October 21, 2019

3434 words 17 mins read

Paper Group AWR 89

Neural Network Decoders for Large-Distance 2D Toric Codes. Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells. Real-Time Object Pose Estimation with Pose Interpreter Networks. Visual Re-ranking with Natural Language Understanding for Text Spotting. Multi-Objective De Novo Drug Design with Conditional Graph G …

Neural Network Decoders for Large-Distance 2D Toric Codes


Title	Neural Network Decoders for Large-Distance 2D Toric Codes
Authors	Xiaotong Ni
Abstract	We still do not have the perfect decoders for topological codes that can satisfy all needs of different experimental setups. Recently, a few neural network based decoders have been studied, with the motivation that they can adapt to a wide range of noise models, and can easily run on dedicated chips without a full-fledged computer. The later feature might lead to fast speed and the ability to operate in low temperature. However, a question which has not been addressed in previous works is whether neural network decoders can handle 2D topological codes with large distances. In this work, we provide a positive answer for the toric code. The structure of our neural network decoder is inspired by the renormalization group decoder. With a fairly strict policy on training time, when the bit-flip error rate is lower than $9%$, the neural network decoder performs better when code distance increases. With a less strict policy, we find it is not hard for the neural decoder to achieve a performance close to the minimum-weight perfect matching algorithm. The numerical simulation is done up to code distance $d=64$. Last but not least, we describe and analyze a few failed approaches. They guide us to the final design of our neural decoder, but also serve as a caution when we gauge the versatility of stock deep neural networks. The source code of our neural decoder can be found at https://github.com/XiaotongNi/toric-code-neural-decoder .
Tasks
Published	2018-09-18
URL	https://arxiv.org/abs/1809.06640v2
PDF	https://arxiv.org/pdf/1809.06640v2.pdf
PWC	https://paperswithcode.com/paper/neural-network-decoders-for-large-distance-2d
Repo	https://github.com/XiaotongNi/toric-code-neural-decoder
Framework	tf

Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells


Title	Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
Authors	Vladimir Nekrasov, Hao Chen, Chunhua Shen, Ian Reid
Abstract	Automated design of neural network architectures tailored for a specific task is an extremely promising, albeit inherently difficult, avenue to explore. While most results in this domain have been achieved on image classification and language modelling problems, here we concentrate on dense per-pixel tasks, in particular, semantic image segmentation using fully convolutional networks. In contrast to the aforementioned areas, the design choices of a fully convolutional network require several changes, ranging from the sort of operations that need to be used—e.g., dilated convolutions—to a solving of a more difficult optimisation problem. In this work, we are particularly interested in searching for high-performance compact segmentation architectures, able to run in real-time using limited resources. To achieve that, we intentionally over-parameterise the architecture during the training time via a set of auxiliary cells that provide an intermediate supervisory signal and can be omitted during the evaluation phase. The design of the auxiliary cell is emitted by a controller, a neural network with the fixed structure trained using reinforcement learning. More crucially, we demonstrate how to efficiently search for these architectures within limited time and computational budgets. In particular, we rely on a progressive strategy that terminates non-promising architectures from being further trained, and on Polyak averaging coupled with knowledge distillation to speed-up the convergence. Quantitatively, in 8 GPU-days our approach discovers a set of architectures performing on-par with state-of-the-art among compact models on the semantic segmentation, pose estimation and depth prediction tasks. Code will be made available here: https://github.com/drsleep/nas-segm-pytorch
Tasks	Depth Estimation, Image Classification, Language Modelling, Neural Architecture Search, Pose Estimation, Semantic Segmentation
Published	2018-10-25
URL	https://arxiv.org/abs/1810.10804v3
PDF	https://arxiv.org/pdf/1810.10804v3.pdf
PWC	https://paperswithcode.com/paper/fast-neural-architecture-search-of-compact
Repo	https://github.com/drsleep/nas-segm-pytorch
Framework	pytorch

