July 29, 2019

2772 words 14 mins read

Paper Group ANR 77

Rank of Experts: Detection Network Ensemble. Enhanced Attacks on Defensively Distilled Deep Neural Networks. Czech Text Document Corpus v 2.0. Wide-Residual-Inception Networks for Real-time Object Detection. Multi-shot Pedestrian Re-identification via Sequential Decision Making. Stochastic L-BFGS: Improved Convergence Rates and Practical Accelerati …

Rank of Experts: Detection Network Ensemble


Title	Rank of Experts: Detection Network Ensemble
Authors	Seung-Hwan Bae, Youngwan Lee, Youngjoo Jo, Yuseok Bae, Joong-won Hwang
Abstract	The recent advances of convolutional detectors show impressive performance improvement for large scale object detection. However, in general, the detection performance usually decreases as the object classes to be detected increases, and it is a practically challenging problem to train a dominant model for all classes due to the limitations of detection models and datasets. In most cases, therefore, there are distinct performance differences of the modern convolutional detectors for each object class detection. In this paper, in order to build an ensemble detector for large scale object detection, we present a conceptually simple but very effective class-wise ensemble detection which is named as Rank of Experts. We first decompose an intractable problem of finding the best detections for all object classes into small subproblems of finding the best ones for each object class. We then solve the detection problem by ranking detectors in order of the average precision rate for each class, and then aggregate the responses of the top ranked detectors (i.e. experts) for class-wise ensemble detection. The main benefit of our method is easy to implement and does not require any joint training of experts for ensemble. Based on the proposed Rank of Experts, we won the 2nd place in the ILSVRC 2017 object detection competition.
Tasks	Object Detection
Published	2017-12-01
URL	http://arxiv.org/abs/1712.00185v1
PDF	http://arxiv.org/pdf/1712.00185v1.pdf
PWC	https://paperswithcode.com/paper/rank-of-experts-detection-network-ensemble
Repo
Framework

Enhanced Attacks on Defensively Distilled Deep Neural Networks


Title	Enhanced Attacks on Defensively Distilled Deep Neural Networks
Authors	Yujia Liu, Weiming Zhang, Shaohua Li, Nenghai Yu
Abstract	Deep neural networks (DNNs) have achieved tremendous success in many tasks of machine learning, such as the image classification. Unfortunately, researchers have shown that DNNs are easily attacked by adversarial examples, slightly perturbed images which can mislead DNNs to give incorrect classification results. Such attack has seriously hampered the deployment of DNN systems in areas where security or safety requirements are strict, such as autonomous cars, face recognition, malware detection. Defensive distillation is a mechanism aimed at training a robust DNN which significantly reduces the effectiveness of adversarial examples generation. However, the state-of-the-art attack can be successful on distilled networks with 100% probability. But it is a white-box attack which needs to know the inner information of DNN. Whereas, the black-box scenario is more general. In this paper, we first propose the epsilon-neighborhood attack, which can fool the defensively distilled networks with 100% success rate in the white-box setting, and it is fast to generate adversarial examples with good visual quality. On the basis of this attack, we further propose the region-based attack against defensively distilled DNNs in the black-box setting. And we also perform the bypass attack to indirectly break the distillation defense as a complementary method. The experimental results show that our black-box attacks have a considerable success rate on defensively distilled networks.
Tasks	Face Recognition, Image Classification, Malware Detection
Published	2017-11-16
URL	http://arxiv.org/abs/1711.05934v1
PDF	http://arxiv.org/pdf/1711.05934v1.pdf
PWC	https://paperswithcode.com/paper/enhanced-attacks-on-defensively-distilled
Repo
Framework

Czech Text Document Corpus v 2.0


Title	Czech Text Document Corpus v 2.0
Authors	Pavel Král, Ladislav Lenc
Abstract	This paper introduces “Czech Text Document Corpus v 2.0”, a collection of text documents for automatic document classification in Czech language. It is composed of the text documents provided by the Czech News Agency and is freely available for research purposes at http://ctdc.kiv.zcu.cz/. This corpus was created in order to facilitate a straightforward comparison of the document classification approaches on Czech data. It is particularly dedicated to evaluation of multi-label document classification approaches, because one document is usually labelled with more than one label. Besides the information about the document classes, the corpus is also annotated at the morphological layer. This paper further shows the results of selected state-of-the-art methods on this corpus to offer the possibility of an easy comparison with these approaches.
Tasks	Document Classification
Published	2017-10-06
URL	http://arxiv.org/abs/1710.02365v2
PDF	http://arxiv.org/pdf/1710.02365v2.pdf
PWC	https://paperswithcode.com/paper/czech-text-document-corpus-v-20
Repo
Framework

