1
Distributionally Adversarial Attack
Recent work on adversarial attack has shown that Projected Gradient Descent (PGD) Adversary is a universal first-order adversary, and the classifier adversarially trained by PGD is robust against a wide range of first-order attacks. However, it is worth noting that the objective of an attacking/defense model relies on a data distribution, typically in the form of risk maximization/minimization: $\max\!/\!\min \mathbb{E}_{p(\mathbf{x})} \mathcal{L}(\mathbf{x})$, with $p(\mathbf{x})$ the data distribution and $\mathcal{L}(\cdot)$ a loss function.
2
Multiple Character Embeddings for Chinese Word Segmentation
Chinese word segmentation (CWS) is often regarded as a character-based sequence labeling task in most current works which have achieved great performance by leveraging powerful neural networks. However, these works neglect an important clue: Chinese characters contain both semantic and phonetic meanings.
3
GestureGAN for Hand Gesture-to-Gesture Translation in the Wild
Therefore, this task requires a high-level understanding of the mapping between the input source gesture and the output target gesture. Meanwhile, the generated images are in high-quality and are photo-realistic, allowing them to be used as data augmentation to improve the performance of a hand gesture classifier.
5
Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models
We introduce a method which enables a recurrent dynamics model to be temporally abstract. Our approach, which we call Adaptive Skip Intervals (ASI), is based on the observation that in many sequential prediction tasks, the exact time at which events occur is irrelevant to the underlying objective.
6
Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models
We introduce a method which enables a recurrent dynamics model to be temporally abstract. Our approach, which we call Adaptive Skip Intervals (ASI), is based on the observation that in many sequential prediction tasks, the exact time at which events occur is irrelevant to the underlying objective.
7
An Overview and a Benchmark of Active Learning for One-Class Classification
This article starts with a categorization of the various methods. One result is that the practicality and the performance of an active learning method strongly depend on its category and on the assumptions behind it.
8
An Overview and a Benchmark of Active Learning for One-Class Classification
This article starts with a categorization of the various methods. One result is that the practicality and the performance of an active learning method strongly depend on its category and on the assumptions behind it.
9
An Overview and a Benchmark of Active Learning for One-Class Classification
This article starts with a categorization of the various methods. One result is that the practicality and the performance of an active learning method strongly depend on its category and on the assumptions behind it.
10
Improving Generalization via Scalable Neighborhood Component Analysis
Current major approaches to visual recognition follow an end-to-end formulation that classifies an input image into one of the pre-determined set of semantic categories. Parametric softmax classifiers are a common choice for such a closed world with fixed categories, especially when big labeled data is available during training.
11
Improving Generalization via Scalable Neighborhood Component Analysis
Current major approaches to visual recognition follow an end-to-end formulation that classifies an input image into one of the pre-determined set of semantic categories. Parametric softmax classifiers are a common choice for such a closed world with fixed categories, especially when big labeled data is available during training.
12
SciSports: Learning football kinematics through two-dimensional tracking data
We also trained a Discriminator network to distinguish between two players based on their trajectories; after training, the network managed to distinguish between some pairs of players, but not between others. After training, the Variational Autoencoders generated trajectories that are difficult to distinguish, visually, from the data.
13
Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding
In this work, we investigate simultaneously predicting categories of different levels in the hierarchy and integrating this structured correlation information into the deep neural network by developing a novel Hierarchical Semantic Embedding (HSE) framework. At each level, it incorporates the predicted score vector of the higher level as prior knowledge to learn finer-grained feature representation.
14
Deep Randomized Ensembles for Metric Learning
Learning embedding functions, which map semantically related inputs to nearby locations in a feature space supports a variety of classification and information retrieval tasks. In this work, we propose a novel, generalizable and fast method to define a family of embedding functions that can be used as an ensemble to give improved results.
15
Improving Shape Deformation in Unsupervised Image-to-Image Translation
Unsupervised image-to-image translation techniques are able to map local texture between two domains, but they are typically unsuccessful when the domains require larger shape change. Inspired by semantic segmentation, we introduce a discriminator with dilated convolutions that is able to use information from across the entire image to train a more context-aware generator.
