Paper Group ANR 811
Decision Support System for Detection and Classification of Skin Cancer using CNN. Adversarial Networks for Camera Pose Regression and Refinement. Winner-Take-All Computation in Spiking Neural Networks. Seeing What a GAN Cannot Generate. Neural Replicator Dynamics. Robot Navigation in Crowds by Graph Convolutional Networks with Attention Learned fr …
Decision Support System for Detection and Classification of Skin Cancer using CNN
| Title | Decision Support System for Detection and Classification of Skin Cancer using CNN |
| Authors | Rishu Garg, Saumil Maheshwari, Anupam Shukla |
| Abstract | Skin Cancer is one of the most deathful of all the cancers. It is bound to spread to different parts of the body on the off chance that it is not analyzed and treated at the beginning time. It is mostly because of the abnormal growth of skin cells, often develops when the body is exposed to sunlight. The Detection Furthermore, the characterization of skin malignant growth in the beginning time is a costly and challenging procedure. It is classified where it develops and its cell type. High Precision and recall are required for the classification of lesions. The paper aims to use MNIST HAM-10000 dataset containing dermoscopy images. The objective is to propose a system that detects skin cancer and classifies it in different classes by using the Convolution Neural Network. The diagnosing methodology uses Image processing and deep learning model. The dermoscopy image of skin cancer taken, undergone various techniques to remove the noise and picture resolution. The image count is also increased by using various image augmentation techniques. In the end, the Transfer Learning method is used to increase the classification accuracy of the images further. Our CNN model gave a weighted average Precision of 0.88, a weighted Recall average of 0.74, and a weighted f1-score of 0.77. The transfer learning approach applied using ResNet model yielded an accuracy of 90.51% |
| Tasks | Image Augmentation, Transfer Learning |
| Published | 2019-12-09 |
| URL | https://arxiv.org/abs/1912.03798v1 |
| https://arxiv.org/pdf/1912.03798v1.pdf | |
| PWC | https://paperswithcode.com/paper/decision-support-system-for-detection-and |
| Repo | |
| Framework | |
Adversarial Networks for Camera Pose Regression and Refinement
| Title | Adversarial Networks for Camera Pose Regression and Refinement |
| Authors | Mai Bui, Christoph Baur, Nassir Navab, Slobodan Ilic, Shadi Albarqouni |
| Abstract | Despite recent advances on the topic of direct camera pose regression using neural networks, accurately estimating the camera pose of a single RGB image still remains a challenging task. To address this problem, we introduce a novel framework based, in its core, on the idea of implicitly learning the joint distribution of RGB images and their corresponding camera poses using a discriminator network and adversarial learning. Our method allows not only to regress the camera pose from a single image, however, also offers a solely RGB-based solution for camera pose refinement using the discriminator network. Further, we show that our method can effectively be used to optimize the predicted camera poses and thus improve the localization accuracy. To this end, we validate our proposed method on the publicly available 7-Scenes dataset improving upon the results of direct camera pose regression methods. |
| Tasks | Pose Estimation |
| Published | 2019-03-15 |
| URL | https://arxiv.org/abs/1903.06646v3 |
| https://arxiv.org/pdf/1903.06646v3.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-joint-image-and-pose-distribution |
| Repo | |
| Framework | |
Winner-Take-All Computation in Spiking Neural Networks
| Title | Winner-Take-All Computation in Spiking Neural Networks |
| Authors | Nancy Lynch, Cameron Musco, Merav Parter |
| Abstract | In this work we study biological neural networks from an algorithmic perspective, focusing on understanding tradeoffs between computation time and network complexity. Our goal is to abstract real neural networks in a way that, while not capturing all interesting features, preserves high-level behavior and allows us to make biologically relevant conclusions. Towards this goal, we consider the implementation of algorithmic primitives in a simple yet biologically plausible model of $stochastic\ spiking\ neural\ networks$. In particular, we show how the stochastic behavior of neurons in this model can be leveraged to solve a basic $symmetry-breaking\ task$ in which we are given neurons with identical firing rates and want to select a distinguished one. In computational neuroscience, this is known as the winner-take-all (WTA) problem, and it is believed to serve as a basic building block in many tasks, e.g., learning, pattern recognition, and clustering. We provide efficient constructions of WTA circuits in our stochastic spiking neural network model, as well as lower bounds in terms of the number of auxiliary neurons required to drive convergence to WTA in a given number of steps. These lower bounds demonstrate that our constructions are near-optimal in some cases. This work covers and gives more in-depth proofs of a subset of results originally published in [LMP17a]. It is adapted from the last chapter of C. Musco’s Ph.D. thesis [Mus18]. |
