# Latest papers

Ordered by date of publication
##### Tree-structured Kronecker Convolutional Networks for Semantic Segmentation
To tackle this issue, we firstly propose a novel Kronecker convolution which adopts Kronecker product to expand the standard convolutional kernel for taking into account the partial feature neglected by atrous convolutions. Therefore, it can capture partial information and enlarge the receptive field of filters simultaneously without introducing extra parameters.
21
12 Dec 2018
##### Semi-Supervised Learning for Face Sketch Synthesis in the Wild
However, due to the lack of training data (photo-sketch pairs), none of such deep learning based methods can be applied successfully to face photos in the wild. Instead of supervising the network with ground truth sketches, we first perform patch matching in feature space between the input photo and photos in a small reference set of photo-sketch pairs.

6
12 Dec 2018
##### CFUN: Combining Faster R-CNN and U-net Network for Efficient Whole Heart Segmentation
In this paper, we propose a novel heart segmentation pipeline Combining Faster R-CNN and U-net Network (CFUN). Due to Faster R-CNN's precise localization ability and U-net's powerful segmentation ability, CFUN needs only one-step detection and segmentation inference to get the whole heart segmentation result, obtaining good results with significantly reduced computational cost.

6
12 Dec 2018
##### A Multimodal LSTM for Predicting Listener Empathic Responses Over Time
People naturally understand the emotions of-and often also empathize with-those around them. In this paper, we predict the emotional valence of an empathic listener over time as they listen to a speaker narrating a life story.

0
12 Dec 2018
##### Recurrent Neural Networks for Fuzz Testing Web Browsers
Generation-based fuzzing is a software testing approach which is able to discover different types of bugs and vulnerabilities in software. It is, however, known to be very time consuming to design and fine tune classical fuzzers to achieve acceptable coverage, even for small-scale software systems.

1
12 Dec 2018
##### Kernel Treelets
A new method for hierarchical clustering is presented. It combines treelets, a particular multiscale decomposition of data, with a projection on a reproducing kernel Hilbert space.

0
12 Dec 2018
##### Kernel Treelets
A new method for hierarchical clustering is presented. It combines treelets, a particular multiscale decomposition of data, with a projection on a reproducing kernel Hilbert space.

0
12 Dec 2018
##### Deep Anomaly Detection with Outlier Exposure
This approach enables anomaly detectors to generalize and detect unseen anomalies. We also analyze the flexibility and robustness of Outlier Exposure, and identify characteristics of the auxiliary dataset that improve performance.

21
11 Dec 2018
##### Adversarial Framing for Image and Video Classification
Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly modifying most of its pixels, or by occluding it with a patch.

6
11 Dec 2018
##### Merge Double Thompson Sampling for Large Scale Online Ranker Evaluation
Online ranker evaluation is one of the key challenges in information retrieval. While the preferences of rankers can be inferred by interleaved comparison methods, how to effectively choose the pair of rankers to generate the result list without degrading the user experience too much can be formalized as a K-armed dueling bandit problem, which is an online partial-information learning framework, where feedback comes in the form of pair-wise preferences.

0
11 Dec 2018
##### Variational Bayesian Complex Network Reconstruction
Complex network reconstruction is a hot topic in many fields. A popular data-driven reconstruction framework is based on lasso.

0
11 Dec 2018
##### Multichannel Semantic Segmentation with Unsupervised Domain Adaptation
The other is a multitask learning approach that uses depth images as outputs. We demonstrated that the segmentation results were improved by using a multitask learning approach with a post-process and created a benchmark for this task.

2
11 Dec 2018
##### On the Dimensionality of Word Embedding
In this paper, we provide a theoretical understanding of word embedding and its dimensionality. Motivated by the unitary-invariance of word embedding, we propose the Pairwise Inner Product (PIP) loss, a novel metric on the dissimilarity between word embeddings.
75
11 Dec 2018
##### A New Ensemble Learning Framework for 3D Biomedical Image Segmentation
Many 2D and 3D deep learning models have achieved state-of-the-art segmentation performance on 3D biomedical image datasets. In this paper, we propose a new ensemble learning framework for 3D biomedical image segmentation that combines the merits of 2D and 3D models.

