1
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.
2
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.
3
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.
4
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.
5
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.
7
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.
8
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.
9
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.
10
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}).
11
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.
12
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.
13
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.
14
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.
15
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.
17
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.
18
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.
19
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.
20
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.
21
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).
22
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.
23
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.
24
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.
25
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.
26
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.
27
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.
28
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.
29
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.
30
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.
31
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.
32
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.
33
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.
34
![Card image cap](https://raw.githubusercontent.com/M-Elfeki/GDPP/master/Figures/Fig_1.png"/>
)
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.
35
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.
36
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.
37
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.
38
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.
40
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.
41
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.
42
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.
43
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.
44
LoAdaBoost:Loss-Based AdaBoost Federated Machine Learning on medical Data
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.
45
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.
46
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.
47
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.
48
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.
49
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.
50
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.
51
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.
52
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.
53
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.
54
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.
56
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.
57
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.
58
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.
59
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.
60
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.
61
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.
62
Partial Convolution based Padding
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.
63
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.
64
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.
65
Core-fringe link prediction
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.
66
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.
67
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.
68
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.
69
Metropolis-Hastings Generative Adversarial Networks
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.
70
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.
71
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.
73
ShelfNet for Real-time Semantic Segmentation
In this project, we present ShelfNet, a lightweight convolutional neural network for accurate real-time semantic segmentation. ShelfNet achieved high accuracy: on PASCAL VOC 2012 test set, it achieved 84.2% mIoU with ResNet101 backbone and 82.8% mIoU with ResNet50 backbone; it achieved 75.8% mIoU with ResNet50 backbone on Cityscapes dataset.
74
Scan2CAD: Learning CAD Model Alignment in RGB-D Scans
For a 3D reconstruction of an indoor scene, our method takes as input a set of CAD models, and predicts a 9DoF pose that aligns each model to the underlying scan geometry. To this end, we design a novel 3D CNN architecture that learns a joint embedding between real and synthetic objects, and from this predicts a correspondence heatmap.
75
Deformable ConvNets v2: More Deformable, Better Results
The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive behavior, we observe that while the spatial support for its neural features conforms more closely than regular ConvNets to object structure, this support may nevertheless extend well beyond the region of interest, causing features to be influenced by irrelevant image content.
76
FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery
We propose FineGAN, a novel unsupervised GAN framework, which disentangles the background, object shape, and object appearance to hierarchically generate images of fine-grained object categories. To disentangle the factors without any supervision, our key idea is to use information theory to associate each factor to a latent code, and to condition the relationships between the codes in a specific way to induce the desired hierarchy.
77
Neural Non-Stationary Spectral Kernel
Standard kernels such as Mat\'ern or RBF kernels only encode simple monotonic dependencies within the input space. Spectral mixture kernels have been proposed as general-purpose, flexible kernels for learning and discovering more complicated patterns in the data.
78
Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing
Diffusion is commonly used as a ranking or re-ranking method in retrieval tasks to achieve higher retrieval performance, and has attracted lots of attention in recent years. A downside to diffusion is that it performs slowly in comparison to the naive k-NN search, which causes a non-trivial online computational cost on large datasets.
79
DSBI: Double-Sided Braille Image Dataset and Algorithm Evaluation for Braille Dots Detection
Braille dots detection is the core and basic step for Braille image recognition. This paper also evaluates some Braille dots detection methods on our dataset DSBI and gives the benchmark performance of recto dots detection.
80
Affinity Derivation and Graph Merge for Instance Segmentation
We present an instance segmentation scheme based on pixel affinity information, which is the relationship of two pixels belonging to a same instance. In our scheme, we use two neural networks with similar structure.
81
A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks
Depending on how much information an adversary can access to, adversarial attacks can be classified as white-box attack and black-box attack. In both cases, optimization-based attack algorithms can achieve relatively low distortions and high attack success rates.
82
Node Embedding with Adaptive Similarities for Scalable Learning over Graphs
In the present work, we propose an adaptive node embedding framework that adjusts the embedding process to a given underlying graph, in a fully unsupervised manner. Moreover, an algorithmic scheme is proposed for training the model parameters effieciently and in an unsupervised manner.
83
Flexible Attributed Network Embedding
Network embedding aims to find a way to encode network by learning an embedding vector for each node in the network. In this paper, we propose a novel framework, FANE, to integrate structure and property information in the network embedding process.
85
Stepping Stones to Inductive Synthesis of Low-Level Looping Programs
We present MAKESPEARE, a simple delayed-acceptance hillclimbing method that synthesizes low-level looping programs from input/output examples. MAKESPEARE has also synthesized a record-setting program on one of the puzzles from the TIS-100 assembly language programming game.