17
iNNvestigate neural networks!
In recent years, deep neural networks have revolutionized many application domains of machine learning and are key components of many critical decision or predictive processes. The presented library iNNvestigate addresses this by providing a common interface and out-of-the- box implementation for many analysis methods, including the reference implementation for PatternNet and PatternAttribution as well as for LRP-methods.
18
Fast Video Shot Transition Localization with Deep Structured Models
Previous studies are restricted on detecting sudden content changes between frames through similarity measurement and multi-scale operations are widely utilized to deal with transitions of various lengths. In order to train a high-performance shot transition detector, we contribute a new database ClipShots, which contains 128636 cut transitions and 38120 gradual transitions from 4039 online videos.
19
Rapid Adaptation of Neural Machine Translation to New Languages
This paper examines the problem of adapting neural machine translation systems to new, low-resourced languages (LRLs) as effectively and rapidly as possible. We propose methods based on starting with massively multilingual "seed models", which can be trained ahead-of-time, and then continuing training on data related to the LRL.
21
Interpretable Time Series Classification using All-Subsequence Learning and Symbolic Representations in Time and Frequency Domains
The time series classification literature has expanded rapidly over the last decade, with many new classification approaches published each year. In this work we analyse the state-of-the-art for time series classification, and propose new algorithms that aim to maintain the classifier accuracy and efficiency, but keep interpretability as a key design constraint.
22
Multimodal Differential Network for Visual Question Generation
Generating natural questions from an image is a semantic task that requires using visual and language modality to learn multimodal representations. We obtain this by using a Multimodal Differential Network to produce natural and engaging questions.
23
Reconfigurable Inverted Index
Existing approximate nearest neighbor search systems suffer from two fundamental problems that are of practical importance but have not received sufficient attention from the research community. Owing to the linear layout, the data structure can be dynamically adjusted after new items are added, maintaining the fast speed of the system.
24
A Fourier View of REINFORCE
We show a connection between the Fourier spectrum of Boolean functions and the REINFORCE gradient estimator for binary latent variable models. Using this connection we offer a new perspective on variance reduction in gradient estimation for latent variable models: namely, that variance reduction involves eliminating or reducing Fourier coefficients that do not have degree 1.
26
Matrix Factorization on GPUs with Memory Optimization and Approximate Computing
Matrix factorization (MF) discovers latent features from observations, which has shown great promises in the fields of collaborative filtering, data compression, feature extraction, word embedding, etc. Current MF implementations are either optimized for a single machine or with a need of a large computer cluster but still are insufficient.
28
A Full End-to-End Semantic Role Labeler, Syntax-agnostic Over Syntax-aware?
Semantic role labeling (SRL) is to recognize the predicate-argument structure of a sentence, including subtasks of predicate disambiguation and argument labeling. Using a biaffine scorer, our model directly predicts all semantic role labels for all given word pairs in the sentence without relying on any syntactic parse information.
29
Neural Network Encapsulation
To resolve this limitation, we approximate the routing process with two branches: a master branch which collects primary information from its direct contact in the lower layer and an aide branch that replenishes master based on pattern variants encoded in other lower capsules. Motivated by the routing to make higher capsule have agreement with lower capsule, we extend the mechanism as a compensation for the rapid loss of information in nearby layers.
30
Learning Multi-touch Conversion Attribution with Dual-attention Mechanisms for Online Advertising
In online advertising, the Internet users may be exposed to a sequence of different ad campaigns, i.e., display ads, search, or referrals from multiple channels, before led up to any final sales conversion and transaction. To achieve this, we utilize sequence-to-sequence prediction for user clicks, and combine both post-view and post-click attribution patterns together for the final conversion estimation.
31
From POS tagging to dependency parsing for biomedical event extraction
Given the importance of relation or event extraction from biomedical research publications to support knowledge capture and synthesis, and the strong dependency of approaches to this information extraction task on syntactic information, it is valuable to understand which approaches to syntactic processing of biomedical text have the highest performance. In this paper, we perform an empirical study comparing state-of-the-art traditional feature-based and neural network-based models for two core NLP tasks of POS tagging and dependency parsing on two benchmark biomedical corpora, GENIA and CRAFT.