8
10 Dec 2018
##### Efficient Condition-based Representations for Long-Term Visual Localization
We propose an approach to localization from images that is designed to explicitly handle the strong variations in appearance happening when capturing conditions change throughout the day or across seasons. As revealed by recent long-term localization benchmarks, both traditional feature-based and retrieval-based approaches still struggle to handle such changes.

0
10 Dec 2018
##### Learning Multiplication-free Linear Transformations
In this paper, we propose several dictionary learning algorithms for sparse representations that also impose specific structures on the learned dictionaries such that they are numerically efficient to use: reduced number of addition/multiplications and even avoiding multiplications altogether. We base our work on factorizations of the dictionary in highly structured basic building blocks (binary orthonormal, scaling and shear transformations) for which we can write closed-form solutions to the optimization problems that we consider.

0
09 Dec 2018
##### Political Popularity Analysis in Social Media
This study has collected and examined 4.5 million tweets related to a US politician, Senator Bernie Sanders. This study investigated eight economic reasons behind the senator's popularity in Twitter.

0
08 Dec 2018
##### Efficient Concept Induction for Description Logics
Concept Induction refers to the problem of creating complex Description Logic class descriptions (i.e., TBox axioms) from instance examples (i.e., ABox data). In this paper we look particularly at the case where both a set of positive and a set of negative instances are given, and complex class expressions are sought under which the positive but not the negative examples fall.

0
08 Dec 2018
##### A biconvex analysis for Lasso l1 reweighting
In this letter, we propose a new convergence analysis of a Lasso l1 reweighting method, based on the observation that the algorithm is an alternated convex search for a biconvex problem. Based on that, we are able to prove the numerical convergence of the sequence of the iterates generated by the algorithm.

0
07 Dec 2018
##### Asynchronous Training of Word Embeddings for Large Text Corpora
Word embeddings are a powerful approach for analyzing language and have been widely popular in numerous tasks in information retrieval and text mining. In this paper, we propose a scalable approach to train word embeddings by partitioning the input space instead in order to scale to massive text corpora while not sacrificing the performance of the embeddings.

1
07 Dec 2018
There is a recent large and growing interest in generative adversarial networks (GANs), which offer powerful features for generative modeling, density estimation, and energy function learning. Ideas stemming from GANs such as adversarial losses are creating research opportunities for other challenges such as domain adaptation.

0
06 Dec 2018
##### Neural Word Search in Historical Manuscript Collections
This is commonly referred to as "word spotting". With only 11 training pages, we enable large scale data collection in manuscript-based historical research.

0
06 Dec 2018
##### Visual Object Networks: Image Generation with Disentangled 3D Representation
Our model first learns to synthesize 3D shapes that are indistinguishable from real shapes. The VON not only generates images that are more realistic than state-of-the-art 2D image synthesis methods, but also enables many 3D operations such as changing the viewpoint of a generated image, editing of shape and texture, linear interpolation in texture and shape space, and transferring appearance across different objects and viewpoints.
0
06 Dec 2018
$J&space;=&space;\int_{t_0}^{t_f}&space;l(\mathbf&space;x,&space;\mathbf&space;u,&space;t)&space;dt$
##### On the stability analysis of optimal state feedbacks as represented by deep neural models
Research has shown how the optimal feedback control of several non linear systems of interest in aerospace applications can be represented by deep neural architectures and trained using techniques including imitation learning, reinforcement learning and evolutionary algorithms. Such deep architectures are here also referred to as Guidance and Control Networks, or G&CNETs.

2
06 Dec 2018
##### MEAL: Multi-Model Ensemble via Adversarial Learning
In this paper, we present a method for compressing large, complex trained ensembles into a single network, where knowledge from a variety of trained deep neural networks (DNNs) is distilled and transferred to a single DNN. In order to distill diverse knowledge from different trained (teacher) models, we propose to use adversarial-based learning strategy where we define a block-wise training loss to guide and optimize the predefined student network to recover the knowledge in teacher models, and to promote the discriminator network to distinguish teacher vs. student features simultaneously.
31
06 Dec 2018
##### Trained Rank Pruning for Efficient Deep Neural Networks
We propose Trained Rank Pruning (TRP), which iterates low rank approximation and training. The TRP trained network has low-rank structure in nature, and can be approximated with negligible performance loss, eliminating fine-tuning after low rank approximation.
0
06 Dec 2018
##### Comparative Document Summarisation via Classification
This paper considers extractive summarisation in a comparative setting: given two or more document groups (e.g., separated by publication time), the goal is to select a small number of documents that are representative of each group, and also maximally distinguishable from other groups. We formulate a set of new objective functions for this problem that connect recent literature on document summarisation, interpretable machine learning, and data subset selection.