| Tasks | |
| Published | 2019-04-25 |
| URL | http://arxiv.org/abs/1904.12591v1 |
| http://arxiv.org/pdf/1904.12591v1.pdf | |
| PWC | https://paperswithcode.com/paper/winner-take-all-computation-in-spiking-neural |
| Repo | |
| Framework | |
Seeing What a GAN Cannot Generate
| Title | Seeing What a GAN Cannot Generate |
| Authors | David Bau, Jun-Yan Zhu, Jonas Wulff, William Peebles, Hendrik Strobelt, Bolei Zhou, Antonio Torralba |
| Abstract | Despite the success of Generative Adversarial Networks (GANs), mode collapse remains a serious issue during GAN training. To date, little work has focused on understanding and quantifying which modes have been dropped by a model. In this work, we visualize mode collapse at both the distribution level and the instance level. First, we deploy a semantic segmentation network to compare the distribution of segmented objects in the generated images with the target distribution in the training set. Differences in statistics reveal object classes that are omitted by a GAN. Second, given the identified omitted object classes, we visualize the GAN’s omissions directly. In particular, we compare specific differences between individual photos and their approximate inversions by a GAN. To this end, we relax the problem of inversion and solve the tractable problem of inverting a GAN layer instead of the entire generator. Finally, we use this framework to analyze several recent GANs trained on multiple datasets and identify their typical failure cases. |
| Tasks | Semantic Segmentation |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.11626v1 |
| https://arxiv.org/pdf/1910.11626v1.pdf | |
| PWC | https://paperswithcode.com/paper/seeing-what-a-gan-cannot-generate-1 |
| Repo | |
| Framework | |
Neural Replicator Dynamics
| Title | Neural Replicator Dynamics |
| Authors | Daniel Hennes, Dustin Morrill, Shayegan Omidshafiei, Remi Munos, Julien Perolat, Marc Lanctot, Audrunas Gruslys, Jean-Baptiste Lespiau, Paavo Parmas, Edgar Duenez-Guzman, Karl Tuyls |
| Abstract | Policy gradient and actor-critic algorithms form the basis of many commonly used training techniques in deep reinforcement learning. Using these algorithms in multiagent environments poses problems such as nonstationarity and instability. In this paper, we first demonstrate that standard softmax-based policy gradient can be prone to poor performance in the presence of even the most benign nonstationarity. By contrast, it is known that the replicator dynamics, a well-studied model from evolutionary game theory, eliminates dominated strategies and exhibits convergence of the time-averaged trajectories to interior Nash equilibria in zero-sum games. Thus, using the replicator dynamics as a foundation, we derive an elegant one-line change to policy gradient methods that simply bypasses the gradient step through the softmax, yielding a new algorithm titled Neural Replicator Dynamics (NeuRD). NeuRD reduces to the exponential weights/Hedge algorithm in the single-state all-actions case. Additionally, NeuRD has formal equivalence to softmax counterfactual regret minimization, which guarantees convergence in the sequential tabular case. Importantly, our algorithm provides a straightforward way of extending the replicator dynamics to the function approximation setting. Empirical results show that NeuRD quickly adapts to nonstationarities, outperforming policy gradient significantly in both tabular and function approximation settings, when evaluated on the standard imperfect information benchmarks of Kuhn Poker, Leduc Poker, and Goofspiel. |
| Tasks | Policy Gradient Methods |
| Published | 2019-06-01 |
| URL | https://arxiv.org/abs/1906.00190v5 |
| https://arxiv.org/pdf/1906.00190v5.pdf | |
| PWC | https://paperswithcode.com/paper/190600190 |
| Repo | |
| Framework | |
Robot Navigation in Crowds by Graph Convolutional Networks with Attention Learned from Human Gaze
| Title | Robot Navigation in Crowds by Graph Convolutional Networks with Attention Learned from Human Gaze |
| Authors | Yuying Chen, Congcong Liu, Ming Liu, Bertram E. Shi |
| Abstract | Safe and efficient crowd navigation for mobile robot is a crucial yet challenging task. Previous work has shown the power of deep reinforcement learning frameworks to train efficient policies. However, their performance deteriorates when the crowd size grows. We suggest that this can be addressed by enabling the network to identify and pay attention to the humans in the crowd that are most critical to navigation. We propose a novel network utilizing a graph representation to learn the policy. We first train a graph convolutional network based on human gaze data that accurately predicts human attention to different agents in the crowd. Then we incorporate the learned attention into a graph-based reinforcement learning architecture. The proposed attention mechanism enables the assignment of meaningful weightings to the neighbors of the robot, and has the additional benefit of interpretability. Experiments on real-world dense pedestrian datasets with various crowd sizes demonstrate that our model outperforms state-of-art methods by 18.4% in task accomplishment and by 16.4% in time efficiency. |