Real-Time Object Pose Estimation with Pose Interpreter Networks


Title	Real-Time Object Pose Estimation with Pose Interpreter Networks
Authors	Jimmy Wu, Bolei Zhou, Rebecca Russell, Vincent Kee, Syler Wagner, Mitchell Hebert, Antonio Torralba, David M. S. Johnson
Abstract	In this work, we introduce pose interpreter networks for 6-DoF object pose estimation. In contrast to other CNN-based approaches to pose estimation that require expensively annotated object pose data, our pose interpreter network is trained entirely on synthetic pose data. We use object masks as an intermediate representation to bridge real and synthetic. We show that when combined with a segmentation model trained on RGB images, our synthetically trained pose interpreter network is able to generalize to real data. Our end-to-end system for object pose estimation runs in real-time (20 Hz) on live RGB data, without using depth information or ICP refinement.
Tasks	Pose Estimation
Published	2018-08-03
URL	http://arxiv.org/abs/1808.01099v1
PDF	http://arxiv.org/pdf/1808.01099v1.pdf
PWC	https://paperswithcode.com/paper/real-time-object-pose-estimation-with-pose
Repo	https://github.com/jimmyyhwu/pose-interpreter-networks
Framework	pytorch

Visual Re-ranking with Natural Language Understanding for Text Spotting


Title	Visual Re-ranking with Natural Language Understanding for Text Spotting
Authors	Ahmed Sabir, Francesc Moreno-Noguer, Lluís Padró
Abstract	Many scene text recognition approaches are based on purely visual information and ignore the semantic relation between scene and text. In this paper, we tackle this problem from natural language processing perspective to fill the gap between language and vision. We propose a post-processing approach to improve scene text recognition accuracy by using occurrence probabilities of words (unigram language model), and the semantic correlation between scene and text. For this, we initially rely on an off-the-shelf deep neural network, already trained with a large amount of data, which provides a series of text hypotheses per input image. These hypotheses are then re-ranked using word frequencies and semantic relatedness with objects or scenes in the image. As a result of this combination, the performance of the original network is boosted with almost no additional cost. We validate our approach on ICDAR’17 dataset.
Tasks	Language Modelling, Scene Text Recognition, Text Spotting
Published	2018-10-29
URL	http://arxiv.org/abs/1810.12738v1
PDF	http://arxiv.org/pdf/1810.12738v1.pdf
PWC	https://paperswithcode.com/paper/visual-re-ranking-with-natural-language
Repo	https://github.com/ahmedssabir/dataset
Framework	none

Multi-Objective De Novo Drug Design with Conditional Graph Generative Model


Title	Multi-Objective De Novo Drug Design with Conditional Graph Generative Model
Authors	Yibo Li, Liangren Zhang, Zhenming Liu
Abstract	Recently, deep generative models have revealed itself as a promising way of performing de novo molecule design. However, previous research has focused mainly on generating SMILES strings instead of molecular graphs. Although current graph generative models are available, they are often too general and computationally expensive, which restricts their application to molecules with small sizes. In this work, a new de novo molecular design framework is proposed based on a type sequential graph generators that do not use atom level recurrent units. Compared with previous graph generative models, the proposed method is much more tuned for molecule generation and have been scaled up to cover significantly larger molecules in the ChEMBL database. It is shown that the graph-based model outperforms SMILES based models in a variety of metrics, especially in the rate of valid outputs. For the application of drug design tasks, conditional graph generative model is employed. This method offers higher flexibility compared to previous fine-tuning based approach and is suitable for generation based on multiple objectives. This approach is applied to solve several drug design problems, including the generation of compounds containing a given scaffold, generation of compounds with specific drug-likeness and synthetic accessibility requirements, as well as generating dual inhibitors against JNK3 and GSK3$\beta$. Results show high enrichment rates for outputs satisfying the given requirements.
Tasks
Published	2018-01-18
URL	http://arxiv.org/abs/1801.07299v3
PDF	http://arxiv.org/pdf/1801.07299v3.pdf
PWC	https://paperswithcode.com/paper/multi-objective-de-novo-drug-design-with
Repo	https://github.com/kevinid/molecule_generator
Framework	mxnet

