July 29, 2019

2886 words 14 mins read

Paper Group AWR 159

Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction. Grounding Language for Transfer in Deep Reinforcement Learning. Local Convergence of Proximal Splitting Methods for Rank Constrained Problems. PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection. The (Un)reliability of saliency methods. Selecting …

Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction


Title	Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction
Authors	Charles Corbière, Hedi Ben-Younes, Alexandre Ramé, Charles Ollion
Abstract	In this paper, we present a method to learn a visual representation adapted for e-commerce products. Based on weakly supervised learning, our model learns from noisy datasets crawled on e-commerce website catalogs and does not require any manual labeling. We show that our representation can be used for downward classification tasks over clothing categories with different levels of granularity. We also demonstrate that the learnt representation is suitable for image retrieval. We achieve nearly state-of-art results on the DeepFashion In-Shop Clothes Retrieval and Categories Attributes Prediction tasks, without using the provided training set.
Tasks	Image Retrieval
Published	2017-09-27
URL	http://arxiv.org/abs/1709.09426v1
PDF	http://arxiv.org/pdf/1709.09426v1.pdf
PWC	https://paperswithcode.com/paper/leveraging-weakly-annotated-data-for-fashion
Repo	https://github.com/fdjingyuan/Deep-Fashion-Analysis-ECCV2018
Framework	pytorch

Grounding Language for Transfer in Deep Reinforcement Learning


Title	Grounding Language for Transfer in Deep Reinforcement Learning
Authors	Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola
Abstract	In this paper, we explore the utilization of natural language to drive transfer for reinforcement learning (RL). Despite the wide-spread application of deep RL techniques, learning generalized policy representations that work across domains remains a challenging problem. We demonstrate that textual descriptions of environments provide a compact intermediate channel to facilitate effective policy transfer. Specifically, by learning to ground the meaning of text to the dynamics of the environment such as transitions and rewards, an autonomous agent can effectively bootstrap policy learning on a new domain given its description. We employ a model-based RL approach consisting of a differentiable planning module, a model-free component and a factorized state representation to effectively use entity descriptions. Our model outperforms prior work on both transfer and multi-task scenarios in a variety of different environments. For instance, we achieve up to 14% and 11.5% absolute improvement over previously existing models in terms of average and initial rewards, respectively.
Tasks
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00133v2
PDF	http://arxiv.org/pdf/1708.00133v2.pdf
PWC	https://paperswithcode.com/paper/grounding-language-for-transfer-in-deep
Repo	https://github.com/karthikncode/Grounded-RL-Transfer
Framework	torch

Local Convergence of Proximal Splitting Methods for Rank Constrained Problems


Title	Local Convergence of Proximal Splitting Methods for Rank Constrained Problems
Authors	Christian Grussler, Pontus Giselsson
Abstract	We analyze the local convergence of proximal splitting algorithms to solve optimization problems that are convex besides a rank constraint. For this, we show conditions under which the proximal operator of a function involving the rank constraint is locally identical to the proximal operator of its convex envelope, hence implying local convergence. The conditions imply that the non-convex algorithms locally converge to a solution whenever a convex relaxation involving the convex envelope can be expected to solve the non-convex problem.
Tasks
Published	2017-10-11
URL	http://arxiv.org/abs/1710.04248v1
PDF	http://arxiv.org/pdf/1710.04248v1.pdf
PWC	https://paperswithcode.com/paper/local-convergence-of-proximal-splitting
Repo	https://github.com/LowRankOpt/LRINorm
Framework	none

PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection


Title	PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection
Authors	Nian Liu, Junwei Han, Ming-Hsuan Yang
Abstract	Contexts play an important role in the saliency detection task. However, given a context region, not all contextual information is helpful for the final task. In this paper, we propose a novel pixel-wise contextual attention network, i.e., the PiCANet, to learn to selectively attend to informative context locations for each pixel. Specifically, for each pixel, it can generate an attention map in which each attention weight corresponds to the contextual relevance at each context location. An attended contextual feature can then be constructed by selectively aggregating the contextual information. We formulate the proposed PiCANet in both global and local forms to attend to global and local contexts, respectively. Both models are fully differentiable and can be embedded into CNNs for joint training. We also incorporate the proposed models with the U-Net architecture to detect salient objects. Extensive experiments show that the proposed PiCANets can consistently improve saliency detection performance. The global and local PiCANets facilitate learning global contrast and homogeneousness, respectively. As a result, our saliency model can detect salient objects more accurately and uniformly, thus performing favorably against the state-of-the-art methods.
Tasks	Saliency Detection
Published	2017-08-21
URL	http://arxiv.org/abs/1708.06433v2
PDF	http://arxiv.org/pdf/1708.06433v2.pdf
PWC	https://paperswithcode.com/paper/picanet-learning-pixel-wise-contextual
Repo	https://github.com/Ugness/PiCANet-Implementation
Framework	pytorch

The (Un)reliability of saliency methods


Title	The (Un)reliability of saliency methods
Authors	Pieter-Jan Kindermans, Sara Hooker, Julius Adebayo, Maximilian Alber, Kristof T. Schütt, Sven Dähne, Dumitru Erhan, Been Kim
Abstract	Saliency methods aim to explain the predictions of deep neural networks. These methods lack reliability when the explanation is sensitive to factors that do not contribute to the model prediction. We use a simple and common pre-processing step —adding a constant shift to the input data— to show that a transformation with no effect on the model can cause numerous methods to incorrectly attribute. In order to guarantee reliability, we posit that methods should fulfill input invariance, the requirement that a saliency method mirror the sensitivity of the model with respect to transformations of the input. We show, through several examples, that saliency methods that do not satisfy input invariance result in misleading attribution.
Tasks	Interpretable Machine Learning
Published	2017-11-02
URL	https://arxiv.org/abs/1711.00867v1
PDF	https://arxiv.org/pdf/1711.00867v1.pdf
PWC	https://paperswithcode.com/paper/the-unreliability-of-saliency-methods
Repo	https://github.com/albermax/innvestigate
Framework	tf

Selecting Representative Examples for Program Synthesis


Title	Selecting Representative Examples for Program Synthesis
Authors	Yewen Pu, Zachery Miranda, Armando Solar-Lezama, Leslie Pack Kaelbling
Abstract	Program synthesis is a class of regression problems where one seeks a solution, in the form of a source-code program, mapping the inputs to their corresponding outputs exactly. Due to its precise and combinatorial nature, program synthesis is commonly formulated as a constraint satisfaction problem, where input-output examples are encoded as constraints and solved with a constraint solver. A key challenge of this formulation is scalability: while constraint solvers work well with a few well-chosen examples, a large set of examples can incur significant overhead in both time and memory. We describe a method to discover a subset of examples that is both small and representative: the subset is constructed iteratively, using a neural network to predict the probability of unchosen examples conditioned on the chosen examples in the subset, and greedily adding the least probable example. We empirically evaluate the representativeness of the subsets constructed by our method, and demonstrate such subsets can significantly improve synthesis time and stability.
Tasks	Program Synthesis
Published	2017-11-09
URL	http://arxiv.org/abs/1711.03243v3
PDF	http://arxiv.org/pdf/1711.03243v3.pdf
PWC	https://paperswithcode.com/paper/selecting-representative-examples-for-program
Repo	https://github.com/evanthebouncy/icml2018_selecting_representative_examples
Framework	tf