Wide-Residual-Inception Networks for Real-time Object Detection


Title	Wide-Residual-Inception Networks for Real-time Object Detection
Authors	Youngwan Lee, Byeonghak Yim, Huien Kim, Eunsoo Park, Xuenan Cui, Taekang Woo, Hakil Kim
Abstract	Since convolutional neural network(CNN)models emerged,several tasks in computer vision have actively deployed CNN models for feature extraction. However,the conventional CNN models have a high computational cost and require high memory capacity, which is impractical and unaffordable for commercial applications such as real-time on-road object detection on embedded boards or mobile platforms. To tackle this limitation of CNN models, this paper proposes a wide-residual-inception (WR-Inception) network, which constructs the architecture based on a residual inception unit that captures objects of various sizes on the same feature map, as well as shallower and wider layers, compared to state-of-the-art networks like ResNet. To verify the proposed networks, this paper conducted two experiments; one is a classification task on CIFAR-10/100 and the other is an on-road object detection task using a Single-Shot Multi-box Detector(SSD) on the KITTI dataset.
Tasks	Object Detection, Real-Time Object Detection
Published	2017-02-04
URL	http://arxiv.org/abs/1702.01243v3
PDF	http://arxiv.org/pdf/1702.01243v3.pdf
PWC	https://paperswithcode.com/paper/wide-residual-inception-networks-for-real
Repo
Framework

Multi-shot Pedestrian Re-identification via Sequential Decision Making


Title	Multi-shot Pedestrian Re-identification via Sequential Decision Making
Authors	Jianfu Zhang, Naiyan Wang, Liqing Zhang
Abstract	Multi-shot pedestrian re-identification problem is at the core of surveillance video analysis. It matches two tracks of pedestrians from different cameras. In contrary to existing works that aggregate single frames features by time series model such as recurrent neural network, in this paper, we propose an interpretable reinforcement learning based approach to this problem. Particularly, we train an agent to verify a pair of images at each time. The agent could choose to output the result (same or different) or request another pair of images to verify (unsure). By this way, our model implicitly learns the difficulty of image pairs, and postpone the decision when the model does not accumulate enough evidence. Moreover, by adjusting the reward for unsure action, we can easily trade off between speed and accuracy. In three open benchmarks, our method are competitive with the state-of-the-art methods while only using 3% to 6% images. These promising results demonstrate that our method is favorable in both efficiency and performance.
Tasks	Decision Making, Time Series
Published	2017-12-19
URL	http://arxiv.org/abs/1712.07257v2
PDF	http://arxiv.org/pdf/1712.07257v2.pdf
PWC	https://paperswithcode.com/paper/multi-shot-pedestrian-re-identification-via
Repo
Framework

Stochastic L-BFGS: Improved Convergence Rates and Practical Acceleration Strategies


Title	Stochastic L-BFGS: Improved Convergence Rates and Practical Acceleration Strategies
Authors	Renbo Zhao, William B. Haskell, Vincent Y. F. Tan
Abstract	We revisit the stochastic limited-memory BFGS (L-BFGS) algorithm. By proposing a new framework for the convergence analysis, we prove improved convergence rates and computational complexities of the stochastic L-BFGS algorithms compared to previous works. In addition, we propose several practical acceleration strategies to speed up the empirical performance of such algorithms. We also provide theoretical analyses for most of the strategies. Experiments on large-scale logistic and ridge regression problems demonstrate that our proposed strategies yield significant improvements vis-`a-vis competing state-of-the-art algorithms.
Tasks
Published	2017-04-01
URL	http://arxiv.org/abs/1704.00116v3
PDF	http://arxiv.org/pdf/1704.00116v3.pdf
PWC	https://paperswithcode.com/paper/stochastic-l-bfgs-improved-convergence-rates
Repo
Framework

Pseudorehearsal in actor-critic agents with neural network function approximation


Title	Pseudorehearsal in actor-critic agents with neural network function approximation
Authors	Vladimir Marochko, Leonard Johard, Manuel Mazzara, Luca Longo
Abstract	Catastrophic forgetting has a significant negative impact in reinforcement learning. The purpose of this study is to investigate how pseudorehearsal can change performance of an actor-critic agent with neural-network function approximation. We tested agent in a pole balancing task and compared different pseudorehearsal approaches. We have found that pseudorehearsal can assist learning and decrease forgetting.
Tasks
Published	2017-12-20
URL	http://arxiv.org/abs/1712.07686v2
PDF	http://arxiv.org/pdf/1712.07686v2.pdf
PWC	https://paperswithcode.com/paper/pseudorehearsal-in-actor-critic-agents-with
Repo
Framework

Physiological and behavioral profiling for nociceptive pain estimation using personalized multitask learning