0
06 Dec 2018
##### Skin Lesions Classification Using Convolutional Neural Networks in Clinical Images
Skin lesions are conditions that appear on a patient due to many different reasons. One of these can be because of an abnormal growth in skin tissue, defined as cancer.

1
06 Dec 2018
Anomaly detection is a significant and hence well-studied problem. However, developing effective anomaly detection methods for complex and high-dimensional data remains a challenge.

12
06 Dec 2018
##### Are you tough enough? Framework for Robustness Validation of Machine Comprehension Systems
Deep Learning NLP domain lacks procedures for the analysis of model robustness. In addition, we have created and published a new dataset that may be used for validation of robustness of a Q&A model.

1
05 Dec 2018
##### Training Competitive Binary Neural Networks from Scratch
Previous work often uses prior knowledge from full-precision models and complex training strategies. In our work, we focus on increasing the performance of binary neural networks without such prior knowledge and a much simpler training strategy.

32
05 Dec 2018
##### Robust Ordinal Embedding from Contaminated Relative Comparisons
Existing ordinal embedding methods usually follow a two-stage routine: outlier detection is first employed to pick out the inconsistent comparisons; then an embedding is learned from the clean data. However, learning in a multi-stage manner is well-known to suffer from sub-optimal solutions.

2
05 Dec 2018
##### Less but Better: Generalization Enhancement of Ordinal Embedding via Distributional Margin
Meanwhile, recent progress in large margin theory discloses that rather than just maximizing the minimum margin, both the margin mean and variance, which characterize the margin distribution, are more crucial to the overall generalization performance. To address the issue of insufficient training samples, we propose a margin distribution learning paradigm for ordinal embedding, entitled Distributional Margin based Ordinal Embedding (\textit{DMOE}).

3
05 Dec 2018
##### Improving Similarity Search with High-dimensional Locality-sensitive Hashing
We propose a new class of data-independent locality-sensitive hashing (LSH) algorithms based on the fruit fly olfactory circuit. The fundamental difference of this approach is that, instead of assigning hashes as dense points in a low dimensional space, hashes are assigned in a high dimensional space, which enhances their separability.

31
05 Dec 2018
##### Photo-Realistic Blocksworld Dataset
In this report, we introduce an artificial dataset generator for Photo-realistic Blocksworld domain. Blocksworld is one of the oldest high-level task planning domain that is well defined but contains sufficient complexity, e.g., the conflicting subgoals and the decomposability into subproblems.

1
05 Dec 2018
##### Neural Abstractive Text Summarization with Sequence-to-Sequence Models
Many interesting techniques have been proposed to improve the seq2seq models, making them capable of handling different challenges, such as saliency, fluency and human readability, and generate high-quality summaries. As part of this survey, we also develop an open source library, namely Neural Abstractive Text Summarizer (NATS) toolkit, for the abstractive text summarization.

26
05 Dec 2018
##### Attending to Mathematical Language with Transformers
Mathematical expressions were generated, evaluated and used to train neural network models based on the transformer architecture. The expressions and their targets were analyzed as a character-level sequence transduction task in which the encoder and decoder are built on attention mechanisms.

6,089
05 Dec 2018
##### Multi$^{\mathbf{3}}$Net: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery
We propose a novel approach for rapid segmentation of flooded buildings by fusing multiresolution, multisensor, and multitemporal satellite imagery in a convolutional neural network. Our model significantly expedites the generation of satellite imagery-based flood maps, crucial for first responders and local authorities in the early stages of flood events.

2
05 Dec 2018
##### Cerebrovascular Network Segmentation on MRA Images with Deep Learning
Deep learning has been shown to produce state of the art results in many tasks in biomedical imaging, especially in segmentation. Moreover, segmentation of the cerebrovascular structure from magnetic resonance angiography is a challenging problem because its complex geometry and topology have a large inter-patient variability.