| Tasks | Robot Navigation |
| Published | 2019-09-23 |
| URL | https://arxiv.org/abs/1909.10400v1 |
| https://arxiv.org/pdf/1909.10400v1.pdf | |
| PWC | https://paperswithcode.com/paper/190910400 |
| Repo | |
| Framework | |
CPWC: Contextual Point Wise Convolution for Object Recognition
| Title | CPWC: Contextual Point Wise Convolution for Object Recognition |
| Authors | Pratik Mazumder, Pravendra Singh, Vinay Namboodiri |
| Abstract | Convolutional layers are a major driving force behind the successes of deep learning. Pointwise convolution (PWC) is a 1x1 convolutional filter that is primarily used for parameter reduction. However, the PWC ignores the spatial information around the points it is processing. This design is by choice, in order to reduce the overall parameters and computations. However, we hypothesize that this shortcoming of PWC has a significant impact on the network performance. We propose an alternative design for pointwise convolution, which uses spatial information from the input efficiently. Our design significantly improves the performance of the networks without substantially increasing the number of parameters and computations. We experimentally show that our design results in significant improvement in the performance of the network for classification as well as detection. |
| Tasks | Object Recognition |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09643v2 |
| https://arxiv.org/pdf/1910.09643v2.pdf | |
| PWC | https://paperswithcode.com/paper/cpwc-contextual-point-wise-convolution-for |
| Repo | |
| Framework | |
Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning
| Title | Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning |
| Authors | Thommen George Karimpanal, Santu Rana, Sunil Gupta, Truyen Tran, Svetha Venkatesh |
| Abstract | Prior access to domain knowledge could significantly improve the performance of a reinforcement learning agent. In particular, it could help agents avoid potentially catastrophic exploratory actions, which would otherwise have to be experienced during learning. In this work, we identify consistently undesirable actions in a set of previously learned tasks, and use pseudo-rewards associated with them to learn a prior policy. In addition to enabling safer exploratory behaviors in subsequent tasks in the domain, we show that these priors are transferable to similar environments, and can be learned off-policy and in parallel with the learning of other tasks in the domain. We compare our approach to established, state-of-the-art algorithms in both discrete as well as continuous environments, and demonstrate that it exhibits a safer exploratory behavior while learning to perform arbitrary tasks in the domain. We also present a theoretical analysis to support these results, and briefly discuss the implications and some alternative formulations of this approach, which could also be useful in certain scenarios. |
| Tasks | Safe Exploration |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04307v4 |
| https://arxiv.org/pdf/1909.04307v4.pdf | |
| PWC | https://paperswithcode.com/paper/learning-transferable-domain-priors-for-safe |
| Repo | |
| Framework | |
A General Theory for Structured Prediction with Smooth Convex Surrogates
| Title | A General Theory for Structured Prediction with Smooth Convex Surrogates |
| Authors | Alex Nowak-Vila, Francis Bach, Alessandro Rudi |
| Abstract | In this work we provide a theoretical framework for structured prediction that generalizes the existing theory of surrogate methods for binary and multiclass classification based on estimating conditional probabilities with smooth convex surrogates (e.g. logistic regression). The theory relies on a natural characterization of structural properties of the task loss and allows to derive statistical guarantees for many widely used methods in the context of multilabeling, ranking, ordinal regression and graph matching. In particular, we characterize the smooth convex surrogates compatible with a given task loss in terms of a suitable Bregman divergence composed with a link function. This allows to derive tight bounds for the calibration function and to obtain novel results on existing surrogate frameworks for structured prediction such as conditional random fields and quadratic surrogates. |
| Tasks | Calibration, Graph Matching, Structured Prediction |
| Published | 2019-02-05 |
| URL | http://arxiv.org/abs/1902.01958v2 |
| http://arxiv.org/pdf/1902.01958v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-general-theory-for-structured-prediction |
| Repo | |
| Framework | |
Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
| Title | Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back |
| Authors | Martin Simonovsky |
