Paper Group AWR 283
A Polynomial-Based Approach for Architectural Design and Learning with Deep Neural Networks. Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration. Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks. Structured Fusion Networks for Dialog. Deep Residual Output Layers for Neural Languag …
A Polynomial-Based Approach for Architectural Design and Learning with Deep Neural Networks
| Title | A Polynomial-Based Approach for Architectural Design and Learning with Deep Neural Networks |
| Authors | Joseph Daws Jr., Clayton G. Webster |
| Abstract | In this effort we propose a novel approach for reconstructing multivariate functions from training data, by identifying both a suitable network architecture and an initialization using polynomial-based approximations. Training deep neural networks using gradient descent can be interpreted as moving the set of network parameters along the loss landscape in order to minimize the loss functional. The initialization of parameters is important for iterative training methods based on descent. Our procedure produces a network whose initial state is a polynomial representation of the training data. The major advantage of this technique is from this initialized state the network may be improved using standard training procedures. Since the network already approximates the data, training is more likely to produce a set of parameters associated with a desirable local minimum. We provide the details of the theory necessary for constructing such networks and also consider several numerical examples that reveal our approach ultimately produces networks which can be effectively trained from our initialized state to achieve an improved approximation for a large class of target functions. |
| Tasks | |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10457v2 |
| https://arxiv.org/pdf/1905.10457v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-polynomial-based-approach-for-architectural |
| Repo | https://github.com/joedaws/poly-init-nets |
| Framework | pytorch |
Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration
| Title | Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration |
| Authors | Xing Liu, Masanori Suganuma, Zhun Sun, Takayuki Okatani |
| Abstract | In this paper, we study design of deep neural networks for tasks of image restoration. We propose a novel style of residual connections dubbed “dual residual connection”, which exploits the potential of paired operations, e.g., up- and down-sampling or convolution with large- and small-size kernels. We design a modular block implementing this connection style; it is equipped with two containers to which arbitrary paired operations are inserted. Adopting the “unraveled” view of the residual networks proposed by Veit et al., we point out that a stack of the proposed modular blocks allows the first operation in a block interact with the second operation in any subsequent blocks. Specifying the two operations in each of the stacked blocks, we build a complete network for each individual task of image restoration. We experimentally evaluate the proposed approach on five image restoration tasks using nine datasets. The results show that the proposed networks with properly chosen paired operations outperform previous methods on almost all of the tasks and datasets. |
| Tasks | Image Restoration |
| Published | 2019-03-21 |
| URL | http://arxiv.org/abs/1903.08817v2 |
| http://arxiv.org/pdf/1903.08817v2.pdf | |
| PWC | https://paperswithcode.com/paper/dual-residual-networks-leveraging-the |
| Repo | https://github.com/liu-vis/DualResidualNetworks |
| Framework | pytorch |
Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks
| Title | Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks |
| Authors | Gaël Letarte, Pascal Germain, Benjamin Guedj, François Laviolette |
| Abstract | We present a comprehensive study of multilayer neural networks with binary activation, relying on the PAC-Bayesian theory. Our contributions are twofold: (i) we develop an end-to-end framework to train a binary activated deep neural network, (ii) we provide nonvacuous PAC-Bayesian generalization bounds for binary activated deep neural networks. Our results are obtained by minimizing the expected loss of an architecture-dependent aggregation of binary activated deep neural networks. Our analysis inherently overcomes the fact that binary activation function is non-differentiable. The performance of our approach is assessed on a thorough numerical experiment protocol on real-life datasets. |
| Tasks | |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10259v5 |
| https://arxiv.org/pdf/1905.10259v5.pdf | |
| PWC | https://paperswithcode.com/paper/dichotomize-and-generalize-pac-bayesian |
| Repo | https://github.com/gletarte/dichotomize-and-generalize |
| Framework | pytorch |
Structured Fusion Networks for Dialog
| Title | Structured Fusion Networks for Dialog |
| Authors | Shikib Mehri, Tejas Srinivasan, Maxine Eskenazi |
