October 21, 2019

3147 words 15 mins read

Paper Group AWR 133

Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification. The Geometry of Culture: Analyzing Meaning through Word Embeddings. Video-based Person Re-identification Using Spatial-Temporal Attention Networks. A Tree-based Decoder for Neural Machine Translation. Constituent Parsing as Sequence Labeling. Taking A …

Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification


Title	Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification
Authors	Qi Lei, Lingfei Wu, Pin-Yu Chen, Alexandros G. Dimakis, Inderjit S. Dhillon, Michael Witbrock
Abstract	Adversarial examples are carefully constructed modifications to an input that completely change the output of a classifier but are imperceptible to humans. Despite these successful attacks for continuous data (such as image and audio samples), generating adversarial examples for discrete structures such as text has proven significantly more challenging. In this paper we formulate the attacks with discrete input on a set function as an optimization task. We prove that this set function is submodular for some popular neural network text classifiers under simplifying assumption. This finding guarantees a $1-1/e$ approximation factor for attacks that use the greedy algorithm. Meanwhile, we show how to use the gradient of the attacked classifier to guide the greedy search. Empirical studies with our proposed optimization scheme show significantly improved attack ability and efficiency, on three different text classification tasks over various baselines. We also use a joint sentence and word paraphrasing technique to maintain the original semantics and syntax of the text. This is validated by a human subject evaluation in subjective metrics on the quality and semantic coherence of our generated adversarial text.
Tasks	Adversarial Text, Text Classification
Published	2018-12-01
URL	http://arxiv.org/abs/1812.00151v2
PDF	http://arxiv.org/pdf/1812.00151v2.pdf
PWC	https://paperswithcode.com/paper/discrete-attacks-and-submodular-optimization
Repo	https://github.com/cecilialeiqi/adversarial_text
Framework	pytorch

The Geometry of Culture: Analyzing Meaning through Word Embeddings


Title	The Geometry of Culture: Analyzing Meaning through Word Embeddings
Authors	Austin C. Kozlowski, Matt Taddy, James A. Evans
Abstract	We demonstrate the utility of a new methodological tool, neural-network word embedding models, for large-scale text analysis, revealing how these models produce richer insights into cultural associations and categories than possible with prior methods. Word embeddings represent semantic relations between words as geometric relationships between vectors in a high-dimensional space, operationalizing a relational model of meaning consistent with contemporary theories of identity and culture. We show that dimensions induced by word differences (e.g. man - woman, rich - poor, black - white, liberal - conservative) in these vector spaces closely correspond to dimensions of cultural meaning, and the projection of words onto these dimensions reflects widely shared cultural connotations when compared to surveyed responses and labeled historical data. We pilot a method for testing the stability of these associations, then demonstrate applications of word embeddings for macro-cultural investigation with a longitudinal analysis of the coevolution of gender and class associations in the United States over the 20th century and a comparative analysis of historic distinctions between markers of gender and class in the U.S. and Britain. We argue that the success of these high-dimensional models motivates a move towards “high-dimensional theorizing” of meanings, identities and cultural processes.
Tasks	Word Embeddings
Published	2018-03-25
URL	http://arxiv.org/abs/1803.09288v1
PDF	http://arxiv.org/pdf/1803.09288v1.pdf
PWC	https://paperswithcode.com/paper/the-geometry-of-culture-analyzing-meaning
Repo	https://github.com/UC-MACSS/persp-analysis_A18
Framework	none

Video-based Person Re-identification Using Spatial-Temporal Attention Networks


Title	Video-based Person Re-identification Using Spatial-Temporal Attention Networks
Authors	Shivansh Rao, Tanzila Rahman, Mrigank Rochan, Yang Wang
Abstract	We consider the problem of video-based person re-identification. The goal is to identify a person from videos captured under different cameras. In this paper, we propose an efficient spatial-temporal attention based model for person re-identification from videos. Our method generates an attention score for each frame based on frame-level features. The attention scores of all frames in a video are used to produce a weighted feature vector for the input video. Unlike most existing deep learning methods that use global representation, our approach focuses on attention scores. Extensive experiments on two benchmark datasets demonstrate that our method achieves the state-of-the-art performance. This is a technical report.
Tasks	Person Re-Identification, Video-Based Person Re-Identification
Published	2018-10-26
URL	http://arxiv.org/abs/1810.11261v1
PDF	http://arxiv.org/pdf/1810.11261v1.pdf
PWC	https://paperswithcode.com/paper/video-based-person-re-identification-using
Repo	https://github.com/rshivansh/Spatial-Temporal-attention
Framework	pytorch