86
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
We first identify a group of interpretable units that are closely related to object concepts with a segmentation-based network dissection method. Then, we quantify the causal effect of interpretable units by measuring the ability of interventions to control objects in the output.
87
Combining neural and knowledge-based approaches to Named Entity Recognition in Polish
Named entity recognition (NER) is one of the tasks in natural language processing that can greatly benefit from the use of external knowledge sources. We propose a named entity recognition framework composed of knowledge-based feature extractors and a deep learning model including contextual word embeddings, long short-term memory (LSTM) layers and conditional random fields (CRF) inference layer.
88
Matchable Image Retrieval by Learning from Surface Reconstruction
Convolutional Neural Networks (CNNs) have achieved superior performance on object image retrieval, while Bag-of-Words (BoW) models with handcrafted local features still dominate the retrieval of overlapping images in 3D reconstruction. In this paper, we narrow down this gap by presenting an efficient CNN-based method to retrieve images with overlaps, which we refer to as the matchable image retrieval problem.
89
A Rule-based Kurdish Text Transliteration System
In this article, we present a rule-based approach for transliterating two mostly used orthographies in Sorani Kurdish. Our work consists of detecting a character in a word by removing the possible ambiguities and mapping it into the target orthography.
90
Bringing a Blurry Frame Alive at High Frame-Rate with an Event Camera
A blurry image can be regarded as the integral of a sequence of latent images, while the events indicate the changes between the latent images. In this paper, we propose a simple and effective approach, the \textbf{Event-based Double Integral (EDI)} model, to reconstruct a high frame-rate, sharp video from a single blurry frame and its event data.
91
Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series
These series of images are a key component of any classification framework to obtain up-to-date and accurate land cover maps of the Earth's soils. For the first time, this paper explores the use of Convolutional Neural Networks (CNNs) with convolutions applied in the temporal dimension for SITS classification.
92
Collaging on Internal Representations: An Intuitive Approach for Semantic Transfiguration
We present a novel CNN-based image editing method that allows the user to change the semantic information of an image over a user-specified region. Our method makes this possible by combining the idea of manifold projection with spatial conditional batch normalization (sCBN), a version of conditional batch normalization with user-specifiable spatial weight maps.
93
Evoplex: A platform for agent-based modeling on networks
Evoplex is a fast, robust and extensible platform for developing agent-based models and multi-agent systems on networks. Each agent is represented as a node and interacts with its neighbors, as defined by the network structure.
94
An overview of deep learning in medical imaging focusing on MRI
Deep neural networks are now the state-of-the-art machine learning models across a variety of areas, from image analysis to natural language processing, and widely deployed in academia and industry. Our aim is threefold: (i) give a brief introduction to deep learning with pointers to core references; (ii) indicate how deep learning has been applied to the entire MRI processing chain, from acquisition to image retrieval, from segmentation to disease prediction; (iii) provide a starting point for people interested in experimenting and perhaps contributing to the field of machine learning for medical imaging by pointing out good educational resources, state-of-the-art open-source code, and interesting sources of data and problems related medical imaging.
95
Sequential Variational Autoencoders for Collaborative Filtering
Variational autoencoders were proven successful in domains such as computer vision and speech processing. We introduce a recurrent version of the VAE, where instead of passing a subset of the whole history regardless of temporal dependencies, we rather pass the consumption sequence subset through a recurrent neural network.
96
PCGAN: Partition-Controlled Human Image Generation
Human image generation is a very challenging task since it is affected by many factors. Many human image generation methods focus on generating human images conditioned on a given pose, while the generated backgrounds are often blurred.In this paper,we propose a novel Partition-Controlled GAN to generate human images according to target pose and background.
97
Streamlining Variational Inference for Constraint Satisfaction Problems
Several algorithms for solving constraint satisfaction problems are based on survey propagation, a variational inference scheme used to obtain approximate marginal probability estimates for variable assignments. These marginals correspond to how frequently each variable is set to true among satisfying assignments, and are used to inform branching decisions during search; however, marginal estimates obtained via survey propagation are approximate and can be self-contradictory.
98
A New Cervical Cytology Dataset for Nucleus Detection and Image Classification (Cervix93) and Methods for Cervical Nucleus Detection
We also present two methods: a baseline method based on a previously proposed approach, and a deep learning method, and compare their results with other state-of-the-art methods. Both the baseline method and the deep learning method outperform other state-of-the-art methods by significant margins.
99
Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses
Research on adversarial examples in computer vision tasks has shown that small, often imperceptible changes to an image can induce misclassification, which has security implications for a wide range of image processing systems. Considering $L_2$ norm distortions, the Carlini and Wagner attack is presently the most effective white-box attack in the literature.
100