0
04 Dec 2018
##### Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware
Using Intel's Loihi neuromorphic research chip and ABR's Nengo Deep Learning toolkit, we analyze the inference speed, dynamic power consumption, and energy cost per inference of a two-layer neural network keyword spotter trained to recognize a single phrase. We perform comparative analyses of this keyword spotter running on more conventional hardware devices including a CPU, a GPU, Nvidia's Jetson TX1, and the Movidius Neural Compute Stick.

0
04 Dec 2018
##### Learning to Sample
We show that it is better to learn how to sample. The network, termed S-NET, takes a point cloud and produces a smaller point cloud that is optimized for a particular task.

4
04 Dec 2018
##### Overcoming Catastrophic Forgetting by Soft Parameter Pruning
However, existing methods try to find the joint distribution of parameters shared with all tasks. In this paper, we proposed a Soft Parameters Pruning (SPP) strategy to reach the trade-off between short-term and long-term profit of a learning model by freeing those parameters less contributing to remember former task domain knowledge to learn future tasks, and preserving memories about previous tasks via those parameters effectively encoding knowledge about tasks at the same time.

2
04 Dec 2018
##### AutoFocus: Efficient Multi-Scale Inference
Instead of processing an entire image pyramid, AutoFocus adopts a coarse to fine approach and only processes regions which are likely to contain small objects at finer scales. To make efficient use of FocusPixels, an algorithm is proposed which generates compact rectangular FocusChips which enclose FocusPixels.

1,828
04 Dec 2018
##### LSCP: Locally Selective Combination in Parallel Outlier Ensembles
In unsupervised outlier ensembles, the absence of ground truth makes the combination of base detectors a challenging task. The top-performing base detectors in this local region are selected and combined as the model's final output.

3
04 Dec 2018
##### SurfConv: Bridging 3D and 2D Convolution for RGBD Images
We tackle the problem of using 3D information in convolutional neural networks for down-stream recognition tasks. On the other hand, 3D convolution wastes a large amount of memory on mostly unoccupied 3D space, which consists of only the surface visible to the sensor.
30
04 Dec 2018
##### Unstructured Semantic Model supported Deep Neural Network for Click-Through Rate Prediction
With the rapid development of online advertising and recommendation systems, click-through rate prediction is expected to play an increasingly important role.Recently many DNN-based models which follow a similar Embedding&MLP paradigm have been proposed, and have achieved good result in image/voice and nlp fields.In these methods the Wide&Deep model announced by Google plays a key role.Most models first map large scale sparse input features into low-dimensional vectors which are transformed to fixed-length vectors, then concatenated together before being fed into a multilayer perceptron (MLP) to learn non-linear relations among input features. The number of trainable variables normally grow dramatically the number of feature fields and the embedding dimension grow.

2
04 Dec 2018
##### Singing Voice Separation Using a Deep Convolutional Neural Network Trained by Ideal Binary Mask and Cross Entropy
We present a unique neural network approach inspired by a technique that has revolutionized the field of vision: pixel-wise image classification, which we combine with cross entropy loss and pretraining of the CNN as an autoencoder on singing voice spectrograms. The IBM identifies the dominant sound source in each T-F bin of the magnitude spectrogram of a mixture signal, by considering each T-F bin as a pixel with a multi-label (for each sound source).

10
04 Dec 2018
##### On learning with shift-invariant structures
We describe new results and algorithms for two different, but related, problems which deal with circulant matrices: learning shift-invariant components from training data and calculating the shift (or alignment) between two given signals. In the first instance, we deal with the shift-invariant dictionary learning problem while the latter bears the name of (compressive) shift retrieval.

0
03 Dec 2018
##### Toward Scalable Neural Dialogue State Tracking Model
The latency in the current neural based dialogue state tracking models prohibits them from being used efficiently for deployment in production systems, albeit their highly accurate performance. This paper proposes a new scalable and accurate neural dialogue state tracking model, based on the recently proposed Global-Local Self-Attention encoder (GLAD) model by Zhong et al. which uses global modules to share parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features.