| Abstract | Neural dialog models have exhibited strong performance, however their end-to-end nature lacks a representation of the explicit structure of dialog. This results in a loss of generalizability, controllability and a data-hungry nature. Conversely, more traditional dialog systems do have strong models of explicit structure. This paper introduces several approaches for explicitly incorporating structure into neural models of dialog. Structured Fusion Networks first learn neural dialog modules corresponding to the structured components of traditional dialog systems and then incorporate these modules in a higher-level generative model. Structured Fusion Networks obtain strong results on the MultiWOZ dataset, both with and without reinforcement learning. Structured Fusion Networks are shown to have several valuable properties, including better domain generalizability, improved performance in reduced data scenarios and robustness to divergence during reinforcement learning. |
| Tasks | |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.10016v1 |
| https://arxiv.org/pdf/1907.10016v1.pdf | |
| PWC | https://paperswithcode.com/paper/structured-fusion-networks-for-dialog |
| Repo | https://github.com/Shikib/structured_fusion_networks |
| Framework | none |
Deep Residual Output Layers for Neural Language Generation
| Title | Deep Residual Output Layers for Neural Language Generation |
| Authors | Nikolaos Pappas, James Henderson |
| Abstract | Many tasks, including language generation, benefit from learning the structure of the output space, particularly when the space of output labels is large and the data is sparse. State-of-the-art neural language models indirectly capture the output space structure in their classifier weights since they lack parameter sharing across output labels. Learning shared output label mappings helps, but existing methods have limited expressivity and are prone to overfitting. In this paper, we investigate the usefulness of more powerful shared mappings for output labels, and propose a deep residual output mapping with dropout between layers to better capture the structure of the output space and avoid overfitting. Evaluations on three language generation tasks show that our output label mapping can match or improve state-of-the-art recurrent and self-attention architectures, and suggest that the classifier does not necessarily need to be high-rank to better model natural language if it is better at capturing the structure of the output space. |
| Tasks | Language Modelling, Machine Translation, Text Generation |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05513v2 |
| https://arxiv.org/pdf/1905.05513v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-residual-output-layers-for-neural |
| Repo | https://github.com/idiap/drill |
| Framework | pytorch |
Analysis of Confident-Classifiers for Out-of-distribution Detection
| Title | Analysis of Confident-Classifiers for Out-of-distribution Detection |
| Authors | Sachin Vernekar, Ashish Gaurav, Taylor Denouden, Buu Phan, Vahdat Abdelzad, Rick Salay, Krzysztof Czarnecki |
| Abstract | Discriminatively trained neural classifiers can be trusted, only when the input data comes from the training distribution (in-distribution). Therefore, detecting out-of-distribution (OOD) samples is very important to avoid classification errors. In the context of OOD detection for image classification, one of the recent approaches proposes training a classifier called “confident-classifier” by minimizing the standard cross-entropy loss on in-distribution samples and minimizing the KL divergence between the predictive distribution of OOD samples in the low-density regions of in-distribution and the uniform distribution (maximizing the entropy of the outputs). Thus, the samples could be detected as OOD if they have low confidence or high entropy. In this paper, we analyze this setting both theoretically and experimentally. We conclude that the resulting confident-classifier still yields arbitrarily high confidence for OOD samples far away from the in-distribution. We instead suggest training a classifier by adding an explicit “reject” class for OOD samples. |
| Tasks | Image Classification, Out-of-Distribution Detection |
| Published | 2019-04-27 |
| URL | http://arxiv.org/abs/1904.12220v1 |
| http://arxiv.org/pdf/1904.12220v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-confident-classifiers-for-out-of |
| Repo | https://github.com/sverneka/ConfidentClassifierICLR19 |
| Framework | none |
Modeling Conceptual Understanding in Image Reference Games
| Title | Modeling Conceptual Understanding in Image Reference Games |
| Authors | Rodolfo Corona, Stephan Alaniz, Zeynep Akata |