Real-time Power System State Estimation and Forecasting via Deep Neural Networks


Title	Real-time Power System State Estimation and Forecasting via Deep Neural Networks
Authors	Liang Zhang, Gang Wang, Georgios B. Giannakis
Abstract	Contemporary power grids are being challenged by rapid voltage fluctuations that are caused by large-scale deployment of renewable generation, electric vehicles, and demand response programs. In this context, monitoring the grid’s operating conditions in real time becomes increasingly critical. With the emergent large scale and nonconvexity however, the existing power system state estimation (PSSE) schemes become computationally expensive or yield suboptimal performance. To bypass these hurdles, this paper advocates deep neural networks (DNNs) for real-time power system monitoring. By unrolling an iterative physics-based prox-linear solver, a novel model-specific DNN is developed for real-time PSSE with affordable training and minimal tuning effort. To further enable system awareness even ahead of the time horizon, as well as to endow the DNN-based estimator with resilience, deep recurrent neural networks (RNNs) are also pursued for power system state forecasting. Deep RNNs leverage the long-term nonlinear dependencies present in the historical voltage time series to enable forecasting, and they are easy to implement. Numerical tests showcase improved performance of the proposed DNN-based estimation and forecasting approaches compared with existing alternatives. In real load data experiments on the IEEE 118-bus benchmark system, the novel model-specific DNN-based PSSE scheme outperforms nearly by an order-of-magnitude the competing alternatives, including the widely adopted Gauss-Newton PSSE solver.
Tasks	Time Series
Published	2018-11-15
URL	http://arxiv.org/abs/1811.06146v2
PDF	http://arxiv.org/pdf/1811.06146v2.pdf
PWC	https://paperswithcode.com/paper/real-time-power-system-state-estimation-and
Repo	https://github.com/umngangaliqiu/dnn4gnetworking
Framework	tf

MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement


Title	MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement
Authors	Wenbo Bao, Wei-Sheng Lai, Xiaoyun Zhang, Zhiyong Gao, Ming-Hsuan Yang
Abstract	Motion estimation (ME) and motion compensation (MC) have been widely used for classical video frame interpolation systems over the past decades. Recently, a number of data-driven frame interpolation methods based on convolutional neural networks have been proposed. However, existing learning based methods typically estimate either flow or compensation kernels, thereby limiting performance on both computational efficiency and interpolation accuracy. In this work, we propose a motion estimation and compensation driven neural network for video frame interpolation. A novel adaptive warping layer is developed to integrate both optical flow and interpolation kernels to synthesize target frame pixels. This layer is fully differentiable such that both the flow and kernel estimation networks can be optimized jointly. The proposed model benefits from the advantages of motion estimation and compensation methods without using hand-crafted features. Compared to existing methods, our approach is computationally efficient and able to generate more visually appealing results. Furthermore, the proposed MEMC-Net can be seamlessly adapted to several video enhancement tasks, e.g., super-resolution, denoising, and deblocking. Extensive quantitative and qualitative evaluations demonstrate that the proposed method performs favorably against the state-of-the-art video frame interpolation and enhancement algorithms on a wide range of datasets.
Tasks	Denoising, Motion Compensation, Motion Estimation, Optical Flow Estimation, Super-Resolution, Video Frame Interpolation
Published	2018-10-20
URL	https://arxiv.org/abs/1810.08768v2
PDF	https://arxiv.org/pdf/1810.08768v2.pdf
PWC	https://paperswithcode.com/paper/memc-net-motion-estimation-and-motion
Repo	https://github.com/baowenbo/MEMC-Net
Framework	pytorch

