Paper Group ANR 1529
DC-SPP-YOLO: Dense Connection and Spatial Pyramid Pooling Based YOLO for Object Detection. Using Sub-Optimal Plan Detection to Identify Commitment Abandonment in Discrete Environments. Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss. Self-Imitation Learning via Trajectory-Conditioned Policy for …
DC-SPP-YOLO: Dense Connection and Spatial Pyramid Pooling Based YOLO for Object Detection
| Title | DC-SPP-YOLO: Dense Connection and Spatial Pyramid Pooling Based YOLO for Object Detection |
| Authors | Zhanchao Huang, Jianlin Wang |
| Abstract | Although YOLOv2 approach is extremely fast on object detection; its backbone network has the low ability on feature extraction and fails to make full use of multi-scale local region features, which restricts the improvement of object detection accuracy. Therefore, this paper proposed a DC-SPP-YOLO (Dense Connection and Spatial Pyramid Pooling Based YOLO) approach for ameliorating the object detection accuracy of YOLOv2. Specifically, the dense connection of convolution layers is employed in the backbone network of YOLOv2 to strengthen the feature extraction and alleviate the vanishing-gradient problem. Moreover, an improved spatial pyramid pooling is introduced to pool and concatenate the multi-scale local region features, so that the network can learn the object features more comprehensively. The DC-SPP-YOLO model is established and trained based on a new loss function composed of mean square error and cross entropy, and the object detection is realized. Experiments demonstrate that the mAP (mean Average Precision) of DC-SPP-YOLO proposed on PASCAL VOC datasets and UA-DETRAC datasets is higher than that of YOLOv2; the object detection accuracy of DC-SPP-YOLO is superior to YOLOv2 by strengthening feature extraction and using the multi-scale local region features. |
| Tasks | Object Detection |
| Published | 2019-03-20 |
| URL | http://arxiv.org/abs/1903.08589v1 |
| http://arxiv.org/pdf/1903.08589v1.pdf | |
| PWC | https://paperswithcode.com/paper/dc-spp-yolo-dense-connection-and-spatial |
| Repo | |
| Framework | |
Using Sub-Optimal Plan Detection to Identify Commitment Abandonment in Discrete Environments
| Title | Using Sub-Optimal Plan Detection to Identify Commitment Abandonment in Discrete Environments |
| Authors | Ramon Fraga Pereira, Nir Oren, Felipe Meneguzzi |
| Abstract | Assessing whether an agent has abandoned a goal or is actively pursuing it is important when multiple agents are trying to achieve joint goals, or when agents commit to achieving goals for each other. Making such a determination for a single goal by observing only plan traces is not trivial as agents often deviate from optimal plans for various reasons, including the pursuit of multiple goals or the inability to act optimally. In this article, we develop an approach based on domain independent heuristics from automated planning, landmarks, and fact partitions to identify sub-optimal action steps - with respect to a plan - within a plan execution trace. Such capability is very important in domains where multiple agents cooperate and delegate tasks among themselves, e.g. through social commitments, and need to ensure that a delegating agent can infer whether or not another agent is actually progressing towards a delegated task. We demonstrate how an agent can use our technique to determine - by observing a trace - whether an agent is honouring a commitment. We empirically show, for a number of representative domains, that our approach infers sub-optimal action steps with very high accuracy and detects commitment abandonment in nearly all cases. |
| Tasks | |
| Published | 2019-04-26 |
| URL | http://arxiv.org/abs/1904.11737v1 |
| http://arxiv.org/pdf/1904.11737v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-sub-optimal-plan-detection-to-identify |
| Repo | |
| Framework | |
Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss
| Title | Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss |
| Authors | Cao Liu, Kang Liu, Shizhu He, Zaiqing Nie, Jun Zhao |
| Abstract | We tackle the task of question generation over knowledge bases. Conventional methods for this task neglect two crucial research issues: 1) the given predicate needs to be expressed; 2) the answer to the generated question needs to be definitive. In this paper, we strive toward the above two issues via incorporating diversified contexts and answer-aware loss. Specifically, we propose a neural encoder-decoder model with multi-level copy mechanisms to generate such questions. Furthermore, the answer aware loss is introduced to make generated questions corresponding to more definitive answers. Experiments demonstrate that our model achieves state-of-the-art performance. Meanwhile, such generated question can express the given predicate and correspond to a definitive answer. |