Title	Physiological and behavioral profiling for nociceptive pain estimation using personalized multitask learning
Authors	Daniel Lopez-Martinez, Ognjen Rudovic, Rosalind Picard
Abstract	Pain is a subjective experience commonly measured through patient’s self report. While there exist numerous situations in which automatic pain estimation methods may be preferred, inter-subject variability in physiological and behavioral pain responses has hindered the development of such methods. In this work, we address this problem by introducing a novel personalized multitask machine learning method for pain estimation based on individual physiological and behavioral pain response profiles, and show its advantages in a dataset containing multimodal responses to nociceptive heat pain.
Tasks
Published	2017-11-10
URL	http://arxiv.org/abs/1711.04036v1
PDF	http://arxiv.org/pdf/1711.04036v1.pdf
PWC	https://paperswithcode.com/paper/physiological-and-behavioral-profiling-for
Repo
Framework

Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks


Title	Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks
Authors	Marian Tietz, Tayfun Alpay, Johannes Twiefel, Stefan Wermter
Abstract	Ladder networks are a notable new concept in the field of semi-supervised learning by showing state-of-the-art results in image recognition tasks while being compatible with many existing neural architectures. We present the recurrent ladder network, a novel modification of the ladder network, for semi-supervised learning of recurrent neural networks which we evaluate with a phoneme recognition task on the TIMIT corpus. Our results show that the model is able to consistently outperform the baseline and achieve fully-supervised baseline performance with only 75% of all labels which demonstrates that the model is capable of using unsupervised data as an effective regulariser.
Tasks
Published	2017-06-07
URL	http://arxiv.org/abs/1706.02124v2
PDF	http://arxiv.org/pdf/1706.02124v2.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-phoneme-recognition-with
Repo
Framework

Automatic detection and decoding of honey bee waggle dances


Title	Automatic detection and decoding of honey bee waggle dances
Authors	Fernando Wario, Benjamin Wild, Raúl Rojas, Tim Landgraf
Abstract	The waggle dance is one of the most popular examples of animal communication. Forager bees direct their nestmates to profitable resources via a complex motor display. Essentially, the dance encodes the polar coordinates to the resource in the field. Unemployed foragers follow the dancer’s movements and then search for the advertised spots in the field. Throughout the last decades, biologists have employed different techniques to measure key characteristics of the waggle dance and decode the information it conveys. Early techniques involved the use of protractors and stopwatches to measure the dance orientation and duration directly from the observation hive. Recent approaches employ digital video recordings and manual measurements on screen. However, manual approaches are very time-consuming. Most studies, therefore, regard only small numbers of animals in short periods of time. We have developed a system capable of automatically detecting, decoding and mapping communication dances in real-time. In this paper, we describe our recording setup, the image processing steps performed for dance detection and decoding and an algorithm to map dances to the field. The proposed system performs with a detection accuracy of 90.07%. The decoded waggle orientation has an average error of -2.92{\deg} ($\pm$ 7.37{\deg} ), well within the range of human error. To evaluate and exemplify the system’s performance, a group of bees was trained to an artificial feeder, and all dances in the colony were automatically detected, decoded and mapped. The system presented here is the first of this kind made publicly available, including source code and hardware specifications. We hope this will foster quantitative analyses of the honey bee waggle dance.
Tasks
Published	2017-08-22
URL	http://arxiv.org/abs/1708.06590v3
PDF	http://arxiv.org/pdf/1708.06590v3.pdf
PWC	https://paperswithcode.com/paper/automatic-detection-and-decoding-of-honey-bee
Repo
Framework

Panorama to panorama matching for location recognition


Title	Panorama to panorama matching for location recognition
Authors	Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Teddy Furon, Ondrej Chum
Abstract	Location recognition is commonly treated as visual instance retrieval on “street view” imagery. The dataset items and queries are panoramic views, i.e. groups of images taken at a single location. This work introduces a novel panorama-to-panorama matching process, either by aggregating features of individual images in a group or by explicitly constructing a larger panorama. In either case, multiple views are used as queries. We reach near perfect location recognition on a standard benchmark with only four query views.
Tasks
Published	2017-04-21
URL	http://arxiv.org/abs/1704.06591v1
PDF	http://arxiv.org/pdf/1704.06591v1.pdf
PWC	https://paperswithcode.com/paper/panorama-to-panorama-matching-for-location
Repo
Framework

Volumetric Data Exploration with Machine Learning-Aided Visualization in Neutron Science