Accelerated Gradient Boosting


Title	Accelerated Gradient Boosting
Authors	Gérard Biau, Benoît Cadre, Laurent Rouvìère
Abstract	Gradient tree boosting is a prediction algorithm that sequentially produces a model in the form of linear combinations of decision trees, by solving an infinite-dimensional optimization problem. We combine gradient boosting and Nesterov’s accelerated descent to design a new algorithm, which we call AGB (for Accelerated Gradient Boosting). Substantial numerical evidence is provided on both synthetic and real-life data sets to assess the excellent performance of the method in a large variety of prediction problems. It is empirically shown that AGB is much less sensitive to the shrinkage parameter and outputs predictors that are considerably more sparse in the number of trees, while retaining the exceptional performance of gradient boosting.
Tasks
Published	2018-03-06
URL	http://arxiv.org/abs/1803.02042v1
PDF	http://arxiv.org/pdf/1803.02042v1.pdf
PWC	https://paperswithcode.com/paper/accelerated-gradient-boosting
Repo	https://github.com/lrouviere/AGB
Framework	none

Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection


Title	Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection
Authors	Yongcheng Liu, Lu Sheng, Jing Shao, Junjie Yan, Shiming Xiang, Chunhong Pan
Abstract	Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless, such methods usually require laborious object-level annotations (i.e., object labels and bounding boxes) for effective learning of the object-level visual features. In this paper, we propose a novel and efficient deep framework to boost multi-label classification by distilling knowledge from weakly-supervised detection task without bounding box annotations. Specifically, given the image-level annotations, (1) we first develop a weakly-supervised detection (WSD) model, and then (2) construct an end-to-end multi-label image classification framework augmented by a knowledge distillation module that guides the classification model by the WSD model according to the class-level predictions for the whole image and the object-level visual features for object RoIs. The WSD model is the teacher model and the classification model is the student model. After this cross-task knowledge distillation, the performance of the classification model is significantly improved and the efficiency is maintained since the WSD model can be safely discarded in the test phase. Extensive experiments on two large-scale datasets (MS-COCO and NUS-WIDE) show that our framework achieves superior performances over the state-of-the-art methods on both performance and efficiency.
Tasks	Image Classification, Multi-Label Classification
Published	2018-09-16
URL	http://arxiv.org/abs/1809.05884v2
PDF	http://arxiv.org/pdf/1809.05884v2.pdf
PWC	https://paperswithcode.com/paper/multi-label-image-classification-via
Repo	https://github.com/Yochengliu/MLIC-KD-WSD
Framework	none

Unsupervised Deep Learning for Structured Shape Matching


Title	Unsupervised Deep Learning for Structured Shape Matching
Authors	Jean-Michel Roufosse, Abhishek Sharma, Maks Ovsjanikov
Abstract	We present a novel method for computing correspondences across 3D shapes using unsupervised learning. Our method computes a non-linear transformation of given descriptor functions, while optimizing for global structural properties of the resulting maps, such as their bijectivity or approximate isometry. To this end, we use the functional maps framework, and build upon the recent FMNet architecture for descriptor learning. Unlike that approach, however, we show that learning can be done in a purely \emph{unsupervised setting}, without having access to any ground truth correspondences. This results in a very general shape matching method that we call SURFMNet for Spectral Unsupervised FMNet, and which can be used to establish correspondences within 3D shape collections without any prior information. We demonstrate on a wide range of challenging benchmarks, that our approach leads to state-of-the-art results compared to the existing unsupervised methods and achieves results that are comparable even to the supervised learning techniques. Moreover, our framework is an order of magnitude faster, and does not rely on geodesic distance computation or expensive post-processing.
Tasks
Published	2018-12-10
URL	https://arxiv.org/abs/1812.03794v3
PDF	https://arxiv.org/pdf/1812.03794v3.pdf
PWC	https://paperswithcode.com/paper/unsupervised-deep-learning-for-structured
Repo	https://github.com/JM-data/Unsupervised_FMnet
Framework	tf