| Tasks | Question Generation |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13108v1 |
| https://arxiv.org/pdf/1910.13108v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-questions-for-knowledge-bases-via |
| Repo | |
| Framework | |
Self-Imitation Learning via Trajectory-Conditioned Policy for Hard-Exploration Tasks
| Title | Self-Imitation Learning via Trajectory-Conditioned Policy for Hard-Exploration Tasks |
| Authors | Yijie Guo, Jongwook Choi, Marcin Moczulski, Samy Bengio, Mohammad Norouzi, Honglak Lee |
| Abstract | Imitation learning from human-expert demonstrations has been shown to be greatly helpful for challenging reinforcement learning problems with sparse environment rewards. However, it is very difficult to achieve similar success without relying on expert demonstrations. Recent works on self-imitation learning showed that imitating the agent’s own past good experience could indirectly drive exploration in some environments, but these methods often lead to sub-optimal and myopic behavior. To address this issue, we argue that exploration in diverse directions by imitating diverse trajectories, instead of focusing on limited good trajectories, is more desirable for the hard-exploration tasks. We propose a new method of learning a trajectory-conditioned policy to imitate diverse trajectories from the agent’s own past experience and show that such self-imitation helps avoid myopic behavior and increases the chance of finding a globally optimal solution for hard-exploration tasks, especially when there are misleading rewards. Our method significantly outperforms existing self-imitation learning and count-based exploration methods on various hard-exploration tasks with local optima. In particular, we report a state-of-the-art score of more than 20,000 points on Montezuma’s Revenge without using expert demonstrations or resetting to arbitrary states. |
| Tasks | Efficient Exploration, Imitation Learning, Montezuma’s Revenge |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10247v2 |
| https://arxiv.org/pdf/1907.10247v2.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-exploration-with-self-imitation |
| Repo | |
| Framework | |
Learning and Exploiting Multiple Subgoals for Fast Exploration in Hierarchical Reinforcement Learning
| Title | Learning and Exploiting Multiple Subgoals for Fast Exploration in Hierarchical Reinforcement Learning |
| Authors | Libo Xing |
| Abstract | Hierarchical Reinforcement Learning (HRL) exploits temporally extended actions, or options, to make decisions from a higher-dimensional perspective to alleviate the sparse reward problem, one of the most challenging problems in reinforcement learning. The majority of existing HRL algorithms require either significant manual design with respect to the specific environment or enormous exploration to automatically learn options from data. To achieve fast exploration without using manual design, we devise a multi-goal HRL algorithm, consisting of a high-level policy Manager and a low-level policy Worker. The Manager provides the Worker multiple subgoals at each time step. Each subgoal corresponds to an option to control the environment. Although the agent may show some confusion at the beginning of training since it is guided by three diverse subgoals, the agent’s behavior policy will quickly learn how to respond to multiple subgoals from the high-level controller on different occasions. By exploiting multiple subgoals, the exploration efficiency is significantly improved. We conduct experiments in Atari’s Montezuma’s Revenge environment, a well-known sparse reward environment, and in doing so achieve the same performance as state-of-the-art HRL methods with substantially reduced training time cost. |
| Tasks | Hierarchical Reinforcement Learning, Montezuma’s Revenge |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.05180v1 |
| https://arxiv.org/pdf/1905.05180v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-and-exploiting-multiple-subgoals-for |
| Repo | |
| Framework | |
Online Convex Optimization in Adversarial Markov Decision Processes
| Title | Online Convex Optimization in Adversarial Markov Decision Processes |
| Authors | Aviv Rosenberg, Yishay Mansour |