32
LemmaTag: Jointly Tagging and Lemmatizing for Morphologically-Rich Languages with BRNNs
We present LemmaTag, a featureless recurrent neural network architecture that jointly generates part-of-speech tags and lemmatizes sentences of languages with complex morphology, using bidirectional RNNs with character-level and word-level embeddings. We demonstrate that both tasks benefit from sharing the encoding part of the network and from using the tagger output as an input to the lemmatizer.
33
Partial Adversarial Domain Adaptation
Domain adversarial learning aligns the feature distributions across the source and target domains in a two-player minimax game. We present Partial Adversarial Domain Adaptation (PADA), which simultaneously alleviates negative transfer by down-weighing the data of outlier source classes for training both source classifier and domain adversary, and promotes positive transfer by matching the feature distributions in the shared label space.
34
Disease Progression Timeline Estimation for Alzheimer's Disease using Discriminative Event Based Modeling
In this work we propose a novel discriminative approach to EBM, which is shown to be more accurate than existing state-of-the-art EBM methods. We evaluated the proposed method on Alzheimer's Disease Neuroimaging Initiative (ADNI) data and compared the results with existing state-of-the-art EBM methods.
35
Exploiting Structure for Fast Kernel Learning
We propose two methods for exact Gaussian process (GP) inference and learning on massive image, video, spatial-temporal, or multi-output datasets with missing values (or "gaps") in the observed responses. The first method ignores the gaps using sparse selection matrices and a highly effective low-rank preconditioner is introduced to accelerate computations.
36
Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer's Disease
In this study, we train a 3D CNN to detect Alzheimer's disease based on structural MRI scans of the brain. In summary, we show that applying different visualization methods is important to understand the decisions of a CNN, a step that is crucial to increase clinical impact and trust in computer-based decision support systems.
37
Random directions stochastic approximation with deterministic perturbations
We introduce deterministic perturbation schemes for the recently proposed random directions stochastic approximation (RDSA) [17], and propose new first-order and second-order algorithms. In the latter case, these are the first second-order algorithms to incorporate deterministic perturbations.
38
On the Solvability of Viewing Graphs
A set of fundamental matrices relating pairs of cameras in some configuration can be represented as edges of a "viewing graph". Whether or not these fundamental matrices are generically sufficient to recover the global camera configuration depends on the structure of this graph.
39
Design Challenges in Named Entity Transliteration
We analyze some of the fundamental design challenges that impact the development of a multilingual state-of-the-art named entity transliteration system, including curating bilingual named entity datasets and evaluation of multiple transliteration methods. We empirically evaluate the transliteration task using traditional weighted finite state transducer (WFST) approach against two neural approaches: the encoder-decoder recurrent neural network method and the recent, non-sequential Transformer method.
40
SketchyScene: Richly-Annotated Scene Sketches
We contribute the first large-scale dataset of scene sketches, SketchyScene, with the goal of advancing research on sketch understanding at both the object and scene level. The dataset is created through a novel and carefully designed crowdsourcing pipeline, enabling users to efficiently generate large quantities of realistic and diverse scene sketches.
41
Data augmentation using synthetic data for time series classification with deep residual networks
Data augmentation in deep neural networks is the process of generating artificial data in order to reduce the variance of the classifier with the goal to reduce the number of errors. This is surprising as the accuracy of deep learning models for TSC could potentially be improved, especially for small datasets that exhibit overfitting, when a data augmentation method is adopted.
42
ODSQA: Open-domain Spoken Question Answering Dataset
Reading comprehension by machine has been widely studied, but machine comprehension of spoken content is still a less investigated problem. In this paper, we release Open-Domain Spoken Question Answering Dataset (ODSQA) with more than three thousand questions.