1
03 Dec 2018
##### What can I do here? Leveraging Deep 3D saliency and geometry for fast and scalable multiple affordance detection
This paper develops and evaluates a novel method that allows for the detection of affordances in a scalable and multiple-instance manner on visually recovered pointclouds. Our approach has many advantages over alternative methods, as it is based on highly parallelizable, one-shot learning that is fast in commodity hardware.

0
03 Dec 2018
##### EnsNet: Ensconce Text in the Wild
The feature of the former is first enhanced by a novel lateral connection structure and then refined by four carefully designed losses: multiscale regression loss and content loss, which capture the global discrepancy of different level features; texture loss and total variation loss, which primarily target filling the text region and preserving the reality of the background. Both qualitative and quantitative sensitivity experiments on synthetic images and the ICDAR 2013 dataset demonstrate that each component of the EnsNet is essential to achieve a good performance.

21
03 Dec 2018
##### Enhancing Perceptual Attributes with Bayesian Style Generation
Deep learning has brought an unprecedented progress in computer vision and significant advances have been made in predicting subjective properties inherent to visual data (e.g., memorability, aesthetic quality, evoked emotions, etc.). Our approach takes as input a natural image and exploits recent models for deep style transfer and generative adversarial networks to change its style in order to modify a specific high-level attribute.

0
03 Dec 2018
##### Deep Learning for Classical Japanese Literature
Much of machine learning research focuses on producing models which perform well on benchmark tasks, in turn improving our understanding of the challenges associated with those tasks. From the perspective of ML researchers, the content of the task itself is largely irrelevant, and thus there have increasingly been calls for benchmark tasks to more heavily focus on problems which are of social or cultural relevance.
186
03 Dec 2018
##### Building Sequential Inference Models for End-to-End Response Selection
This paper presents an end-to-end response selection model for Track 1 of the 7th Dialogue System Technology Challenges (DSTC7). This task focuses on selecting the correct next utterance from a set of candidates given a partial conversation.

1
03 Dec 2018
##### Practical Window Setting Optimization for Medical Image Deep Learning
The recent advancements in deep learning have allowed for numerous applications in computed tomography (CT), with potential to improve diagnostic accuracy, speed of interpretation, and clinical efficiency. However, the deep learning community has to date neglected window display settings - a key feature of clinical CT interpretation and opportunity for additional optimization.

4
03 Dec 2018
##### Deep Cosine Metric Learning for Person Re-Identification
Metric learning aims to construct an embedding where two extracted features corresponding to the same identity are likely to be closer than features from different identities. This paper presents a method for learning such a feature space where the cosine similarity is effectively optimized through a simple re-parametrization of the conventional softmax classification regime.

94
02 Dec 2018
##### Regularized Wasserstein Means Based on Variational Transportation
We raise the problem of regularizing Wasserstein means and propose several terms tailored to tackle different problems. Our formulation is based on variational transportation to distribute a sparse discrete measure into the target domain without mass splitting.

3
02 Dec 2018
##### Macro action selection with deep reinforcement learning in StarCraft
StarCraft (SC) is one of the most popular and successful Real Time Strategy (RTS) games. In recent years, SC is also considered as a testbed for AI research, due to its enormous state space, hidden information, multi-agent collaboration and so on.

12
02 Dec 2018
##### ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
In this paper, we present \emph{ProxylessNAS} that can \emph{directly} learn the architectures for large-scale target tasks and target hardware platforms. We address the high memory consumption issue of differentiable NAS and reduce the computational cost (GPU hours and GPU memory) to the same level of regular training while still allowing a large candidate set.
170
02 Dec 2018
##### Multi-View Egocentric Video Summarization
With vast amounts of video content being uploaded to the Internet every minute, video summarization becomes critical for efficient browsing, searching, and indexing of visual content. In this paper, we propose the problem of summarizing videos recorded simultaneously by several egocentric cameras that intermittently share the field of view.

