | http://arxiv.org/abs/1711.03638v2 |
| http://arxiv.org/pdf/1711.03638v2.pdf | |
| PWC | https://paperswithcode.com/paper/provably-accurate-double-sparse-coding |
| Repo | https://github.com/thanh-isu/double-sparse-coding |
| Framework | none |
Not-So-Random Features
| Title | Not-So-Random Features |
| Authors | Brian Bullins, Cyril Zhang, Yi Zhang |
| Abstract | We propose a principled method for kernel learning, which relies on a Fourier-analytic characterization of translation-invariant or rotation-invariant kernels. Our method produces a sequence of feature maps, iteratively refining the SVM margin. We provide rigorous guarantees for optimality and generalization, interpreting our algorithm as online equilibrium-finding dynamics in a certain two-player min-max game. Evaluations on synthetic and real-world datasets demonstrate scalability and consistent improvements over related random features-based methods. |
| Tasks | |
| Published | 2017-10-27 |
| URL | http://arxiv.org/abs/1710.10230v2 |
| http://arxiv.org/pdf/1710.10230v2.pdf | |
| PWC | https://paperswithcode.com/paper/not-so-random-features |
| Repo | https://github.com/yz-ignescent/Not-So-Random-Features |
| Framework | pytorch |
CycleGAN Face-off
| Title | CycleGAN Face-off |
| Authors | Xiaohan Jin, Ye Qi, Shangxuan Wu |
| Abstract | Face-off is an interesting case of style transfer where the facial expressions and attributes of one person could be fully transformed to another face. We are interested in the unsupervised training process which only requires two sequences of unaligned video frames from each person and learns what shared attributes to extract automatically. In this project, we explored various improvements for adversarial training (i.e. CycleGAN[Zhu et al., 2017]) to capture details in facial expressions and head poses and thus generate transformation videos of higher consistency and stability. |
| Tasks | Style Transfer |
| Published | 2017-12-09 |
| URL | http://arxiv.org/abs/1712.03451v5 |
| http://arxiv.org/pdf/1712.03451v5.pdf | |
| PWC | https://paperswithcode.com/paper/cyclegan-face-off |
| Repo | https://github.com/ShangxuanWu/CycleGAN-Face-off |
| Framework | pytorch |
SalGAN: Visual Saliency Prediction with Generative Adversarial Networks
| Title | SalGAN: Visual Saliency Prediction with Generative Adversarial Networks |
| Authors | Junting Pan, Cristian Canton Ferrer, Kevin McGuinness, Noel E. O’Connor, Jordi Torres, Elisa Sayrol, Xavier Giro-i-Nieto |
| Abstract | We introduce SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples. The first stage of the network consists of a generator model whose weights are learned by back-propagation computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency maps. The resulting prediction is processed by a discriminator network trained to solve a binary classification task between the saliency maps generated by the generative stage and the ground truth ones. Our experiments show how adversarial training allows reaching state-of-the-art performance across different metrics when combined with a widely-used loss function like BCE. Our results can be reproduced with the source code and trained models available at https://imatge-upc.github.io/saliency-salgan-2017/. |
| Tasks | Saliency Prediction |
| Published | 2017-01-04 |
| URL | http://arxiv.org/abs/1701.01081v3 |
| http://arxiv.org/pdf/1701.01081v3.pdf | |
| PWC | https://paperswithcode.com/paper/salgan-visual-saliency-prediction-with |
| Repo | https://github.com/imatge-upc/salgan |
| Framework | pytorch |
Advances in Pre-Training Distributed Word Representations
| Title | Advances in Pre-Training Distributed Word Representations |
| Authors | Tomas Mikolov, Edouard Grave, Piotr Bojanowski, Christian Puhrsch, Armand Joulin |
| Abstract | Many Natural Language Processing applications nowadays rely on pre-trained word representations estimated from large text corpora such as news collections, Wikipedia and Web Crawl. In this paper, we show how to train high-quality word vector representations by using a combination of known tricks that are however rarely used together. The main result of our work is the new set of publicly available pre-trained models that outperform the current state of the art by a large margin on a number of tasks. |
| Tasks | |
| Published | 2017-12-26 |
| URL | http://arxiv.org/abs/1712.09405v1 |
| http://arxiv.org/pdf/1712.09405v1.pdf | |
| PWC | https://paperswithcode.com/paper/advances-in-pre-training-distributed-word |
| Repo | https://github.com/L-sky/concept-finder |
| Framework | none |
Cognitive Mapping and Planning for Visual Navigation
| Title | Cognitive Mapping and Planning for Visual Navigation |
| Authors | Saurabh Gupta, Varun Tolani, James Davidson, Sergey Levine, Rahul Sukthankar, Jitendra Malik |
| Abstract | We introduce a neural architecture for navigation in novel environments. Our proposed architecture learns to map from first-person views and plans a sequence of actions towards goals in the environment. The Cognitive Mapper and Planner (CMP) is based on two key ideas: a) a unified joint architecture for mapping and planning, such that the mapping is driven by the needs of the task, and b) a spatial memory with the ability to plan given an incomplete set of observations about the world. CMP constructs a top-down belief map of the world and applies a differentiable neural net planner to produce the next action at each time step. The accumulated belief of the world enables the agent to track visited regions of the environment. We train and test CMP on navigation problems in simulation environments derived from scans of real world buildings. Our experiments demonstrate that CMP outperforms alternate learning-based architectures, as well as, classical mapping and path planning approaches in many cases. Furthermore, it naturally extends to semantically specified goals, such as ‘going to a chair’. We also deploy CMP on physical robots in indoor environments, where it achieves reasonable performance, even though it is trained entirely in simulation. |
| Tasks | Visual Navigation |
| Published | 2017-02-13 |
| URL | http://arxiv.org/abs/1702.03920v3 |
| http://arxiv.org/pdf/1702.03920v3.pdf | |
| PWC | https://paperswithcode.com/paper/cognitive-mapping-and-planning-for-visual |
| Repo | https://github.com/zuoxingdong/VIN_PyTorch_Visdom |
| Framework | pytorch |