43
Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image
We propose a computational framework to jointly parse a single RGB image and reconstruct a holistic 3D configuration composed by a set of CAD models using a stochastic grammar model. Specifically, we introduce a Holistic Scene Grammar (HSG) to represent the 3D scene structure, which characterizes a joint distribution over the functional and geometric space of indoor scenes.
44
Quantized Densely Connected U-Nets for Efficient Landmark Localization
In this paper, we propose quantized densely connected U-Nets for efficient visual landmark localization. Finally, to reduce the memory consumption and high precision operations both in training and testing, we further quantize weights, inputs, and gradients of our localization network to low bit-width numbers.
45
Adversarial Vision Challenge
The NIPS 2018 Adversarial Vision Challenge is a competition to facilitate measurable progress towards robust machine vision models and more generally applicable adversarial attacks. This document is an updated version of our competition proposal that was accepted in the competition track of 32nd Conference on Neural Information Processing Systems (NIPS 2018).
46
Visual Question Generation for Class Acquisition of Unknown Objects
Traditional image recognition methods only consider objects belonging to already learned classes. In this paper, we propose a method for generating questions about unknown objects in an image, as means to get information about classes that have not been learned.
47
Skin Lesion Diagnosis using Ensembles, Unscaled Multi-Crop Evaluation and Loss Weighting
In this paper we present the methods of our submission to the ISIC 2018 challenge for skin lesion diagnosis (Task 3). We identify heavy class imbalance as a key problem for this challenge and consider multiple balancing approaches such as loss weighting and balanced batch sampling.
48
Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
The prediction accuracy has been the long-lasting and sole standard for comparing the performance of different image classification models, including the ImageNet competition. However, recent studies have highlighted the lack of robustness in well-trained deep neural networks to adversarial examples.
49
Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
The prediction accuracy has been the long-lasting and sole standard for comparing the performance of different image classification models, including the ImageNet competition. However, recent studies have highlighted the lack of robustness in well-trained deep neural networks to adversarial examples.
50
Learning monocular depth estimation with unsupervised trinocular assumptions
Obtaining accurate depth measurements out of a single image represents a fascinating solution to 3D sensing. CNNs led to considerable improvements in this field, and recent trends replaced the need for ground-truth labels with geometry-guided image reconstruction signals enabling unsupervised training.
51
Video Re-localization
We first exploit and reorganize the videos in ActivityNet to form a new dataset for video re-localization research, which consists of about 10,000 videos of diverse visual appearances associated with localized boundary information. Subsequently, we propose an innovative cross gated bilinear matching model such that every time-step in the reference video is matched against the attentively weighted query video.
52
Stock Price Correlation Coefficient Prediction with ARIMA-LSTM Hybrid Model
Predicting the price correlation of two assets for future time periods is important in portfolio optimization. To encompass both linearity and nonlinearity in the model, we adopt the ARIMA model as well.
53
Deep Multi-Center Learning for Face Alignment
Most of the existing deep learning methods only use one fully-connected layer called shape prediction layer to estimate the location of facial landmarks. Challenging landmarks are focused firstly, and each cluster of landmarks is further optimized respectively.
54
Deep Reinforcement One-Shot Learning for Artificially Intelligent Classification Systems
The basic idea of the DeROL algorithm is to train a deep-Q network to obtain a policy which is oblivious to the unseen classes in the testing data. Second, we develop the first open-source software for practical artificially intelligent one-shot classification systems with limited resources for the benefit of researchers in related fields.
55
MCRM: Mother Compact Recurrent Memory A Biologically Inspired Recurrent Neural Network Architecture
MCRMs are a type of a nested LSTM-GRU architecture where the cell state is the GRU's hidden state. The vein is the output from the fetus which plays the role of the hidden state of the GRU.
56
Learning Multi-scale Features for Foreground Segmentation
Foreground segmentation algorithms aim segmenting moving objects from the background in a robust way under various challenging scenarios. Encoder-decoder type deep neural networks that are used in this domain recently perform impressive segmentation results.
57
T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks
Current methods for single-image depth estimation use training datasets with real image-depth pairs or stereo pairs, which are not easy to acquire. We propose a framework, trained on synthetic image-depth pairs and unpaired real images, that comprises an image translation network for enhancing realism of input images, followed by a depth prediction network.