| Abstract | A graph is a powerful concept for representation of relations between pairs of entities. Data with underlying graph structure can be found across many disciplines and there is a natural desire for understanding such data better. Deep learning (DL) has achieved significant breakthroughs in a variety of machine learning tasks in recent years, especially where data is structured on a grid, such as in text, speech, or image understanding. However, surprisingly little has been done to explore the applicability of DL on arbitrary graph-structured data directly. The goal of this thesis is to investigate architectures for DL on graphs and study how to transfer, adapt or generalize concepts that work well on sequential and image data to this domain. We concentrate on two important primitives: embedding graphs or their nodes into a continuous vector space representation (encoding) and, conversely, generating graphs from such vectors back (decoding). To that end, we make the following contributions. First, we introduce Edge-Conditioned Convolutions (ECC), a convolution-like operation on graphs performed in the spatial domain where filters are dynamically generated based on edge attributes. The method is used to encode graphs with arbitrary and varying structure. Second, we propose SuperPoint Graph, an intermediate point cloud representation with rich edge attributes encoding the contextual relationship between object parts. Based on this representation, ECC is employed to segment large-scale point clouds without major sacrifice in fine details. Third, we present GraphVAE, a graph generator allowing us to decode graphs with variable but upper-bounded number of nodes making use of approximate graph matching for aligning the predictions of an autoencoder with its inputs. The method is applied to the task of molecule generation. |
| Tasks | Graph Matching |
| Published | 2019-01-24 |
| URL | http://arxiv.org/abs/1901.08296v1 |
| http://arxiv.org/pdf/1901.08296v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-on-attributed-graphs-a-journey |
| Repo | |
| Framework | |
Topological descriptors of spatial coherence in a convective boundary layer
| Title | Topological descriptors of spatial coherence in a convective boundary layer |
| Authors | José Licón-Saláiz, Cedrick Ansorge |
| Abstract | The interaction between a turbulent convective boundary layer (CBL) and the underlying land surface is an important research problem in the geosciences. In order to model this interaction adequately, it is necessary to develop tools which can describe it quantitatively. Commonly employed methods, such as bulk flow statistics, are known to be insufficient for this task, especially when land surfaces with equal aggregate statistics but different spatial patterns are involved. While geometrical properties of the surface forcing have a strong influence on flow structure, it is precisely those properties that get neglected when computing bulk statistics. Here, we present a set of descriptors based on low-level topological information (i.,e. connectivity), and show how these can be used both in the structural analysis of the CBL and in modeling its response to differences in surface forcing. The topological property of connectivity is not only easier to compute than its higher-dimensional homological counterparts, but also has a natural relation to the physical concept of a coherent structure. |
| Tasks | |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.02993v1 |
| https://arxiv.org/pdf/1906.02993v1.pdf | |
| PWC | https://paperswithcode.com/paper/topological-descriptors-of-spatial-coherence |
| Repo | |
| Framework | |
Sequential Triggers for Watermarking of Deep Reinforcement Learning Policies
| Title | Sequential Triggers for Watermarking of Deep Reinforcement Learning Policies |
| Authors | Vahid Behzadan, William Hsu |
| Abstract | This paper proposes a novel scheme for the watermarking of Deep Reinforcement Learning (DRL) policies. This scheme provides a mechanism for the integration of a unique identifier within the policy in the form of its response to a designated sequence of state transitions, while incurring minimal impact on the nominal performance of the policy. The applications of this watermarking scheme include detection of unauthorized replications of proprietary policies, as well as enabling the graceful interruption or termination of DRL activities by authorized entities. We demonstrate the feasibility of our proposal via experimental evaluation of watermarking a DQN policy trained in the Cartpole environment. |
| Tasks | |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.01126v1 |
| https://arxiv.org/pdf/1906.01126v1.pdf | |
| PWC | https://paperswithcode.com/paper/sequential-triggers-for-watermarking-of-deep |
| Repo | |
| Framework | |
Linear Stochastic Bandits Under Safety Constraints
| Title | Linear Stochastic Bandits Under Safety Constraints |
| Authors | Sanae Amani, Mahnoosh Alizadeh, Christos Thrampoulidis |