| Abstract | We consider online learning in episodic loop-free Markov decision processes (MDPs), where the loss function can change arbitrarily between episodes, and the transition function is not known to the learner. We show $\tilde{O}(LX\sqrt{AT})$ regret bound, where $T$ is the number of episodes, $X$ is the state space, $A$ is the action space, and $L$ is the length of each episode. Our online algorithm is implemented using entropic regularization methodology, which allows to extend the original adversarial MDP model to handle convex performance criteria (different ways to aggregate the losses of a single episode) , as well as improve previous regret bounds. |
| Tasks | |
| Published | 2019-05-19 |
| URL | https://arxiv.org/abs/1905.07773v1 |
| https://arxiv.org/pdf/1905.07773v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-convex-optimization-in-adversarial |
| Repo | |
| Framework | |
Study of Deep Generative Models for Inorganic Chemical Compositions
| Title | Study of Deep Generative Models for Inorganic Chemical Compositions |
| Authors | Yoshihide Sawada, Koji Morikawa, Mikiya Fujii |
| Abstract | Generative models based on generative adversarial networks (GANs) and variational autoencoders (VAEs) have been widely studied in the fields of image generation, speech generation, and drug discovery, but, only a few studies have focused on the generation of inorganic materials. Such studies use the crystal structures of materials, but material researchers rarely store this information. Thus, we generate chemical compositions without using crystal information. We use a conditional VAE (CondVAE) and a conditional GAN (CondGAN) and show that CondGAN using the bag-of-atom representation with physical descriptors generates better compositions than other generative models. Also, we evaluate the effectiveness of the Metropolis-Hastings-based atomic valency modification and the extrapolation performance, which is important to material discovery. |
| Tasks | Drug Discovery, Image Generation |
| Published | 2019-10-25 |
| URL | https://arxiv.org/abs/1910.11499v1 |
| https://arxiv.org/pdf/1910.11499v1.pdf | |
| PWC | https://paperswithcode.com/paper/study-of-deep-generative-models-for-inorganic |
| Repo | |
| Framework | |
Multi-stream Data Analytics for Enhanced Performance Prediction in Fantasy Football
| Title | Multi-stream Data Analytics for Enhanced Performance Prediction in Fantasy Football |
| Authors | Nicholas Bonello, Joeran Beel, Seamus Lawless, Jeremy Debattista |
| Abstract | Fantasy Premier League (FPL) performance predictors tend to base their algorithms purely on historical statistical data. The main problems with this approach is that external factors such as injuries, managerial decisions and other tournament match statistics can never be factored into the final predictions. In this paper, we present a new method for predicting future player performances by automatically incorporating human feedback into our model. Through statistical data analysis such as previous performances, upcoming fixture difficulty ratings, betting market analysis, opinions of the general-public and experts alike via social media and web articles, we can improve our understanding of who is likely to perform well in upcoming matches. When tested on the English Premier League 2018/19 season, the model outperformed regular statistical predictors by over 300 points, an average of 11 points per week, ranking within the top 0.5% of players rank 30,000 out of over 6.5 million players. |
| Tasks | |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07441v1 |
| https://arxiv.org/pdf/1912.07441v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-stream-data-analytics-for-enhanced |
| Repo | |
| Framework | |
An RNN-based IMM Filter Surrogate
| Title | An RNN-based IMM Filter Surrogate |
| Authors | Stefan Becker, Ronny Hug, Wolfgang Hübner, Michael Arens |
| Abstract | The problem of varying dynamics of tracked objects, such as pedestrians, is traditionally tackled with approaches like the Interacting Multiple Model (IMM) filter using a Bayesian formulation. By following the current trend towards using deep neural networks, in this paper an RNN-based IMM filter surrogate is presented. Similar to an IMM filter solution, the presented RNN-based model assigns a probability value to a performed dynamic and, based on them, puts out a multi-modal distribution over future pedestrian trajectories. The evaluation is done on synthetic data, reflecting prototypical pedestrian maneuvers. |
| Tasks | |
| Published | 2019-02-05 |
| URL | http://arxiv.org/abs/1902.01739v2 |
| http://arxiv.org/pdf/1902.01739v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-rnn-based-imm-filter-surrogate |
| Repo | |
| Framework | |
Brain MR Image Segmentation in Small Dataset with Adversarial Defense and Task Reorganization
| Title | Brain MR Image Segmentation in Small Dataset with Adversarial Defense and Task Reorganization |