3
01 Dec 2018
##### GDPP: Learning Diverse Generations Using Determinantal Point Process
A fundamental characteristic of generative models is their ability to produce multi-modal outputs. Embedded in an adversarial training and variational autoencoder, our Generative DPP approach shows a consistent resistance to mode-collapse on a wide-variety of synthetic data and natural image datasets including MNIST, CIFAR10, and CelebA, while outperforming state-of-the-art methods for data-efficiency, convergence-time, and generation quality.
0
30 Nov 2018
##### Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger
We formulate the problem of defogging as state estimation and future state prediction from previous, partial observations in the context of real-time strategy games. We propose to employ encoder-decoder neural networks for this task, and introduce proxy tasks and baselines for evaluation to assess their ability of capturing basic game rules and high-level dynamics.
7
30 Nov 2018
##### Recurrent machines for likelihood-free inference
Likelihood-free inference is concerned with the estimation of the parameters of a non-differentiable stochastic simulator that best reproduce real observations. In the absence of a likelihood function, most of the existing inference methods optimize the simulator parameters through a handcrafted iterative procedure that tries to make the simulated data more similar to the observations.

4
30 Nov 2018
##### Real Time Bangladeshi Sign Language Detection using Faster R-CNN
In this paper, we present a technique to detect BdSL from images that performs in real time. Our method uses Convolutional Neural Network based object detection technique to detect the presence of signs in the image region and to recognize its class.

0
30 Nov 2018
##### iW-Net: an automatic and minimalistic interactive lung nodule segmentation deep network
We propose iW-Net, a deep learning model that allows for both automatic and interactive segmentation of lung nodules in computed tomography images. iW-Net is composed of two blocks: the first one provides an automatic segmentation and the second one allows to correct it by analyzing 2 points introduced by the user in the nodule's boundary.

2
30 Nov 2018
##### Model-blind Video Denoising Via Frame-to-frame Training
Modeling the processing chain that has produced a video is a difficult reverse engineering task, even when the camera is available. This makes model based video processing a still more complex task.

1
30 Nov 2018
##### Non-Local Video Denoising by CNN
The non-locality is incorporated into the network via a first non-trainable layer which finds for each patch in the input image its most similar patches in a search region. To the best of our knowledge, this is the first successful application of a CNN to video denoising.

4
30 Nov 2018
##### Practical methods for graph two-sample testing
Hypothesis testing for graphs has been an important tool in applied research fields for more than two decades, and still remains a challenging problem as one often needs to draw inference from few replicates of large graphs. Recent studies in statistics and learning theory have provided some theoretical insights about such high-dimensional graph testing problems, but the practicality of the developed theoretical methods remains an open question.

0
30 Nov 2018
##### Void Filling of Digital Elevation Models with Deep Generative Models
In recent years, advances in machine learning algorithms, cheap computational resources, and the availability of big data have spurred the deep learning revolution in various application domains. In particular, supervised learning techniques in image analysis have led to superhuman performance in various tasks, such as classification, localization, and segmentation, while unsupervised learning techniques based on increasingly advanced generative models have been applied to generate high-resolution synthetic images indistinguishable from real images.

2
30 Nov 2018
##### Inferring Concept Prerequisite Relations from Online Educational Resources
The Internet has rich and rapidly increasing sources of high quality educational content. PREREQ can learn unknown concept prerequisites from course prerequisites and labeled concept prerequisite data.

0
30 Nov 2018
Vast amount of medical data are stored in different locations ,on many different devices and in different data silos. In this article, we proposed an adaptive boosting method that increases the efficiency of federated machine learning.

0
30 Nov 2018
##### Adversarial Examples as an Input-Fault Tolerance Problem
We analyze the adversarial examples problem in terms of a model's fault tolerance with respect to its input. Whereas previous work focuses on arbitrarily strict threat models, i.e., $\epsilon$-perturbations, we consider arbitrary valid inputs and propose an information-based characteristic for evaluating tolerance to diverse input faults.

0
30 Nov 2018
##### Parsing R-CNN for Instance-Level Human Analysis
Models need to distinguish different human instances in the image panel and learn rich features to represent the details of each instance. Parsing R-CNN is very flexible and efficient, which is applicable to many issues in human instance analysis.
29
30 Nov 2018
##### Lightweight and Efficient Image Super-Resolution with Block State-based Recursive Network
Recently, several deep learning-based image super-resolution methods have been developed by stacking massive numbers of layers. However, this leads too large model sizes and high computational complexities, thus some recursive parameter-sharing methods have been also proposed.