58
Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation
We present the first exploration of multiple uncertainty estimates based on Monte Carlo (MC) dropout [4] in the context of deep networks for lesion detection and segmentation in medical images. We analyze the performance of voxel-based segmentation and lesion-level detection by choosing operating points based on the uncertainty.
60
iSPA-Net: Iterative Semantic Pose Alignment Network
Our approach focuses on exploiting semantic 3D structural regularity to solve the task of fine-grained pose estimation by predicting viewpoint difference between a given pair of images. Such image comparison based approach also alleviates the problem of data scarcity and hence enhances scalability of the proposed approach for novel object categories with minimal annotation.
61
Real-Time Object Pose Estimation with Pose Interpreter Networks
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.
62
CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled rawly from the Internet by using text queries, without any human annotation. We develop a principled learning strategy by leveraging curriculum learning, with the goal of handling massive amount of noisy labels and data imbalance effectively.
63
Diverse Image-to-Image Translation via Disentangled Representations
In this work, we present an approach based on disentangled representation for producing diverse outputs without paired training images. Our model takes the encoded content features extracted from a given input and the attribute vectors sampled from the attribute space to produce diverse outputs at test time.
64
Weakly Supervised Localisation for Fetal Ultrasound Images
This paper addresses the task of detecting and localising fetal anatomical regions in 2D ultrasound images, where only image-level labels are present at training, i.e. without any localisation or segmentation information. We examine the use of convolutional neural network architectures coupled with soft proposal layers.
65
Weakly Supervised Localisation for Fetal Ultrasound Images
This paper addresses the task of detecting and localising fetal anatomical regions in 2D ultrasound images, where only image-level labels are present at training, i.e. without any localisation or segmentation information. We examine the use of convolutional neural network architectures coupled with soft proposal layers.
66
Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction
However, GRU based approaches are unable to consistently estimate 3D shapes given the same set of input images as the recurrent unit is permutation variant. In this paper, we present a new feed-forward neural module, named AttSets, together with a dedicated training algorithm, named JTSO, to attentionally aggregate an arbitrary sized deep feature set for multi-view 3D reconstruction.
67
PCN: Point Completion Network
Shape completion, the problem of estimating the complete geometry of objects from partial observations, lies at the core of many vision and robotics applications. In this work, we propose Point Completion Network (PCN), a novel learning-based approach for shape completion.
68
Open Category Detection with PAC Guarantees
Open category detection is the problem of detecting "alien" test instances that belong to categories or classes that were not present in the training data. Further, while there are algorithms for open category detection, there are few empirical results that directly report alien detection rates.
69
Neural Arithmetic Logic Units
Neural networks can learn to represent and manipulate numerical information, but they seldom generalize well outside of the range of numerical values encountered during training. To encourage more systematic numerical extrapolation, we propose an architecture that represents numerical quantities as linear activations which are manipulated using primitive arithmetic operators, controlled by learned gates.
70
Neural Arithmetic Logic Units
Neural networks can learn to represent and manipulate numerical information, but they seldom generalize well outside of the range of numerical values encountered during training. To encourage more systematic numerical extrapolation, we propose an architecture that represents numerical quantities as linear activations which are manipulated using primitive arithmetic operators, controlled by learned gates.
71
Neural Arithmetic Logic Units
Neural networks can learn to represent and manipulate numerical information, but they seldom generalize well outside of the range of numerical values encountered during training. To encourage more systematic numerical extrapolation, we propose an architecture that represents numerical quantities as linear activations which are manipulated using primitive arithmetic operators, controlled by learned gates.
72
Neural Arithmetic Logic Units
Neural networks can learn to represent and manipulate numerical information, but they seldom generalize well outside of the range of numerical values encountered during training. To encourage more systematic numerical extrapolation, we propose an architecture that represents numerical quantities as linear activations which are manipulated using primitive arithmetic operators, controlled by learned gates.