| Abstract | An agent who interacts with a wide population of other agents needs to be aware that there may be variations in their understanding of the world. Furthermore, the machinery which they use to perceive may be inherently different, as is the case between humans and machines. In this work, we present both an image reference game between a speaker and a population of listeners where reasoning about the concepts other agents can comprehend is necessary and a model formulation with this capability. We focus on reasoning about the conceptual understanding of others, as well as adapting to novel gameplay partners and dealing with differences in perceptual machinery. Our experiments on three benchmark image/attribute datasets suggest that our learner indeed encodes information directly pertaining to the understanding of other agents, and that leveraging this information is crucial for maximizing gameplay performance. |
| Tasks | |
| Published | 2019-10-10 |
| URL | https://arxiv.org/abs/1910.04872v2 |
| https://arxiv.org/pdf/1910.04872v2.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-conceptual-understanding-in-image |
| Repo | https://github.com/rcorona/conceptual_img_ref |
| Framework | pytorch |
Sequential Scenario-Specific Meta Learner for Online Recommendation
| Title | Sequential Scenario-Specific Meta Learner for Online Recommendation |
| Authors | Zhengxiao Du, Xiaowei Wang, Hongxia Yang, Jingren Zhou, Jie Tang |
| Abstract | Cold-start problems are long-standing challenges for practical recommendations. Most existing recommendation algorithms rely on extensive observed data and are brittle to recommendation scenarios with few interactions. This paper addresses such problems using few-shot learning and meta learning. Our approach is based on the insight that having a good generalization from a few examples relies on both a generic model initialization and an effective strategy for adapting this model to newly arising tasks. To accomplish this, we combine the scenario-specific learning with a model-agnostic sequential meta-learning and unify them into an integrated end-to-end framework, namely Scenario-specific Sequential Meta learner (or s^2 meta). By doing so, our meta-learner produces a generic initial model through aggregating contextual information from a variety of prediction tasks while effectively adapting to specific tasks by leveraging learning-to-learn knowledge. Extensive experiments on various real-world datasets demonstrate that our proposed model can achieve significant gains over the state-of-the-arts for cold-start problems in online recommendation. Deployment is at the Guess You Like session, the front page of the Mobile Taobao. |
| Tasks | Few-Shot Learning, Meta-Learning |
| Published | 2019-06-02 |
| URL | https://arxiv.org/abs/1906.00391v1 |
| https://arxiv.org/pdf/1906.00391v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600391 |
| Repo | https://github.com/THUDM/ScenarioMeta |
| Framework | pytorch |
Underwater Image Super-Resolution using Deep Residual Multipliers
| Title | Underwater Image Super-Resolution using Deep Residual Multipliers |
| Authors | Md Jahidul Islam, Sadman Sakib Enan, Peigen Luo, Junaed Sattar |
| Abstract | We present a deep residual network-based generative model for single image super-resolution (SISR) of underwater imagery for use by autonomous underwater robots. We also provide an adversarial training pipeline for learning SISR from paired data. In order to supervise the training, we formulate an objective function that evaluates the \textit{perceptual quality} of an image based on its global content, color, and local style information. Additionally, we present USR-248, a large-scale dataset of three sets of underwater images of ‘high’ (640x480) and ‘low’ (80x60, 160x120, and 320x240) spatial resolution. USR-248 contains paired instances for supervised training of 2x, 4x, or 8x SISR models. Furthermore, we validate the effectiveness of our proposed model through qualitative and quantitative experiments and compare the results with several state-of-the-art models’ performances. We also analyze its practical feasibility for applications such as scene understanding and attention modeling in noisy visual conditions. |
| Tasks | Image Super-Resolution, Scene Understanding, Super-Resolution |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09437v3 |
| https://arxiv.org/pdf/1909.09437v3.pdf | |
| PWC | https://paperswithcode.com/paper/underwater-image-super-resolution-using-deep |
| Repo | https://github.com/xahidbuffon/srdrm |
| Framework | tf |
Learned Image Downscaling for Upscaling using Content Adaptive Resampler
| Title | Learned Image Downscaling for Upscaling using Content Adaptive Resampler |
| Authors | Wanjie Sun, Zhenzhong Chen |
