Paper Group ANR 337
CUNet: A Compact Unsupervised Network for Image Classification. Reshaped Wirtinger Flow and Incremental Algorithm for Solving Quadratic System of Equations. SynsetRank: Degree-adjusted Random Walk for Relation Identification. X-ray Scattering Image Classification Using Deep Learning. DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification. …
CUNet: A Compact Unsupervised Network for Image Classification
| Title | CUNet: A Compact Unsupervised Network for Image Classification |
| Authors | Le Dong, Ling He, Gaipeng Kong, Qianni Zhang, Xiaochun Cao, Ebroul Izquierdo |
| Abstract | In this paper, we propose a compact network called CUNet (compact unsupervised network) to counter the image classification challenge. Different from the traditional convolutional neural networks learning filters by the time-consuming stochastic gradient descent, CUNet learns the filter bank from diverse image patches with the simple K-means, which significantly avoids the requirement of scarce labeled training images, reduces the training consumption, and maintains the high discriminative ability. Besides, we propose a new pooling method named weighted pooling considering the different weight values of adjacent neurons, which helps to improve the robustness to small image distortions. In the output layer, CUNet integrates the feature maps gained in the last hidden layer, and straightforwardly computes histograms in non-overlapped blocks. To reduce feature redundancy, we implement the max-pooling operation on adjacent blocks to select the most competitive features. Comprehensive experiments are conducted to demonstrate the state-of-the-art classification performances with CUNet on CIFAR-10, STL-10, MNIST and Caltech101 benchmark datasets. |
| Tasks | Image Classification |
| Published | 2016-07-06 |
| URL | http://arxiv.org/abs/1607.01577v1 |
| http://arxiv.org/pdf/1607.01577v1.pdf | |
| PWC | https://paperswithcode.com/paper/cunet-a-compact-unsupervised-network-for |
| Repo | |
| Framework | |
Reshaped Wirtinger Flow and Incremental Algorithm for Solving Quadratic System of Equations
| Title | Reshaped Wirtinger Flow and Incremental Algorithm for Solving Quadratic System of Equations |
| Authors | Huishuai Zhang, Yi Zhou, Yingbin Liang, Yuejie Chi |
| Abstract | We study the phase retrieval problem, which solves quadratic system of equations, i.e., recovers a vector $\boldsymbol{x}\in \mathbb{R}^n$ from its magnitude measurements $y_i=\langle \boldsymbol{a}_i, \boldsymbol{x}\rangle, i=1,…, m$. We develop a gradient-like algorithm (referred to as RWF representing reshaped Wirtinger flow) by minimizing a nonconvex nonsmooth loss function. In comparison with existing nonconvex Wirtinger flow (WF) algorithm \cite{candes2015phase}, although the loss function becomes nonsmooth, it involves only the second power of variable and hence reduces the complexity. We show that for random Gaussian measurements, RWF enjoys geometric convergence to a global optimal point as long as the number $m$ of measurements is on the order of $n$, the dimension of the unknown $\boldsymbol{x}$. This improves the sample complexity of WF, and achieves the same sample complexity as truncated Wirtinger flow (TWF) \cite{chen2015solving}, but without truncation in gradient loop. Furthermore, RWF costs less computationally than WF, and runs faster numerically than both WF and TWF. We further develop the incremental (stochastic) reshaped Wirtinger flow (IRWF) and show that IRWF converges linearly to the true signal. We further establish performance guarantee of an existing Kaczmarz method for the phase retrieval problem based on its connection to IRWF. We also empirically demonstrate that IRWF outperforms existing ITWF algorithm (stochastic version of TWF) as well as other batch algorithms. |
| Tasks | |
| Published | 2016-05-25 |
| URL | http://arxiv.org/abs/1605.07719v2 |
| http://arxiv.org/pdf/1605.07719v2.pdf | |
| PWC | https://paperswithcode.com/paper/reshaped-wirtinger-flow-and-incremental |
| Repo | |
| Framework | |
SynsetRank: Degree-adjusted Random Walk for Relation Identification
| Title | SynsetRank: Degree-adjusted Random Walk for Relation Identification |
| Authors | Shinichi Nakajima, Sebastian Krause, Dirk Weissenborn, Sven Schmeier, Nico Goernitz, Feiyu Xu |