| Authors | Xuhua Ren, Lichi Zhang, Qian Wang, Dinggang Shen |
| Abstract | Medical image segmentation is challenging especially in dealing with small dataset of 3D MR images. Encoding the variation of brain anatomical struc-tures from individual subjects cannot be easily achieved, which is further chal-lenged by only a limited number of well labeled subjects for training. In this study, we aim to address the issue of brain MR image segmentation in small da-taset. First, concerning the limited number of training images, we adopt adver-sarial defense to augment the training data and therefore increase the robustness of the network. Second, inspired by the prior knowledge of neural anatomies, we reorganize the segmentation tasks of different regions into several groups in a hierarchical way. Third, the task reorganization extends to the semantic level, as we incorporate an additional object-level classification task to contribute high-order visual features toward the pixel-level segmentation task. In experiments we validate our method by segmenting gray matter, white matter, and several major regions on a challenge dataset. The proposed method with only seven subjects for training can achieve 84.46% of Dice score in the onsite test set. |
| Tasks | Adversarial Defense, Medical Image Segmentation, Semantic Segmentation |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10400v1 |
| https://arxiv.org/pdf/1906.10400v1.pdf | |
| PWC | https://paperswithcode.com/paper/brain-mr-image-segmentation-in-small-dataset |
| Repo | |
| Framework | |
Style Transfer With Adaptation to the Central Objects of the Scene
| Title | Style Transfer With Adaptation to the Central Objects of the Scene |
| Authors | Alexey Schekalev, Victor Kitov |
| Abstract | Style transfer is a problem of rendering image with some content in the style of another image, for example a family photo in the style of a painting of some famous artist. The drawback of classical style transfer algorithm is that it imposes style uniformly on all parts of the content image, which perturbs central objects on the content image, such as faces or text, and makes them unrecognizable. This work proposes a novel style transfer algorithm which automatically detects central objects on the content image, generates spatial importance mask and imposes style non-uniformly: central objects are stylized less to preserve their recognizability and other parts of the image are stylized as usual to preserve the style. Three methods of automatic central object detection are proposed and evaluated qualitatively and via a user evaluation study. Both comparisons demonstrate higher quality of stylization compared to the classical style transfer method. |
| Tasks | Object Detection, Style Transfer |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01134v1 |
| https://arxiv.org/pdf/1906.01134v1.pdf | |
| PWC | https://paperswithcode.com/paper/style-transfer-with-adaptation-to-the-central |
| Repo | |
| Framework | |
Improved Adversarial Robustness via Logit Regularization Methods
| Title | Improved Adversarial Robustness via Logit Regularization Methods |
| Authors | Cecilia Summers, Michael J. Dinneen |
| Abstract | While great progress has been made at making neural networks effective across a wide range of visual tasks, most models are surprisingly vulnerable. This frailness takes the form of small, carefully chosen perturbations of their input, known as adversarial examples, which represent a security threat for learned vision models in the wild – a threat which should be responsibly defended against in safety-critical applications of computer vision. In this paper, we advocate for and experimentally investigate the use of a family of logit regularization techniques as an adversarial defense, which can be used in conjunction with other methods for creating adversarial robustness at little to no marginal cost. We also demonstrate that much of the effectiveness of one recent adversarial defense mechanism can in fact be attributed to logit regularization, and show how to improve its defense against both white-box and black-box attacks, in the process creating a stronger black-box attack against PGD-based models. We validate our methods on three datasets and include results on both gradient-free attacks and strong gradient-based iterative attacks with as many as 1,000 steps. |
| Tasks | Adversarial Defense |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.03749v1 |
| https://arxiv.org/pdf/1906.03749v1.pdf | |
| PWC | https://paperswithcode.com/paper/improved-adversarial-robustness-via-logit |
| Repo | |
| Framework | |
The phase diagram of approximation rates for deep neural networks