Title	Volumetric Data Exploration with Machine Learning-Aided Visualization in Neutron Science
Authors	Yawei Hui, Yaohua Liu
Abstract	Recent advancements in neutron and X-ray sources, instrumentation and data collection modes have significantly increased the experimental data size (which could easily contain 10$^{8}$ – 10$^{10}$ data points), so that conventional volumetric visualization approaches become inefficient for both still imaging and interactive OpenGL rendition in a 3D setting. We introduce a new approach based on the unsupervised machine learning algorithm, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), to efficiently analyze and visualize large volumetric datasets. Here we present two examples of analyzing and visualizing datasets from the diffuse scattering experiment of a single crystal sample and the tomographic reconstruction of a neutron scanning of a turbine blade. We found that by using the intensity as the weighting factor in the clustering process, DBSCAN becomes very effective in de-noising and feature/boundary detection, and thus enables better visualization of the hierarchical internal structures of the neutron scattering data.
Tasks	Boundary Detection
Published	2017-10-16
URL	http://arxiv.org/abs/1710.05994v3
PDF	http://arxiv.org/pdf/1710.05994v3.pdf
PWC	https://paperswithcode.com/paper/volumetric-data-exploration-with-machine
Repo
Framework

Semantic Segmentation from Limited Training Data


Title	Semantic Segmentation from Limited Training Data
Authors	A. Milan, T. Pham, K. Vijay, D. Morrison, A. W. Tow, L. Liu, J. Erskine, R. Grinover, A. Gurman, T. Hunn, N. Kelly-Boxall, D. Lee, M. McTaggart, G. Rallos, A. Razjigaev, T. Rowntree, T. Shen, R. Smith, S. Wade-McCue, Z. Zhuang, C. Lehnert, G. Lin, I. Reid, P. Corke, J. Leitner
Abstract	We present our approach for robotic perception in cluttered scenes that led to winning the recent Amazon Robotics Challenge (ARC) 2017. Next to small objects with shiny and transparent surfaces, the biggest challenge of the 2017 competition was the introduction of unseen categories. In contrast to traditional approaches which require large collections of annotated data and many hours of training, the task here was to obtain a robust perception pipeline with only few minutes of data acquisition and training time. To that end, we present two strategies that we explored. One is a deep metric learning approach that works in three separate steps: semantic-agnostic boundary detection, patch classification and pixel-wise voting. The other is a fully-supervised semantic segmentation approach with efficient dataset collection. We conduct an extensive analysis of the two methods on our ARC 2017 dataset. Interestingly, only few examples of each class are sufficient to fine-tune even very deep convolutional neural networks for this specific task.
Tasks	Boundary Detection, Metric Learning, Semantic Segmentation
Published	2017-09-22
URL	http://arxiv.org/abs/1709.07665v1
PDF	http://arxiv.org/pdf/1709.07665v1.pdf
PWC	https://paperswithcode.com/paper/semantic-segmentation-from-limited-training
Repo
Framework

Balanced Excitation and Inhibition are Required for High-Capacity, Noise-Robust Neuronal Selectivity


Title	Balanced Excitation and Inhibition are Required for High-Capacity, Noise-Robust Neuronal Selectivity
Authors	Ran Rubin, L. F. Abbott, Haim Sompolinsky
Abstract	Neurons and networks in the cerebral cortex must operate reliably despite multiple sources of noise. To evaluate the impact of both input and output noise, we determine the robustness of single-neuron stimulus selective responses, as well as the robustness of attractor states of networks of neurons performing memory tasks. We find that robustness to output noise requires synaptic connections to be in a balanced regime in which excitation and inhibition are strong and largely cancel each other. We evaluate the conditions required for this regime to exist and determine the properties of networks operating within it. A plausible synaptic plasticity rule for learning that balances weight configurations is presented. Our theory predicts an optimal ratio of the number of excitatory and inhibitory synapses for maximizing the encoding capacity of balanced networks for a given statistics of afferent activations. Previous work has shown that balanced networks amplify spatio-temporal variability and account for observed asynchronous irregular states. Here we present a novel type of balanced network that amplifies small changes in the impinging signals, and emerges automatically from learning to perform neuronal and network functions robustly.
Tasks
Published	2017-05-03
URL	http://arxiv.org/abs/1705.01502v1
PDF	http://arxiv.org/pdf/1705.01502v1.pdf
PWC	https://paperswithcode.com/paper/balanced-excitation-and-inhibition-are
Repo
Framework

Learning rates for classification with Gaussian kernels


Title	Learning rates for classification with Gaussian kernels
Authors	Shao-Bo Lin, Jinshan Zeng, Xiangyu Chang
Abstract	This paper aims at refined error analysis for binary classification using support vector machine (SVM) with Gaussian kernel and convex loss. Our first result shows that for some loss functions such as the truncated quadratic loss and quadratic loss, SVM with Gaussian kernel can reach the almost optimal learning rate, provided the regression function is smooth. Our second result shows that, for a large number of loss functions, under some Tsybakov noise assumption, if the regression function is infinitely smooth, then SVM with Gaussian kernel can achieve the learning rate of order $m^{-1}$, where $m$ is the number of samples.
Tasks
Published	2017-02-28
URL	http://arxiv.org/abs/1702.08701v3
PDF	http://arxiv.org/pdf/1702.08701v3.pdf
PWC	https://paperswithcode.com/paper/learning-rates-for-classification-with
Repo
Framework