| Abstract | In relation extraction, a key process is to obtain good detectors that find relevant sentences describing the target relation. To minimize the necessity of labeled data for refining detectors, previous work successfully made use of BabelNet, a semantic graph structure expressing relationships between synsets, as side information or prior knowledge. The goal of this paper is to enhance the use of graph structure in the framework of random walk with a few adjustable parameters. Actually, a straightforward application of random walk degrades the performance even after parameter optimization. With the insight from this unsuccessful trial, we propose SynsetRank, which adjusts the initial probability so that high degree nodes influence the neighbors as strong as low degree nodes. In our experiment on 13 relations in the FB15K-237 dataset, SynsetRank significantly outperforms baselines and the plain random walk approach. |
| Tasks | Relation Extraction |
| Published | 2016-09-02 |
| URL | http://arxiv.org/abs/1609.00626v2 |
| http://arxiv.org/pdf/1609.00626v2.pdf | |
| PWC | https://paperswithcode.com/paper/synsetrank-degree-adjusted-random-walk-for |
| Repo | |
| Framework | |
X-ray Scattering Image Classification Using Deep Learning
| Title | X-ray Scattering Image Classification Using Deep Learning |
| Authors | Boyu Wang, Kevin Yager, Dantong Yu, Minh Hoai |
| Abstract | Visual inspection of x-ray scattering images is a powerful technique for probing the physical structure of materials at the molecular scale. In this paper, we explore the use of deep learning to develop methods for automatically analyzing x-ray scattering images. In particular, we apply Convolutional Neural Networks and Convolutional Autoencoders for x-ray scattering image classification. To acquire enough training data for deep learning, we use simulation software to generate synthetic x-ray scattering images. Experiments show that deep learning methods outperform previously published methods by 10% on synthetic and real datasets. |
| Tasks | Image Classification |
| Published | 2016-11-10 |
| URL | http://arxiv.org/abs/1611.03313v1 |
| http://arxiv.org/pdf/1611.03313v1.pdf | |
| PWC | https://paperswithcode.com/paper/x-ray-scattering-image-classification-using |
| Repo | |
| Framework | |
DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification
| Title | DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification |
| Authors | Shu Zhang, Ran He, Tieniu Tan |
| Abstract | MeshFace photos have been widely used in many Chinese business organizations to protect ID face photos from being misused. The occlusions incurred by random meshes severely degenerate the performance of face verification systems, which raises the MeshFace verification problem between MeshFace and daily photos. Previous methods cast this problem as a typical low-level vision problem, i.e. blind inpainting. They recover perceptually pleasing clear ID photos from MeshFaces by enforcing pixel level similarity between the recovered ID images and the ground-truth clear ID images and then perform face verification on them. Essentially, face verification is conducted on a compact feature space rather than the image pixel space. Therefore, this paper argues that pixel level similarity and feature level similarity jointly offer the key to improve the verification performance. Based on this insight, we offer a novel feature oriented blind face inpainting framework. Specifically, we implement this by establishing a novel DeMeshNet, which consists of three parts. The first part addresses blind inpainting of the MeshFaces by implicitly exploiting extra supervision from the occlusion position to enforce pixel level similarity. The second part explicitly enforces a feature level similarity in the compact feature space, which can explore informative supervision from the feature space to produce better inpainting results for verification. The last part copes with face alignment within the net via a customized spatial transformer module when extracting deep facial features. All the three parts are implemented within an end-to-end network that facilitates efficient optimization. Extensive experiments on two MeshFace datasets demonstrate the effectiveness of the proposed DeMeshNet as well as the insight of this paper. |
| Tasks | Face Alignment, Face Verification, Facial Inpainting |
| Published | 2016-11-16 |
| URL | http://arxiv.org/abs/1611.05271v1 |
| http://arxiv.org/pdf/1611.05271v1.pdf | |
| PWC | https://paperswithcode.com/paper/demeshnet-blind-face-inpainting-for-deep |
| Repo | |
| Framework | |
Clustering subgaussian mixtures by semidefinite programming
| Title | Clustering subgaussian mixtures by semidefinite programming |
| Authors | Dustin G. Mixon, Soledad Villar, Rachel Ward |