73
Neural Arithmetic Logic Units
Neural networks can learn to represent and manipulate numerical information, but they seldom generalize well outside of the range of numerical values encountered during training. To encourage more systematic numerical extrapolation, we propose an architecture that represents numerical quantities as linear activations which are manipulated using primitive arithmetic operators, controlled by learned gates.
74
Neural Arithmetic Logic Units
Neural networks can learn to represent and manipulate numerical information, but they seldom generalize well outside of the range of numerical values encountered during training. To encourage more systematic numerical extrapolation, we propose an architecture that represents numerical quantities as linear activations which are manipulated using primitive arithmetic operators, controlled by learned gates.
75
Neural Arithmetic Logic Units
Neural networks can learn to represent and manipulate numerical information, but they seldom generalize well outside of the range of numerical values encountered during training. To encourage more systematic numerical extrapolation, we propose an architecture that represents numerical quantities as linear activations which are manipulated using primitive arithmetic operators, controlled by learned gates.
76
Model-order selection in statistical shape models
It requires choosing a model order, which determines how much of the variation seen in the training data is accounted for by the PDM. A good choice of the model order depends on the number of training samples and the noise level in the training data set.
77
A Deep Neural Model Of Emotion Appraisal
In this paper, we propose a deep neural model which is designed in the light of different aspects of developmental learning of emotional concepts to provide an integrated solution for internal and external emotion appraisal. We evaluate the performance of the proposed model with different challenging corpora and compare it with state-of-the-art models for external emotion appraisal.
78
Instance-level Human Parsing via Part Grouping Network
Instance-level human parsing towards real-world human analysis scenarios is still under-explored due to the absence of sufficient data resources and technical difficulty in parsing multiple instances in a single pass. Several related works all follow the "parsing-by-detection" pipeline that heavily relies on separately trained detection models to localize instances and then performs human parsing for each instance sequentially.
79
Multi-modal Cycle-consistent Generalized Zero-Shot Learning
In generalized zero shot learning (GZSL), the set of classes are split into seen and unseen classes, where training relies on the semantic features of the seen and unseen classes and the visual representations of only the seen classes, while testing uses the visual representations of the seen and unseen classes. This constraint can result in synthetic visual representations that do not represent well their semantic features.
80
The Unreasonable Effectiveness of Texture Transfer for Single Image Super-resolution
While implicit generative models such as GANs have shown impressive results in high quality image reconstruction and manipulation using a combination of various losses, we consider a simpler approach leading to surprisingly strong results. Moreover, we show that a texture representation of those deep features better capture the perceptual quality of an image than the original deep features.
81
Online Adaptative Curriculum Learning for GANs
Generative Adversarial Networks (GANs) can successfully learn a probability distribution and produce realistic samples. In this paper, we build on existing work in the area by proposing a novel framework for training the generator against an ensemble of discriminator networks, which can be seen as a one-student/multiple-teachers setting.
82
Online Adaptative Curriculum Learning for GANs
Generative Adversarial Networks (GANs) can successfully learn a probability distribution and produce realistic samples. In this paper, we build on existing work in the area by proposing a novel framework for training the generator against an ensemble of discriminator networks, which can be seen as a one-student/multiple-teachers setting.
83
Online Adaptative Curriculum Learning for GANs
Generative Adversarial Networks (GANs) can successfully learn a probability distribution and produce realistic samples. In this paper, we build on existing work in the area by proposing a novel framework for training the generator against an ensemble of discriminator networks, which can be seen as a one-student/multiple-teachers setting.
84
Egocentric Spatial Memory
Egocentric spatial memory (ESM) defines a memory system with encoding, storing, recognizing and recalling the spatial information about the environment from an egocentric perspective. We introduce an integrated deep neural network architecture for modeling ESM.
85
Deep End-to-end Fingerprint Denoising and Inpainting
This work describes our winning solution for the Chalearn LAP In-painting Competition Track 3 - Fingerprint Denoising and In-painting. The objective of this competition is to reduce noise, remove the background pattern and replace missing parts of fingerprint images in order to simplify the verification made by humans or third-party software.