| Title | The phase diagram of approximation rates for deep neural networks |
| Authors | Dmitry Yarotsky, Anton Zhevnerchuk |
| Abstract | We explore the phase diagram of approximation rates for deep neural networks. The phase diagram describes theoretically optimal accuracy-complexity relations and their qualitative properties. Our contribution is three-fold. First, we generalize the existing result on the existence of deep discontinuous phase in ReLU networks to functional classes of arbitrary positive smoothness, and identify the boundary between the feasible and infeasible rates. Second, we demonstrate that standard fully-connected architectures of a fixed width independent of smoothness can adapt to smoothness and achieve almost optimal rates. Finally, we discuss how the phase diagram can change in the case of non-ReLU activation functions. In particular, we prove that using both sine and ReLU activations theoretically leads to very fast, nearly exponential approximation rates, thanks to the emerging capability of the network to implement efficient lookup operations. |
| Tasks | |
| Published | 2019-06-22 |
| URL | https://arxiv.org/abs/1906.09477v1 |
| https://arxiv.org/pdf/1906.09477v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-phase-diagram-of-approximation-rates-for |
| Repo | |
| Framework | |
Heterogeneous Domain Adaptation via Soft Transfer Network
| Title | Heterogeneous Domain Adaptation via Soft Transfer Network |
| Authors | Yuan Yao, Yu Zhang, Xutao Li, Yunming Ye |
| Abstract | Heterogeneous domain adaptation (HDA) aims to facilitate the learning task in a target domain by borrowing knowledge from a heterogeneous source domain. In this paper, we propose a Soft Transfer Network (STN), which jointly learns a domain-shared classifier and a domain-invariant subspace in an end-to-end manner, for addressing the HDA problem. The proposed STN not only aligns the discriminative directions of domains but also matches both the marginal and conditional distributions across domains. To circumvent negative transfer, STN aligns the conditional distributions by using the soft-label strategy of unlabeled target data, which prevents the hard assignment of each unlabeled target data to only one category that may be incorrect. Further, STN introduces an adaptive coefficient to gradually increase the importance of the soft-labels since they will become more and more accurate as the number of iterations increases. We perform experiments on the transfer tasks of image-to-image, text-to-image, and text-to-text. Experimental results testify that the STN significantly outperforms several state-of-the-art approaches. |
| Tasks | Domain Adaptation |
| Published | 2019-08-28 |
| URL | https://arxiv.org/abs/1908.10552v1 |
| https://arxiv.org/pdf/1908.10552v1.pdf | |
| PWC | https://paperswithcode.com/paper/heterogeneous-domain-adaptation-via-soft |
| Repo | |
| Framework | |
Analyzing an Imitation Learning Network for Fundus Image Registration Using a Divide-and-Conquer Approach
| Title | Analyzing an Imitation Learning Network for Fundus Image Registration Using a Divide-and-Conquer Approach |
| Authors | Siming Bayer, Xia Zhong, Weilin Fu, Nishant Ravikumar, Andreas Maier |
| Abstract | Comparison of microvascular circulation on fundoscopic images is a non-invasive clinical indication for the diagnosis and monitoring of diseases, such as diabetes and hypertensions. The differences between intra-patient images can be assessed quantitatively by registering serial acquisitions. Due to the variability of the images (i.e. contrast, luminosity) and the anatomical changes of the retina, the registration of fundus images remains a challenging task. Recently, several deep learning approaches have been proposed to register fundus images in an end-to-end fashion, achieving remarkable results. However, the results are difficult to interpret and analyze. In this work, we propose an imitation learning framework for the registration of 2D color funduscopic images for a wide range of applications such as disease monitoring, image stitching and super-resolution. We follow a divide-and-conquer approach to improve the interpretability of the proposed network, and analyze both the influence of the input image and the hyperparameters on the registration result. The results show that the proposed registration network reduces the initial target registration error up to 95%. |
| Tasks | Image Registration, Image Stitching, Imitation Learning, Super-Resolution |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.10837v1 |
| https://arxiv.org/pdf/1912.10837v1.pdf | |
| PWC | https://paperswithcode.com/paper/analyzing-an-imitation-learning-network-for |
| Repo | |
| Framework | |