| Abstract | We introduce a model-free relax-and-round algorithm for k-means clustering based on a semidefinite relaxation due to Peng and Wei. The algorithm interprets the SDP output as a denoised version of the original data and then rounds this output to a hard clustering. We provide a generic method for proving performance guarantees for this algorithm, and we analyze the algorithm in the context of subgaussian mixture models. We also study the fundamental limits of estimating Gaussian centers by k-means clustering in order to compare our approximation guarantee to the theoretically optimal k-means clustering solution. |
| Tasks | |
| Published | 2016-02-22 |
| URL | http://arxiv.org/abs/1602.06612v2 |
| http://arxiv.org/pdf/1602.06612v2.pdf | |
| PWC | https://paperswithcode.com/paper/clustering-subgaussian-mixtures-by |
| Repo | |
| Framework | |
Charged Point Normalization: An Efficient Solution to the Saddle Point Problem
| Title | Charged Point Normalization: An Efficient Solution to the Saddle Point Problem |
| Authors | Armen Aghajanyan |
| Abstract | Recently, the problem of local minima in very high dimensional non-convex optimization has been challenged and the problem of saddle points has been introduced. This paper introduces a dynamic type of normalization that forces the system to escape saddle points. Unlike other saddle point escaping algorithms, second order information is not utilized, and the system can be trained with an arbitrary gradient descent learner. The system drastically improves learning in a range of deep neural networks on various data-sets in comparison to non-CPN neural networks. |
| Tasks | |
| Published | 2016-09-29 |
| URL | http://arxiv.org/abs/1609.09522v2 |
| http://arxiv.org/pdf/1609.09522v2.pdf | |
| PWC | https://paperswithcode.com/paper/charged-point-normalization-an-efficient |
| Repo | |
| Framework | |
Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers
| Title | Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers |
| Authors | Alexander Binder, Grégoire Montavon, Sebastian Bach, Klaus-Robert Müller, Wojciech Samek |
| Abstract | Layer-wise relevance propagation is a framework which allows to decompose the prediction of a deep neural network computed over a sample, e.g. an image, down to relevance scores for the single input dimensions of the sample such as subpixels of an image. While this approach can be applied directly to generalized linear mappings, product type non-linearities are not covered. This paper proposes an approach to extend layer-wise relevance propagation to neural networks with local renormalization layers, which is a very common product-type non-linearity in convolutional neural networks. We evaluate the proposed method for local renormalization layers on the CIFAR-10, Imagenet and MIT Places datasets. |
| Tasks | |
| Published | 2016-04-04 |
| URL | http://arxiv.org/abs/1604.00825v1 |
| http://arxiv.org/pdf/1604.00825v1.pdf | |
| PWC | https://paperswithcode.com/paper/layer-wise-relevance-propagation-for-neural |
| Repo | |
| Framework | |
Cosolver2B: An Efficient Local Search Heuristic for the Travelling Thief Problem
| Title | Cosolver2B: An Efficient Local Search Heuristic for the Travelling Thief Problem |
| Authors | Mohamed El Yafrani, Belaïd Ahiod |
| Abstract | Real-world problems are very difficult to optimize. However, many researchers have been solving benchmark problems that have been extensively investigated for the last decades even if they have very few direct applications. The Traveling Thief Problem (TTP) is a NP-hard optimization problem that aims to provide a more realistic model. TTP targets particularly routing problem under packing/loading constraints which can be found in supply chain management and transportation. In this paper, TTP is presented and formulated mathematically. A combined local search algorithm is proposed and compared with Random Local Search (RLS) and Evolutionary Algorithm (EA). The obtained results are quite promising since new better solutions were found. |
| Tasks | |
| Published | 2016-03-23 |
| URL | http://arxiv.org/abs/1603.07051v1 |
| http://arxiv.org/pdf/1603.07051v1.pdf | |
| PWC | https://paperswithcode.com/paper/cosolver2b-an-efficient-local-search |
| Repo | |
| Framework | |
Situational Awareness by Risk-Conscious Skills
| Title | Situational Awareness by Risk-Conscious Skills |
| Authors | Daniel J. Mankowitz, Aviv Tamar, Shie Mannor |