A Tree-based Decoder for Neural Machine Translation


Title	A Tree-based Decoder for Neural Machine Translation
Authors	Xinyi Wang, Hieu Pham, Pengcheng Yin, Graham Neubig
Abstract	Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations. Most existing work utilizes some specific types of linguistically-inspired tree structures, like constituency and dependency parse trees. This is often done via a standard RNN decoder that operates on a linearized target tree structure. However, it is an open question of what specific linguistic formalism, if any, is the best structural representation for NMT. In this paper, we (1) propose an NMT model that can naturally generate the topology of an arbitrary tree structure on the target side, and (2) experiment with various target tree structures. Our experiments show the surprising result that our model delivers the best improvements with balanced binary trees constructed without any linguistic knowledge; this model outperforms standard seq2seq models by up to 2.1 BLEU points, and other methods for incorporating target-side syntax by up to 0.7 BLEU.
Tasks	Machine Translation
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09374v1
PDF	http://arxiv.org/pdf/1808.09374v1.pdf
PWC	https://paperswithcode.com/paper/a-tree-based-decoder-for-neural-machine
Repo	https://github.com/cindyxinyiwang/TrDec_pytorch
Framework	pytorch

Constituent Parsing as Sequence Labeling


Title	Constituent Parsing as Sequence Labeling
Authors	Carlos Gómez-Rodríguez, David Vilares
Abstract	We introduce a method to reduce constituent parsing to sequence labeling. For each word w_t, it generates a label that encodes: (1) the number of ancestors in the tree that the words w_t and w_{t+1} have in common, and (2) the nonterminal symbol at the lowest common ancestor. We first prove that the proposed encoding function is injective for any tree without unary branches. In practice, the approach is made extensible to all constituency trees by collapsing unary branches. We then use the PTB and CTB treebanks as testbeds and propose a set of fast baselines. We achieve 90.7% F-score on the PTB test set, outperforming the Vinyals et al. (2015) sequence-to-sequence parser. In addition, sacrificing some accuracy, our approach achieves the fastest constituent parsing speeds reported to date on PTB by a wide margin.
Tasks
Published	2018-10-21
URL	https://arxiv.org/abs/1810.08994v2
PDF	https://arxiv.org/pdf/1810.08994v2.pdf
PWC	https://paperswithcode.com/paper/constituent-parsing-as-sequence-labeling
Repo	https://github.com/aghie/tree2labels
Framework	tf

Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation


Title	Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation
Authors	Yawei Luo, Liang Zheng, Tao Guan, Junqing Yu, Yi Yang
Abstract	We consider the problem of unsupervised domain adaptation in semantic segmentation. The key in this campaign consists in reducing the domain shift, i.e., enforcing the data distributions of the two domains to be similar. A popular strategy is to align the marginal distribution in the feature space through adversarial learning. However, this global alignment strategy does not consider the local category-level feature distribution. A possible consequence of the global movement is that some categories which are originally well aligned between the source and target may be incorrectly mapped. To address this problem, this paper introduces a category-level adversarial network, aiming to enforce local semantic consistency during the trend of global alignment. Our idea is to take a close look at the category-level data distribution and align each class with an adaptive adversarial loss. Specifically, we reduce the weight of the adversarial loss for category-level aligned features while increasing the adversarial force for those poorly aligned. In this process, we decide how well a feature is category-level aligned between source and target by a co-training approach. In two domain adaptation tasks, i.e., GTA5 -> Cityscapes and SYNTHIA -> Cityscapes, we validate that the proposed method matches the state of the art in segmentation accuracy.
Tasks	Domain Adaptation, Semantic Segmentation, Synthetic-to-Real Translation, Unsupervised Domain Adaptation
Published	2018-09-25
URL	http://arxiv.org/abs/1809.09478v3
PDF	http://arxiv.org/pdf/1809.09478v3.pdf
PWC	https://paperswithcode.com/paper/taking-a-closer-look-at-domain-shift-category
Repo	https://github.com/RoyalVane/CLAN
Framework	pytorch

Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception


Title	Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception
Authors	Federico Paredes-Vallés, Kirk Y. W. Scheper, Guido C. H. E. de Croon
Abstract	The combination of spiking neural networks and event-based vision sensors holds the potential of highly efficient and high-bandwidth optical flow estimation. This paper presents the first hierarchical spiking architecture in which motion (direction and speed) selectivity emerges in an unsupervised fashion from the raw stimuli generated with an event-based camera. A novel adaptive neuron model and stable spike-timing-dependent plasticity formulation are at the core of this neural network governing its spike-based processing and learning, respectively. After convergence, the neural architecture exhibits the main properties of biological visual motion systems, namely feature extraction and local and global motion perception. Convolutional layers with input synapses characterized by single and multiple transmission delays are employed for feature and local motion perception, respectively; while global motion selectivity emerges in a final fully-connected layer. The proposed solution is validated using synthetic and real event sequences. Along with this paper, we provide the cuSNN library, a framework that enables GPU-accelerated simulations of large-scale spiking neural networks. Source code and samples are available at https://github.com/tudelft/cuSNN.
Tasks	Event-based vision, Optical Flow Estimation
Published	2018-07-28
URL	http://arxiv.org/abs/1807.10936v2
PDF	http://arxiv.org/pdf/1807.10936v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-learning-of-a-hierarchical
Repo	https://github.com/tudelft/cuSNN
Framework	none

Self-Attention Generative Adversarial Networks


Title	Self-Attention Generative Adversarial Networks
Authors	Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena
Abstract	In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks. Traditional convolutional GANs generate high-resolution details as a function of only spatially local points in lower-resolution feature maps. In SAGAN, details can be generated using cues from all feature locations. Moreover, the discriminator can check that highly detailed features in distant portions of the image are consistent with each other. Furthermore, recent work has shown that generator conditioning affects GAN performance. Leveraging this insight, we apply spectral normalization to the GAN generator and find that this improves training dynamics. The proposed SAGAN achieves the state-of-the-art results, boosting the best published Inception score from 36.8 to 52.52 and reducing Frechet Inception distance from 27.62 to 18.65 on the challenging ImageNet dataset. Visualization of the attention layers shows that the generator leverages neighborhoods that correspond to object shapes rather than local regions of fixed shape.
Tasks	Conditional Image Generation, Image Generation
Published	2018-05-21
URL	https://arxiv.org/abs/1805.08318v2
PDF	https://arxiv.org/pdf/1805.08318v2.pdf
PWC	https://paperswithcode.com/paper/self-attention-generative-adversarial
Repo	https://github.com/recluse27/Colorizator
Framework	tf

Mapping Language to Code in Programmatic Context


Title	Mapping Language to Code in Programmatic Context
Authors	Srinivasan Iyer, Ioannis Konstas, Alvin Cheung, Luke Zettlemoyer
Abstract	Source code is rarely written in isolation. It depends significantly on the programmatic context, such as the class that the code would reside in. To study this phenomenon, we introduce the task of generating class member functions given English documentation and the programmatic context provided by the rest of the class. This task is challenging because the desired code can vary greatly depending on the functionality the class provides (e.g., a sort function may or may not be available when we are asked to “return the smallest element” in a particular member variable list). We introduce CONCODE, a new large dataset with over 100,000 examples consisting of Java classes from online code repositories, and develop a new encoder-decoder architecture that models the interaction between the method documentation and the class environment. We also present a detailed error analysis suggesting that there is significant room for future work on this task.
Tasks
Published	2018-08-29
URL	http://arxiv.org/abs/1808.09588v1
PDF	http://arxiv.org/pdf/1808.09588v1.pdf
PWC	https://paperswithcode.com/paper/mapping-language-to-code-in-programmatic
Repo	https://github.com/sriniiyer/concode
Framework	pytorch