| Abstract | Bandit algorithms have various application in safety-critical systems, where it is important to respect the system constraints that rely on the bandit’s unknown parameters at every round. In this paper, we formulate a linear stochastic multi-armed bandit problem with safety constraints that depend (linearly) on an unknown parameter vector. As such, the learner is unable to identify all safe actions and must act conservatively in ensuring that her actions satisfy the safety constraint at all rounds (at least with high probability). For these bandits, we propose a new UCB-based algorithm called Safe-LUCB, which includes necessary modifications to respect safety constraints. The algorithm has two phases. During the pure exploration phase the learner chooses her actions at random from a restricted set of safe actions with the goal of learning a good approximation of the entire unknown safe set. Once this goal is achieved, the algorithm begins a safe exploration-exploitation phase where the learner gradually expands their estimate of the set of safe actions while controlling the growth of regret. We provide a general regret bound for the algorithm, as well as a problem dependent bound that is connected to the location of the optimal action within the safe set. We then propose a modified heuristic that exploits our problem dependent analysis to improve the regret. |
| Tasks | Safe Exploration |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.05814v1 |
| https://arxiv.org/pdf/1908.05814v1.pdf | |
| PWC | https://paperswithcode.com/paper/linear-stochastic-bandits-under-safety |
| Repo | |
| Framework | |
TSXplain: Demystification of DNN Decisions for Time-Series using Natural Language and Statistical Features
| Title | TSXplain: Demystification of DNN Decisions for Time-Series using Natural Language and Statistical Features |
| Authors | Mohsin Munir, Shoaib Ahmed Siddiqui, Ferdinand Küsters, Dominique Mercier, Andreas Dengel, Sheraz Ahmed |
| Abstract | Neural networks (NN) are considered as black-boxes due to the lack of explainability and transparency of their decisions. This significantly hampers their deployment in environments where explainability is essential along with the accuracy of the system. Recently, significant efforts have been made for the interpretability of these deep networks with the aim to open up the black-box. However, most of these approaches are specifically developed for visual modalities. In addition, the interpretations provided by these systems require expert knowledge and understanding for intelligibility. This indicates a vital gap between the explainability provided by the systems and the novice user. To bridge this gap, we present a novel framework i.e. Time-Series eXplanation (TSXplain) system which produces a natural language based explanation of the decision taken by a NN. It uses the extracted statistical features to describe the decision of a NN, merging the deep learning world with that of statistics. The two-level explanation provides ample description of the decision made by the network to aid an expert as well as a novice user alike. Our survey and reliability assessment test confirm that the generated explanations are meaningful and correct. We believe that generating natural language based descriptions of the network’s decisions is a big step towards opening up the black-box. |
| Tasks | Time Series |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.06175v1 |
| https://arxiv.org/pdf/1905.06175v1.pdf | |
| PWC | https://paperswithcode.com/paper/tsxplain-demystification-of-dnn-decisions-for |
| Repo | |
| Framework | |
Domain Independent SVM for Transfer Learning in Brain Decoding
| Title | Domain Independent SVM for Transfer Learning in Brain Decoding |
| Authors | Shuo Zhou, Wenwen Li, Christopher R. Cox, Haiping Lu |
| Abstract | Brain imaging data are important in brain sciences yet expensive to obtain, with big volume (i.e., large p) but small sample size (i.e., small n). To tackle this problem, transfer learning is a promising direction that leverages source data to improve performance on related, target data. Most transfer learning methods focus on minimizing data distribution mismatch. However, a big challenge in brain imaging is the large domain discrepancies in cognitive experiment designs and subject-specific structures and functions. A recent transfer learning approach minimizes domain dependence to learn common features across domains, via the Hilbert-Schmidt Independence Criterion (HSIC). Inspired by this method, we propose a new Domain Independent Support Vector Machine (DI-SVM) for transfer learning in brain condition decoding. Specifically, DI-SVM simultaneously minimizes the SVM empirical risk and the dependence on domain information via a simplified HSIC. We use public data to construct 13 transfer learning tasks in brain decoding, including three interesting multi-source transfer tasks. Experiments show that DI-SVM’s superior performance over eight competing methods on these tasks, particularly an improvement of more than 24% on multi-source transfer tasks. |
| Tasks | Brain Decoding, Transfer Learning |
| Published | 2019-03-26 |
| URL | http://arxiv.org/abs/1903.11020v1 |
| http://arxiv.org/pdf/1903.11020v1.pdf | |
| PWC | https://paperswithcode.com/paper/domain-independent-svm-for-transfer-learning |
| Repo | |
| Framework | |