Verification for Machine Learning, Autonomy, and Neural Networks Survey


Title	Verification for Machine Learning, Autonomy, and Neural Networks Survey
Authors	Weiming Xiang, Patrick Musau, Ayana A. Wild, Diego Manzanas Lopez, Nathaniel Hamilton, Xiaodong Yang, Joel Rosenfeld, Taylor T. Johnson
Abstract	This survey presents an overview of verification techniques for autonomous systems, with a focus on safety-critical autonomous cyber-physical systems (CPS) and subcomponents thereof. Autonomy in CPS is enabling by recent advances in artificial intelligence (AI) and machine learning (ML) through approaches such as deep neural networks (DNNs), embedded in so-called learning enabled components (LECs) that accomplish tasks from classification to control. Recently, the formal methods and formal verification community has developed methods to characterize behaviors in these LECs with eventual goals of formally verifying specifications for LECs, and this article presents a survey of many of these recent approaches.
Tasks
Published	2018-10-03
URL	http://arxiv.org/abs/1810.01989v1
PDF	http://arxiv.org/pdf/1810.01989v1.pdf
PWC	https://paperswithcode.com/paper/verification-for-machine-learning-autonomy
Repo	https://github.com/verivital/nnv
Framework	none

Extended Bit-Plane Compression for Convolutional Neural Network Accelerators


Title	Extended Bit-Plane Compression for Convolutional Neural Network Accelerators
Authors	Lukas Cavigelli, Luca Benini
Abstract	After the tremendous success of convolutional neural networks in image classification, object detection, speech recognition, etc., there is now rising demand for deployment of these compute-intensive ML models on tightly power constrained embedded and mobile systems at low cost as well as for pushing the throughput in data centers. This has triggered a wave of research towards specialized hardware accelerators. Their performance is often constrained by I/O bandwidth and the energy consumption is dominated by I/O transfers to off-chip memory. We introduce and evaluate a novel, hardware-friendly compression scheme for the feature maps present within convolutional neural networks. We show that an average compression ratio of 4.4x relative to uncompressed data and a gain of 60% over existing method can be achieved for ResNet-34 with a compression block requiring <300 bit of sequential cells and minimal combinational logic.
Tasks	Image Classification, Object Detection, Speech Recognition
Published	2018-10-01
URL	http://arxiv.org/abs/1810.03979v1
PDF	http://arxiv.org/pdf/1810.03979v1.pdf
PWC	https://paperswithcode.com/paper/extended-bit-plane-compression-for
Repo	https://github.com/lukasc-ch/ExtendedBitPlaneCompression
Framework	none

Detecting Adversarial Examples via Neural Fingerprinting


Title	Detecting Adversarial Examples via Neural Fingerprinting
Authors	Sumanth Dathathri, Stephan Zheng, Tianwei Yin, Richard M. Murray, Yisong Yue
Abstract	Deep neural networks are vulnerable to adversarial examples, which dramatically alter model output using small input changes. We propose Neural Fingerprinting, a simple, yet effective method to detect adversarial examples by verifying whether model behavior is consistent with a set of secret fingerprints, inspired by the use of biometric and cryptographic signatures. The benefits of our method are that 1) it is fast, 2) it is prohibitively expensive for an attacker to reverse-engineer which fingerprints were used, and 3) it does not assume knowledge of the adversary. In this work, we pose a formal framework to analyze fingerprints under various threat models, and characterize Neural Fingerprinting for linear models. For complex neural networks, we empirically demonstrate that Neural Fingerprinting significantly improves on state-of-the-art detection mechanisms by detecting the strongest known adversarial attacks with 98-100% AUC-ROC scores on the MNIST, CIFAR-10 and MiniImagenet (20 classes) datasets. In particular, the detection accuracy of Neural Fingerprinting generalizes well to unseen test-data under various black- and whitebox threat models, and is robust over a wide range of hyperparameters and choices of fingerprints.
Tasks
Published	2018-03-11
URL	https://arxiv.org/abs/1803.03870v3
PDF	https://arxiv.org/pdf/1803.03870v3.pdf
PWC	https://paperswithcode.com/paper/detecting-adversarial-examples-via-neural
Repo	https://github.com/StephanZheng/neural-fingerprinting
Framework	tf