| Abstract | Deep convolutional neural network based image super-resolution (SR) models have shown superior performance in recovering the underlying high resolution (HR) images from low resolution (LR) images obtained from the predefined downscaling methods. In this paper we propose a learned image downscaling method based on content adaptive resampler (CAR) with consideration on the upscaling process. The proposed resampler network generates content adaptive image resampling kernels that are applied to the original HR input to generate pixels on the downscaled image. Moreover, a differentiable upscaling (SR) module is employed to upscale the LR result into its underlying HR counterpart. By back-propagating the reconstruction error down to the original HR input across the entire framework to adjust model parameters, the proposed framework achieves a new state-of-the-art SR performance through upscaling guided image resamplers which adaptively preserve detailed information that is essential to the upscaling. Experimental results indicate that the quality of the generated LR image is comparable to that of the traditional interpolation based method, but the significant SR performance gain is achieved by deep SR models trained jointly with the CAR model. The code is publicly available on: URL https://github.com/sunwj/CAR. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.12904v2 |
| https://arxiv.org/pdf/1907.12904v2.pdf | |
| PWC | https://paperswithcode.com/paper/learned-image-downscaling-for-upscaling-using |
| Repo | https://github.com/sunwj/CAR |
| Framework | pytorch |
Generating Contrastive Explanations with Monotonic Attribute Functions
| Title | Generating Contrastive Explanations with Monotonic Attribute Functions |
| Authors | Ronny Luss, Pin-Yu Chen, Amit Dhurandhar, Prasanna Sattigeri, Yunfeng Zhang, Karthikeyan Shanmugam, Chun-Chen Tu |
| Abstract | Explaining decisions of deep neural networks is a hot research topic with applications in medical imaging, video surveillance, and self driving cars. Many methods have been proposed in literature to explain these decisions by identifying relevance of different pixels, limiting the types of explanations possible. In this paper, we propose a method that can generate contrastive explanations for such data where we not only highlight aspects that are in themselves sufficient to justify the classification by the deep model, but also new aspects which if added will change the classification. In order to move beyond the limitations of previous explanations, our key contribution is how we define “addition” for such rich data in a formal yet humanly interpretable way that leads to meaningful results. This was one of the open questions laid out in in Dhurandhar et.al. (2018) [6], which proposed a general framework for creating (local) contrastive explanations for deep models, but is limited to simple use cases such as black/white images. We showcase the efficacy of our approach on three diverse image data sets (faces, skin lesions, and fashion apparel) in creating intuitive explanations that are also quantitatively superior compared with other state-of-the-art interpretability methods. A thorough user study with 200 individuals asks how well the various methods are understood by humans and demonstrates which aspects of contrastive explanations are most desirable. |
| Tasks | Self-Driving Cars |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12698v2 |
| https://arxiv.org/pdf/1905.12698v2.pdf | |
| PWC | https://paperswithcode.com/paper/generating-contrastive-explanations-with |
| Repo | https://github.com/IBM/AIX360 |
| Framework | pytorch |
Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation
| Title | Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation |
| Authors | Yogesh Balaji, Rama Chellappa, Soheil Feizi |
| Abstract | Understanding proper distance measures between distributions is at the core of several learning tasks such as generative models, domain adaptation, clustering, etc. In this work, we focus on mixture distributions that arise naturally in several application domains where the data contains different sub-populations. For mixture distributions, established distance measures such as the Wasserstein distance do not take into account imbalanced mixture proportions. Thus, even if two mixture distributions have identical mixture components but different mixture proportions, the Wasserstein distance between them will be large. This often leads to undesired results in distance-based learning methods for mixture distributions. In this paper, we resolve this issue by introducing the Normalized Wasserstein measure. The key idea is to introduce mixture proportions as optimization variables, effectively normalizing mixture proportions in the Wasserstein formulation. Using the proposed normalized Wasserstein measure leads to significant performance gains for mixture distributions with imbalanced mixture proportions compared to the vanilla Wasserstein distance. We demonstrate the effectiveness of the proposed measure in GANs, domain adaptation and adversarial clustering in several benchmark datasets. |
| Tasks | Domain Adaptation |
| Published | 2019-02-01 |
| URL | https://arxiv.org/abs/1902.00415v2 |
| https://arxiv.org/pdf/1902.00415v2.pdf | |
| PWC | https://paperswithcode.com/paper/normalized-wasserstein-distance-for-mixture |
| Repo | https://github.com/yogeshbalaji/Normalized-Wasserstein |
| Framework | tf |
A*3D Dataset: Towards Autonomous Driving in Challenging Environments
| Title | A*3D Dataset: Towards Autonomous Driving in Challenging Environments |
| Authors | Quang-Hieu Pham, Pierre Sevestre, Ramanpreet Singh Pahwa, Huijing Zhan, Chun Ho Pang, Yuda Chen, Armin Mustafa, Vijay Chandrasekhar, Jie Lin |