10
30 Nov 2018
##### CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
This motivates us to propose a general and efficient framework, CNN-Cert, that is capable of certifying robustness on general convolutional neural networks. We demonstrate by extensive experiments that our method outperforms state-of-the-art lower-bound-based certification algorithms in terms of both bound quality and speed.

5
29 Nov 2018
##### ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes. Some recent studies hint to a more important role of image textures.
31
29 Nov 2018
##### ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes. Some recent studies hint to a more important role of image textures.
33
29 Nov 2018
##### Parameter-Free Spatial Attention Network for Person Re-Identification
While GAP helps the convolution neural network to attend to the most discriminative features of an object, it may suffer if that information is missing e.g. due to camera viewpoint changes. We propose a novel architecture for Person Re-Identification, based on a novel parameter-free spatial attention layer introducing spatial relations among the feature map activations back to the model.

6
29 Nov 2018
##### Parameter-Free Spatial Attention Network for Person Re-Identification
While GAP helps the convolution neural network to attend to the most discriminative features of an object, it may suffer if that information is missing e.g. due to camera viewpoint changes. We propose a novel architecture for Person Re-Identification, based on a novel parameter-free spatial attention layer introducing spatial relations among the feature map activations back to the model.

6
29 Nov 2018
##### Parameter-Free Spatial Attention Network for Person Re-Identification
While GAP helps the convolution neural network to attend to the most discriminative features of an object, it may suffer if that information is missing e.g. due to camera viewpoint changes. We propose a novel architecture for Person Re-Identification, based on a novel parameter-free spatial attention layer introducing spatial relations among the feature map activations back to the model.

6
29 Nov 2018
##### Improving Robustness of Neural Dialog Systems in a Data-Efficient Way with Turn Dropout
Neural network-based dialog models often lack robustness to anomalous, out-of-domain (OOD) user input which leads to unexpected dialog behavior and thus considerably limits such models' usage in mission-critical production environments. We present a new dataset for studying the robustness of dialog systems to OOD input, which is bAbI Dialog Task 6 augmented with OOD content in a controlled way.

1
29 Nov 2018
##### Learning to Reason with Third-Order Tensor Products
We combine Recurrent Neural Networks with Tensor Product Representations to learn combinatorial representations of sequential data. This improves symbolic interpretation and systematic generalisation.

16
29 Nov 2018
##### Visual SLAM with Network Uncertainty Informed Feature Selection
In order to facilitate long-term localization using a visual simultaneous localization and mapping (SLAM) algorithm, careful feature selection is required such that reference points persist over long durations and the runtime and storage complexity of the algorithm remain consistent. We present SIVO (Semantically Informed Visual Odometry and Mapping), a novel information-theoretic feature selection method for visual SLAM which incorporates machine learning and neural network uncertainty into the feature selection pipeline.

22
29 Nov 2018
##### The SWAG Algorithm; a Mathematical Approach that Outperforms Traditional Deep Learning. Theory and Implementation
The performance of artificial neural networks (ANNs) is influenced by weight initialization, the nature of activation functions, and their architecture. A widespread practice is to use the same type of activation function in all neurons in a given layer.
4
28 Nov 2018
##### 3D human pose estimation in video with temporal convolutions and semi-supervised training
We also introduce back-projection, a simple and effective semi-supervised training method that leverages unlabeled video data. We start with predicted 2D keypoints for unlabeled video, then estimate 3D poses and finally back-project to the input 2D keypoints.

209
28 Nov 2018
##### Attributed Network Embedding for Incomplete Structure Information
Network Embedding (NE) for such an attributed network by considering both structure and attribute information has recently attracted considerable attention, since each node embedding is simply a unified low-dimension vector representation that makes downstream tasks e.g. link prediction more efficient and much easier to realize. The experiments of link prediction and node classification tasks on real-world datasets confirm the robustness and effectiveness of our method to the different levels of the incomplete structure information.

2
28 Nov 2018
##### Attributed Network Embedding for Incomplete Structure Information
Network Embedding (NE) for such an attributed network by considering both structure and attribute information has recently attracted considerable attention, since each node embedding is simply a unified low-dimension vector representation that makes downstream tasks e.g. link prediction more efficient and much easier to realize. The experiments of link prediction and node classification tasks on real-world datasets confirm the robustness and effectiveness of our method to the different levels of the incomplete structure information.