| Abstract | Hierarchical Reinforcement Learning has been previously shown to speed up the convergence rate of RL planning algorithms as well as mitigate feature-based model misspecification (Mankowitz et. al. 2016a,b, Bacon 2015). To do so, it utilizes hierarchical abstractions, also known as skills – a type of temporally extended action (Sutton et. al. 1999) to plan at a higher level, abstracting away from the lower-level details. We incorporate risk sensitivity, also referred to as Situational Awareness (SA), into hierarchical RL for the first time by defining and learning risk aware skills in a Probabilistic Goal Semi-Markov Decision Process (PG-SMDP). This is achieved using our novel Situational Awareness by Risk-Conscious Skills (SARiCoS) algorithm which comes with a theoretical convergence guarantee. We show in a RoboCup soccer domain that the learned risk aware skills exhibit complex human behaviors such as `time-wasting’ in a soccer game. In addition, the learned risk aware skills are able to mitigate reward-based model misspecification. | |
| Tasks | Hierarchical Reinforcement Learning |
| Published | 2016-10-10 |
| URL | http://arxiv.org/abs/1610.02847v1 |
| http://arxiv.org/pdf/1610.02847v1.pdf | |
| PWC | https://paperswithcode.com/paper/situational-awareness-by-risk-conscious |
| Repo | |
| Framework | |
Multi-Stage Temporal Difference Learning for 2048-like Games
| Title | Multi-Stage Temporal Difference Learning for 2048-like Games |
| Authors | Kun-Hao Yeh, I-Chen Wu, Chu-Hsuan Hsueh, Chia-Chuan Chang, Chao-Chin Liang, Han Chiang |
| Abstract | Szubert and Jaskowski successfully used temporal difference (TD) learning together with n-tuple networks for playing the game 2048. However, we observed a phenomenon that the programs based on TD learning still hardly reach large tiles. In this paper, we propose multi-stage TD (MS-TD) learning, a kind of hierarchical reinforcement learning method, to effectively improve the performance for the rates of reaching large tiles, which are good metrics to analyze the strength of 2048 programs. Our experiments showed significant improvements over the one without using MS-TD learning. Namely, using 3-ply expectimax search, the program with MS-TD learning reached 32768-tiles with a rate of 18.31%, while the one with TD learning did not reach any. After further tuned, our 2048 program reached 32768-tiles with a rate of 31.75% in 10,000 games, and one among these games even reached a 65536-tile, which is the first ever reaching a 65536-tile to our knowledge. In addition, MS-TD learning method can be easily applied to other 2048-like games, such as Threes. Based on MS-TD learning, our experiments for Threes also demonstrated similar performance improvement, where the program with MS-TD learning reached 6144-tiles with a rate of 7.83%, while the one with TD learning only reached 0.45%. |
| Tasks | Hierarchical Reinforcement Learning |
| Published | 2016-06-23 |
| URL | http://arxiv.org/abs/1606.07374v2 |
| http://arxiv.org/pdf/1606.07374v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-stage-temporal-difference-learning-for |
| Repo | |
| Framework | |
First-order Methods for Geodesically Convex Optimization
| Title | First-order Methods for Geodesically Convex Optimization |
| Authors | Hongyi Zhang, Suvrit Sra |
| Abstract | Geodesic convexity generalizes the notion of (vector space) convexity to nonlinear metric spaces. But unlike convex optimization, geodesically convex (g-convex) optimization is much less developed. In this paper we contribute to the understanding of g-convex optimization by developing iteration complexity analysis for several first-order algorithms on Hadamard manifolds. Specifically, we prove upper bounds for the global complexity of deterministic and stochastic (sub)gradient methods for optimizing smooth and nonsmooth g-convex functions, both with and without strong g-convexity. Our analysis also reveals how the manifold geometry, especially \emph{sectional curvature}, impacts convergence rates. To the best of our knowledge, our work is the first to provide global complexity analysis for first-order algorithms for general g-convex optimization. |
| Tasks | |
| Published | 2016-02-19 |
| URL | http://arxiv.org/abs/1602.06053v1 |
| http://arxiv.org/pdf/1602.06053v1.pdf | |
| PWC | https://paperswithcode.com/paper/first-order-methods-for-geodesically-convex |
| Repo | |
| Framework | |
RRV: A Spatiotemporal Descriptor for Rigid Body Motion Recognition
| Title | RRV: A Spatiotemporal Descriptor for Rigid Body Motion Recognition |
| Authors | Yao Guo, Youfu Li, Zhanpeng Shao |