Long short-term memory and learning-to-learn in networks of spiking neurons


Title	Long short-term memory and learning-to-learn in networks of spiking neurons
Authors	Guillaume Bellec, Darjan Salaj, Anand Subramoney, Robert Legenstein, Wolfgang Maass
Abstract	Recurrent networks of spiking neurons (RSNNs) underlie the astounding computing and learning capabilities of the brain. But computing and learning capabilities of RSNN models have remained poor, at least in comparison with artificial neural networks (ANNs). We address two possible reasons for that. One is that RSNNs in the brain are not randomly connected or designed according to simple rules, and they do not start learning as a tabula rasa network. Rather, RSNNs in the brain were optimized for their tasks through evolution, development, and prior experience. Details of these optimization processes are largely unknown. But their functional contribution can be approximated through powerful optimization methods, such as backpropagation through time (BPTT). A second major mismatch between RSNNs in the brain and models is that the latter only show a small fraction of the dynamics of neurons and synapses in the brain. We include neurons in our RSNN model that reproduce one prominent dynamical process of biological neurons that takes place at the behaviourally relevant time scale of seconds: neuronal adaptation. We denote these networks as LSNNs because of their Long short-term memory. The inclusion of adapting neurons drastically increases the computing and learning capability of RSNNs if they are trained and configured by deep learning (BPTT combined with a rewiring algorithm that optimizes the network architecture). In fact, the computational performance of these RSNNs approaches for the first time that of LSTM networks. In addition RSNNs with adapting neurons can acquire abstract knowledge from prior learning in a Learning-to-Learn (L2L) scheme, and transfer that knowledge in order to learn new but related tasks from very few examples. We demonstrate this for supervised learning and reinforcement learning.
Tasks
Published	2018-03-26
URL	http://arxiv.org/abs/1803.09574v4
PDF	http://arxiv.org/pdf/1803.09574v4.pdf
PWC	https://paperswithcode.com/paper/long-short-term-memory-and-learning-to-learn
Repo	https://github.com/IGITUGraz/LSNN-official
Framework	tf

Ontology Reasoning with Deep Neural Networks


Title	Ontology Reasoning with Deep Neural Networks
Authors	Patrick Hohenecker, Thomas Lukasiewicz
Abstract	The ability to conduct logical reasoning is a fundamental aspect of intelligent behavior, and thus an important problem along the way to human-level artificial intelligence. Traditionally, symbolic logic-based methods from the field of knowledge representation and reasoning have been used to equip agents with capabilities that resemble human logical reasoning qualities. More recently, however, there has been an increasing interest in using machine learning rather than symbolic logic-based formalisms to tackle these tasks. In this paper, we employ state-of-the-art methods for training deep neural networks to devise a novel model that is able to learn how to effectively perform logical reasoning in the form of basic ontology reasoning. This is an important and at the same time very natural logical reasoning task, which is why the presented approach is applicable to a plethora of important real-world problems. We present the outcomes of several experiments, which show that our model learned to perform precise ontology reasoning on diverse and challenging tasks. Furthermore, it turned out that the suggested approach suffers much less from different obstacles that prohibit logic-based symbolic reasoning, and, at the same time, is surprisingly plausible from a biological point of view.
Tasks
Published	2018-08-24
URL	http://arxiv.org/abs/1808.07980v3
PDF	http://arxiv.org/pdf/1808.07980v3.pdf
PWC	https://paperswithcode.com/paper/ontology-reasoning-with-deep-neural-networks
Repo	https://github.com/phohenecker/family-tree-data-gen
Framework	none