Revisiting the Importance of Encoding Logic Rules in Sentiment Classification


Title	Revisiting the Importance of Encoding Logic Rules in Sentiment Classification
Authors	Kalpesh Krishna, Preethi Jyothi, Mohit Iyyer
Abstract	We analyze the performance of different sentiment classification models on syntactically complex inputs like A-but-B sentences. The first contribution of this analysis addresses reproducible research: to meaningfully compare different models, their accuracies must be averaged over far more random seeds than what has traditionally been reported. With proper averaging in place, we notice that the distillation model described in arXiv:1603.06318v4 [cs.LG], which incorporates explicit logic rules for sentiment classification, is ineffective. In contrast, using contextualized ELMo embeddings (arXiv:1802.05365v2 [cs.CL]) instead of logic rules yields significantly better performance. Additionally, we provide analysis and visualizations that demonstrate ELMo’s ability to implicitly learn logic rules. Finally, a crowdsourced analysis reveals how ELMo outperforms baseline models even on sentences with ambiguous sentiment labels.
Tasks	Sentiment Analysis
Published	2018-08-23
URL	http://arxiv.org/abs/1808.07733v1
PDF	http://arxiv.org/pdf/1808.07733v1.pdf
PWC	https://paperswithcode.com/paper/revisiting-the-importance-of-encoding-logic
Repo	https://github.com/martiansideofthemoon/logic-rules-sentiment
Framework	none

On the Limitation of MagNet Defense against $L_1$-based Adversarial Examples


Title	On the Limitation of MagNet Defense against $L_1$-based Adversarial Examples
Authors	Pei-Hsuan Lu, Pin-Yu Chen, Kang-Cheng Chen, Chia-Mu Yu
Abstract	In recent years, defending adversarial perturbations to natural examples in order to build robust machine learning models trained by deep neural networks (DNNs) has become an emerging research field in the conjunction of deep learning and security. In particular, MagNet consisting of an adversary detector and a data reformer is by far one of the strongest defenses in the black-box oblivious attack setting, where the attacker aims to craft transferable adversarial examples from an undefended DNN model to bypass an unknown defense module deployed on the same DNN model. Under this setting, MagNet can successfully defend a variety of attacks in DNNs, including the high-confidence adversarial examples generated by the Carlini and Wagner’s attack based on the $L_2$ distortion metric. However, in this paper, under the same attack setting we show that adversarial examples crafted based on the $L_1$ distortion metric can easily bypass MagNet and mislead the target DNN image classifiers on MNIST and CIFAR-10. We also provide explanations on why the considered approach can yield adversarial examples with superior attack performance and conduct extensive experiments on variants of MagNet to verify its lack of robustness to $L_1$ distortion based attacks. Notably, our results substantially weaken the assumption of effective threat models on MagNet that require knowing the deployed defense technique when attacking DNNs (i.e., the gray-box attack setting).
Tasks
Published	2018-04-14
URL	http://arxiv.org/abs/1805.00310v2
PDF	http://arxiv.org/pdf/1805.00310v2.pdf
PWC	https://paperswithcode.com/paper/on-the-limitation-of-magnet-defense-against
Repo	https://github.com/ysharma1126/EAD-Attack
Framework	tf

Learning Inductive Biases with Simple Neural Networks


Title	Learning Inductive Biases with Simple Neural Networks
Authors	Reuben Feinman, Brenden M. Lake
Abstract	People use rich prior knowledge about the world in order to efficiently learn new concepts. These priors - also known as “inductive biases” - pertain to the space of internal models considered by a learner, and they help the learner make inferences that go beyond the observed data. A recent study found that deep neural networks optimized for object recognition develop the shape bias (Ritter et al., 2017), an inductive bias possessed by children that plays an important role in early word learning. However, these networks use unrealistically large quantities of training data, and the conditions required for these biases to develop are not well understood. Moreover, it is unclear how the learning dynamics of these networks relate to developmental processes in childhood. We investigate the development and influence of the shape bias in neural networks using controlled datasets of abstract patterns and synthetic images, allowing us to systematically vary the quantity and form of the experience provided to the learning algorithms. We find that simple neural networks develop a shape bias after seeing as few as 3 examples of 4 object categories. The development of these biases predicts the onset of vocabulary acceleration in our networks, consistent with the developmental process in children.
Tasks	Object Recognition
Published	2018-02-08
URL	http://arxiv.org/abs/1802.02745v2
PDF	http://arxiv.org/pdf/1802.02745v2.pdf
PWC	https://paperswithcode.com/paper/learning-inductive-biases-with-simple-neural
Repo	https://github.com/rfeinman/learning-to-learn
Framework	tf