| Abstract | Motion behaviors of a rigid body can be characterized by a 6-dimensional motion trajectory, which contains position vectors of a reference point on the rigid body and rotations of this rigid body over time. This paper devises a Rotation and Relative Velocity (RRV) descriptor by exploring the local translational and rotational invariants of motion trajectories of rigid bodies, which is insensitive to noise, invariant to rigid transformation and scaling. A flexible metric is also introduced to measure the distance between two RRV descriptors. The RRV descriptor is then applied to characterize motions of a human body skeleton modeled as articulated interconnections of multiple rigid bodies. To illustrate the descriptive ability of the RRV descriptor, we explore it for different rigid body motion recognition tasks. The experimental results on benchmark datasets demonstrate that this simple RRV descriptor outperforms the previous ones regarding recognition accuracy without increasing computational cost. |
| Tasks | |
| Published | 2016-06-18 |
| URL | http://arxiv.org/abs/1606.05729v2 |
| http://arxiv.org/pdf/1606.05729v2.pdf | |
| PWC | https://paperswithcode.com/paper/rrv-a-spatiotemporal-descriptor-for-rigid |
| Repo | |
| Framework | |
Option Discovery in Hierarchical Reinforcement Learning using Spatio-Temporal Clustering
| Title | Option Discovery in Hierarchical Reinforcement Learning using Spatio-Temporal Clustering |
| Authors | Aravind S. Lakshminarayanan, Ramnandan Krishnamurthy, Peeyush Kumar, Balaraman Ravindran |
| Abstract | This paper introduces an automated skill acquisition framework in reinforcement learning which involves identifying a hierarchical description of the given task in terms of abstract states and extended actions between abstract states. Identifying such structures present in the task provides ways to simplify and speed up reinforcement learning algorithms. These structures also help to generalize such algorithms over multiple tasks without relearning policies from scratch. We use ideas from dynamical systems to find metastable regions in the state space and associate them with abstract states. The spectral clustering algorithm PCCA+ is used to identify suitable abstractions aligned to the underlying structure. Skills are defined in terms of the sequence of actions that lead to transitions between such abstract states. The connectivity information from PCCA+ is used to generate these skills or options. These skills are independent of the learning task and can be efficiently reused across a variety of tasks defined over the same model. This approach works well even without the exact model of the environment by using sample trajectories to construct an approximate estimate. We also present our approach to scaling the skill acquisition framework to complex tasks with large state spaces for which we perform state aggregation using the representation learned from an action conditional video prediction network and use the skill acquisition framework on the aggregated state space. |
| Tasks | Hierarchical Reinforcement Learning, Video Prediction |
| Published | 2016-05-17 |
| URL | http://arxiv.org/abs/1605.05359v2 |
| http://arxiv.org/pdf/1605.05359v2.pdf | |
| PWC | https://paperswithcode.com/paper/option-discovery-in-hierarchical |
| Repo | |
| Framework | |
Algorithms for Batch Hierarchical Reinforcement Learning
| Title | Algorithms for Batch Hierarchical Reinforcement Learning |
| Authors | Tiancheng Zhao, Mohammad Gowayyed |
| Abstract | Hierarchical Reinforcement Learning (HRL) exploits temporal abstraction to solve large Markov Decision Processes (MDP) and provide transferable subtask policies. In this paper, we introduce an off-policy HRL algorithm: Hierarchical Q-value Iteration (HQI). We show that it is possible to effectively learn recursive optimal policies for any valid hierarchical decomposition of the original MDP, given a fixed dataset collected from a flat stochastic behavioral policy. We first formally prove the convergence of the algorithm for tabular MDP. Then our experiments on the Taxi domain show that HQI converges faster than a flat Q-value Iteration and enjoys easy state abstraction. Also, we demonstrate that our algorithm is able to learn optimal policies for different hierarchical structures from the same fixed dataset, which enables model comparison without recollecting data. |
| Tasks | Hierarchical Reinforcement Learning |
| Published | 2016-03-29 |
| URL | http://arxiv.org/abs/1603.08869v1 |
| http://arxiv.org/pdf/1603.08869v1.pdf | |
| PWC | https://paperswithcode.com/paper/algorithms-for-batch-hierarchical |
| Repo | |
| Framework | |