3
28 Nov 2018
##### CCNet: Criss-Cross Attention for Semantic Segmentation
Concretely, for each pixel, our CCNet can harvest the contextual information of its surrounding pixels on the criss-cross path through a novel criss-cross attention module. Compared with the non-local block, the recurrent criss-cross attention module requires $11\times$ less GPU memory usage.
203
28 Nov 2018
In this paper, we present a simple yet effective padding scheme that can be used as a drop-in module for existing convolutional neural networks. We call it partial convolution based padding, with the intuition that the padded region can be treated as holes and the original input as non-holes.
178
28 Nov 2018
##### Robust Face Detection via Learning Small Faces on Hard Images
Recent anchor-based deep face detectors have achieved promising performance, but they are still struggling to detect hard faces, such as small, blurred and partially occluded faces. In this paper, we propose that the robustness of a face detector against hard faces can be improved by learning small faces on hard images.
74
28 Nov 2018
##### Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects
Using our framework and a self-assembled dataset of 3D objects, we investigate the vulnerability of DNNs to OoD poses of well-known objects in ImageNet. We find that 99.9% and 99.4% of the poses misclassified by Inception-v3 also transfer to the AlexNet and ResNet-50 image classifiers trained on the same ImageNet dataset, respectively, and 75.5% transfer to the YOLOv3 object detector trained on MS COCO.
35
28 Nov 2018
A common example arises in the process collecting network data: we often obtain network datasets by recording all of the interactions among a small set of core nodes, so that we end up with a measurement of the network consisting of these core nodes together with a potentially much larger set of fringe nodes that have links to the core. In some datasets, once an algorithm is selected, including any additional data from the fringe can actually hurt prediction performance; in other datasets, including some amount of fringe information is useful before prediction performance saturates or even declines; and in further cases, including the entire fringe leads to the best performance.

7
28 Nov 2018
##### Image Reconstruction with Predictive Filter Flow
We propose a simple, interpretable framework for solving a wide range of image reconstruction problems such as denoising and deconvolution. Given a corrupted input image, the model synthesizes a spatially varying linear filter which, when applied to the input image, reconstructs the desired output.

10
28 Nov 2018
##### GIRNet: Interleaved Multi-Task Recurrent State Sequence Models
Or, we may have available models for labeling whole passages (say, with sentiments), which we would like to exploit toward better position-specific label inference (say, target-dependent sentiment annotation). A primary instance is also submitted to each auxiliary RNN, but their state sequences are gated and merged into a novel composite state sequence tailored to the primary inference task.

3
28 Nov 2018
##### ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2, for modeling visual and sequential data. Our network uses group point-wise and depth-wise dilated separable convolutions to learn representations from a large effective receptive field with fewer FLOPs and parameters.
78
28 Nov 2018
##### Spectral Feature Transformation for Person Re-identification
With the surge of deep learning techniques, the field of person re-identification has witnessed rapid progress in recent years. Deep learning based methods focus on learning a feature space where samples are clustered compactly according to their corresponding identities.

7
28 Nov 2018
We introduce the Metropolis-Hastings generative adversarial network (MH-GAN), which combines aspects of Markov chain Monte Carlo and GANs. The MH-GAN draws samples from the distribution implicitly defined by a GAN's discriminator-generator pair, as opposed to sampling in a standard GAN which draws samples from the distribution defined by the generator.
36
28 Nov 2018
##### Effective Ways to Build and Evaluate Individual Survival Distributions
An accurate model of a patient's individual survival distribution can help determine the appropriate treatment for terminal patients. This paper first motivates such "individual survival distribution" (ISD) models, and explains how they differ from standard models.

0
28 Nov 2018
##### Improved Speech Enhancement with the Wave-U-Net
We study the use of the Wave-U-Net architecture for speech enhancement, a model introduced by Stoller et al for the separation of music vocals and accompaniment. This end-to-end learning method for audio source separation operates directly in the time domain, permitting the integrated modelling of phase information and being able to take large temporal contexts into account.

1
27 Nov 2018
##### Patch-based Progressive 3D Point Set Upsampling
We present a detail-driven deep neural network for point set upsampling. A high-resolution point set is essential for point-based rendering and surface reconstruction.

9
27 Nov 2018