86
t-SNE-CUDA: GPU-Accelerated t-SNE and its Applications to Modern Data
Modern datasets and models are notoriously difficult to explore and analyze due to their inherent high dimensionality and massive numbers of samples. t-SNE-CUDA significantly outperforms current implementations with 50-700x speedups on the CIFAR-10 and MNIST datasets.
87
Attention is All We Need: Nailing Down Object-centric Attention for Egocentric Activity Recognition
In this paper we propose an end-to-end trainable deep neural network model for egocentric activity recognition. Our model is built on the observation that egocentric activities are highly characterized by the objects and their locations in the video.
89
The Devil of Face Recognition is in the Noise
2) With the original datasets and cleaned subsets, we profile and analyze label noise properties of MegaFace and MS-Celeb-1M. 3) We study the association between different types of noise, i.e., label flips and outliers, with the accuracy of face recognition models.
91
Acquisition of Localization Confidence for Accurate Object Detection
Modern CNN-based object detectors rely on bounding box regression and non-maximum suppression to localize objects. The network acquires this confidence of localization, which improves the NMS procedure by preserving accurately localized bounding boxes.
92
Textual Explanations for Self-Driving Vehicles
We propose a new approach to introspective explanations which consists of two parts. Finally, we explore a version of our model that generates rationalizations, and compare with introspective explanations on the same video segments.
93
Unsupervised Domain Adaptive Re-Identification: Theory and Practice
We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation. We first extend existing unsupervised domain adaptive classification theories to re-ID tasks.
94
Graphene: Semantically-Linked Propositions in Open Information Extraction
We present an Open Information Extraction (IE) approach that uses a two-layered transformation stage consisting of a clausal disembedding layer and a phrasal disembedding layer, together with rhetorical relation identification. In that way, we convert sentences that present a complex linguistic structure into simplified, syntactically sound sentences, from which we can extract propositions that are represented in a two-layered hierarchy in the form of core relational tuples and accompanying contextual information which are semantically linked via rhetorical relations.
95
Semantic Labeling in Very High Resolution Images via a Self-Cascaded Convolutional Neural Network
Semantic labeling for very high resolution (VHR) images in urban areas, is of significant importance in a wide range of remote sensing applications. Specifically, for confusing manmade objects, ScasNet improves the labeling coherence with sequential global-to-local contexts aggregation.
96
Improving Electron Micrograph Signal-to-Noise with an Atrous Convolutional Encoder-Decoder
Our neural network was trained end-to-end to remove Poisson noise applied to low-dose ($\ll$ 300 counts ppx) micrographs created from a new dataset of 17267 2048$\times$2048 high-dose ($>$ 2500 counts ppx) micrographs and then fine-tuned for ordinary doses (200-2500 counts ppx). Our network outperforms their best mean squared error and structural similarity index performances by 24.6% and 9.6% for low doses and by 43.7% and 5.5% for ordinary doses.
97
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Currently, the neural network architecture design is mostly guided by the \emph{indirect} metric of computation complexity, i.e., FLOPs. However, the \emph{direct} metric, e.g., speed, also depends on the other factors such as memory access cost and platform characterics.
98
ARM: Augment-REINFORCE-Merge Gradient for Discrete Latent Variable Models
To backpropagate the gradients through discrete stochastic layers, we encode the true gradients into a multiplication between random noises and the difference of the same function of two different sets of discrete latent variables, which are correlated with these random noises. The expectations of that multiplication over iterations are zeros combined with spikes from time to time.
99
ADAM-ADMM: A Unified, Systematic Framework of Structured Weight Pruning for DNNs
Weight pruning methods of deep neural networks (DNNs) have been demonstrated to achieve a good model pruning ratio without loss of accuracy, thereby alleviating the significant computation/storage requirements of large-scale DNNs. In this work, we overcome pruning ratio and GPU acceleration limitations by proposing a unified, systematic framework of structured weight pruning for DNNs, named ADAM-ADMM (Adaptive Moment Estimation-Alternating Direction Method of Multipliers).
100