Adversarial Learning for Semi-Supervised Semantic Segmentation


Title	Adversarial Learning for Semi-Supervised Semantic Segmentation
Authors	Wei-Chih Hung, Yi-Hsuan Tsai, Yan-Ting Liou, Yen-Yu Lin, Ming-Hsuan Yang
Abstract	We propose a method for semi-supervised semantic segmentation using an adversarial network. While most existing discriminators are trained to classify input images as real or fake on the image level, we design a discriminator in a fully convolutional manner to differentiate the predicted probability maps from the ground truth segmentation distribution with the consideration of the spatial resolution. We show that the proposed discriminator can be used to improve semantic segmentation accuracy by coupling the adversarial loss with the standard cross entropy loss of the proposed model. In addition, the fully convolutional discriminator enables semi-supervised learning through discovering the trustworthy regions in predicted results of unlabeled images, thereby providing additional supervisory signals. In contrast to existing methods that utilize weakly-labeled images, our method leverages unlabeled images to enhance the segmentation model. Experimental results on the PASCAL VOC 2012 and Cityscapes datasets demonstrate the effectiveness of the proposed algorithm.
Tasks	Semantic Segmentation, Semi-Supervised Semantic Segmentation
Published	2018-02-22
URL	http://arxiv.org/abs/1802.07934v2
PDF	http://arxiv.org/pdf/1802.07934v2.pdf
PWC	https://paperswithcode.com/paper/adversarial-learning-for-semi-supervised
Repo	https://github.com/lym29/DASeg
Framework	pytorch

Black-box Variational Inference for Stochastic Differential Equations


Title	Black-box Variational Inference for Stochastic Differential Equations
Authors	Thomas Ryder, Andrew Golightly, A. Stephen McGough, Dennis Prangle
Abstract	Parameter inference for stochastic differential equations is challenging due to the presence of a latent diffusion process. Working with an Euler-Maruyama discretisation for the diffusion, we use variational inference to jointly learn the parameters and the diffusion paths. We use a standard mean-field variational approximation of the parameter posterior, and introduce a recurrent neural network to approximate the posterior for the diffusion paths conditional on the parameters. This neural network learns how to provide Gaussian state transitions which bridge between observations in a very similar way to the conditioned diffusion process. The resulting black-box inference method can be applied to any SDE system with light tuning requirements. We illustrate the method on a Lotka-Volterra system and an epidemic model, producing accurate parameter estimates in a few hours.
Tasks
Published	2018-02-09
URL	http://arxiv.org/abs/1802.03335v3
PDF	http://arxiv.org/pdf/1802.03335v3.pdf
PWC	https://paperswithcode.com/paper/black-box-variational-inference-for
Repo	https://github.com/anonmaths/tumour_sde_model
Framework	tf

Adversarial Training of Variational Auto-encoders for High Fidelity Image Generation


Title	Adversarial Training of Variational Auto-encoders for High Fidelity Image Generation
Authors	Salman H. Khan, Munawar Hayat, Nick Barnes
Abstract	Variational auto-encoders (VAEs) provide an attractive solution to image generation problem. However, they tend to produce blurred and over-smoothed images due to their dependence on pixel-wise reconstruction loss. This paper introduces a new approach to alleviate this problem in the VAE based generative models. Our model simultaneously learns to match the data, reconstruction loss and the latent distributions of real and fake images to improve the quality of generated samples. To compute the loss distributions, we introduce an auto-encoder based discriminator model which allows an adversarial learning procedure. The discriminator in our model also provides perceptual guidance to the VAE by matching the learned similarity metric of the real and fake samples in the latent space. To stabilize the overall training process, our model uses an error feedback approach to maintain the equilibrium between competing networks in the model. Our experiments show that the generated samples from our proposed model exhibit a diverse set of attributes and facial expressions and scale up to high-resolution images very well.
Tasks	Image Generation
Published	2018-04-27
URL	http://arxiv.org/abs/1804.10323v1
PDF	http://arxiv.org/pdf/1804.10323v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-training-of-variational-auto
Repo	https://github.com/OsvaldN/APS360_Project
Framework	pytorch