| Abstract | With the increasing global popularity of self-driving cars, there is an immediate need for challenging real-world datasets for benchmarking and training various computer vision tasks such as 3D object detection. Existing datasets either represent simple scenarios or provide only day-time data. In this paper, we introduce a new challenging A3D dataset which consists of RGB images and LiDAR data with significant diversity of scene, time, and weather. The dataset consists of high-density images ($\approx~10$ times more than the pioneering KITTI dataset), heavy occlusions, a large number of night-time frames ($\approx~3$ times the nuScenes dataset), addressing the gaps in the existing datasets to push the boundaries of tasks in autonomous driving research to more challenging highly diverse environments. The dataset contains $39\text{K}$ frames, $7$ classes, and $230\text{K}$ 3D object annotations. An extensive 3D object detection benchmark evaluation on the A3D dataset for various attributes such as high density, day-time/night-time, gives interesting insights into the advantages and limitations of training and testing 3D object detection in real-world setting. |
| Tasks | 3D Object Detection, Autonomous Driving, Object Detection, Self-Driving Cars |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.07541v1 |
| https://arxiv.org/pdf/1909.07541v1.pdf | |
| PWC | https://paperswithcode.com/paper/a3d-dataset-towards-autonomous-driving-in |
| Repo | https://github.com/I2RDL2/ASTAR-3D |
| Framework | none |
R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
| Title | R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object |
| Authors | Xue Yang, Qingqing Liu, Junchi Yan, Ang Li, Zhiqiang Zhang, Gang Yu |
| Abstract | Rotation detection is a challenging task due to the difficulties of locating the multi-angle objects and separating them accurately and quickly from the background. Though considerable progress has been made, for practical settings, there still exist challenges for rotating objects with large aspect ratio, dense distribution and category extremely imbalance. In this paper, we propose an end-to-end refined single-stage rotation detector for fast and accurate positioning objects. Considering the shortcoming of feature misalignment in existing refined single-stage detector, we design a feature refinement module to improve detection performance by getting more accurate features. The key idea of feature refinement module is to re-encode the position information of the current refined bounding box to the corresponding feature points through feature interpolation to realize feature reconstruction and alignment. Extensive experiments on two remote sensing public datasets DOTA, HRSC2016 as well as scene text data ICDAR2015 show the state-of-the-art accuracy and speed of our detector. Code is available at https://github.com/Thinklab-SJTU/R3Det_Tensorflow. |
| Tasks | |
| Published | 2019-08-15 |
| URL | https://arxiv.org/abs/1908.05612v5 |
| https://arxiv.org/pdf/1908.05612v5.pdf | |
| PWC | https://paperswithcode.com/paper/r3det-refined-single-stage-detector-with |
| Repo | https://github.com/Thinklab-SJTU/R3Det_Tensorflow |
| Framework | tf |
Multi-Agent Deep Reinforcement Learning for Liquidation Strategy Analysis
| Title | Multi-Agent Deep Reinforcement Learning for Liquidation Strategy Analysis |
| Authors | Wenhang Bao, Xiao-yang Liu |
| Abstract | Liquidation is the process of selling a large number of shares of one stock sequentially within a given time frame, taking into consideration the costs arising from market impact and a trader’s risk aversion. The main challenge in optimizing liquidation is to find an appropriate modeling system that can incorporate the complexities of the stock market and generate practical trading strategies. In this paper, we propose to use multi-agent deep reinforcement learning model, which better captures high-level complexities comparing to various machine learning methods, such that agents can learn how to make the best selling decisions. First, we theoretically analyze the Almgren and Chriss model and extend its fundamental mechanism so it can be used as the multi-agent trading environment. Our work builds the foundation for future multi-agent environment trading analysis. Secondly, we analyze the cooperative and competitive behaviours between agents by adjusting the reward functions for each agent, which overcomes the limitation of single-agent reinforcement learning algorithms. Finally, we simulate trading and develop an optimal trading strategy with practical constraints by using a reinforcement learning method, which shows the capabilities of reinforcement learning methods in solving realistic liquidation problems. |
| Tasks | |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.11046v1 |
| https://arxiv.org/pdf/1906.11046v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-agent-deep-reinforcement-learning-for-3 |
| Repo | https://github.com/WenhangBao/Multi-Agent-RL-for-Liquidation |
| Framework | pytorch |