Hierarchical Cellular Automata for Visual Saliency


Title	Hierarchical Cellular Automata for Visual Saliency
Authors	Yao Qin, Mengyang Feng, Huchuan Lu, Garrison W. Cottrell
Abstract	Saliency detection, finding the most important parts of an image, has become increasingly popular in computer vision. In this paper, we introduce Hierarchical Cellular Automata (HCA) – a temporally evolving model to intelligently detect salient objects. HCA consists of two main components: Single-layer Cellular Automata (SCA) and Cuboid Cellular Automata (CCA). As an unsupervised propagation mechanism, Single-layer Cellular Automata can exploit the intrinsic relevance of similar regions through interactions with neighbors. Low-level image features as well as high-level semantic information extracted from deep neural networks are incorporated into the SCA to measure the correlation between different image patches. With these hierarchical deep features, an impact factor matrix and a coherence matrix are constructed to balance the influences on each cell’s next state. The saliency values of all cells are iteratively updated according to a well-defined update rule. Furthermore, we propose CCA to integrate multiple saliency maps generated by SCA at different scales in a Bayesian framework. Therefore, single-layer propagation and multi-layer integration are jointly modeled in our unified HCA. Surprisingly, we find that the SCA can improve all existing methods that we applied it to, resulting in a similar precision level regardless of the original results. The CCA can act as an efficient pixel-wise aggregation algorithm that can integrate state-of-the-art methods, resulting in even better results. Extensive experiments on four challenging datasets demonstrate that the proposed algorithm outperforms state-of-the-art conventional methods and is competitive with deep learning based approaches.
Tasks	Saliency Detection
Published	2017-05-26
URL	http://arxiv.org/abs/1705.09425v1
PDF	http://arxiv.org/pdf/1705.09425v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-cellular-automata-for-visual
Repo	https://github.com/ArcherFMY/HCA_saliency_codes
Framework	none

Online and Linear-Time Attention by Enforcing Monotonic Alignments


Title	Online and Linear-Time Attention by Enforcing Monotonic Alignments
Authors	Colin Raffel, Minh-Thang Luong, Peter J. Liu, Ron J. Weiss, Douglas Eck
Abstract	Recurrent neural network models with an attention mechanism have proven to be extremely effective on a wide variety of sequence-to-sequence problems. However, the fact that soft attention mechanisms perform a pass over the entire input sequence when producing each element in the output sequence precludes their use in online settings and results in a quadratic time complexity. Based on the insight that the alignment between input and output sequence elements is monotonic in many problems of interest, we propose an end-to-end differentiable method for learning monotonic alignments which, at test time, enables computing attention online and in linear time. We validate our approach on sentence summarization, machine translation, and online speech recognition problems and achieve results competitive with existing sequence-to-sequence models.
Tasks	Machine Translation, Speech Recognition, Text Summarization
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00784v2
PDF	http://arxiv.org/pdf/1704.00784v2.pdf
PWC	https://paperswithcode.com/paper/online-and-linear-time-attention-by-enforcing
Repo	https://github.com/craffel/mad
Framework	tf

Kernel Feature Selection via Conditional Covariance Minimization


Title	Kernel Feature Selection via Conditional Covariance Minimization
Authors	Jianbo Chen, Mitchell Stern, Martin J. Wainwright, Michael I. Jordan
Abstract	We propose a method for feature selection that employs kernel-based measures of independence to find a subset of covariates that is maximally predictive of the response. Building on past work in kernel dimension reduction, we show how to perform feature selection via a constrained optimization problem involving the trace of the conditional covariance operator. We prove various consistency results for this procedure, and also demonstrate that our method compares favorably with other state-of-the-art algorithms on a variety of synthetic and real data sets.
Tasks	Dimensionality Reduction, Feature Selection
Published	2017-07-04
URL	http://arxiv.org/abs/1707.01164v2
PDF	http://arxiv.org/pdf/1707.01164v2.pdf
PWC	https://paperswithcode.com/paper/kernel-feature-selection-via-conditional
Repo	https://github.com/Jianbo-Lab/CCM
Framework	tf

RankPL: A Qualitative Probabilistic Programming Language


Title	RankPL: A Qualitative Probabilistic Programming Language
Authors	Tjitze Rienstra
Abstract	In this paper we introduce RankPL, a modeling language that can be thought of as a qualitative variant of a probabilistic programming language with a semantics based on Spohn’s ranking theory. Broadly speaking, RankPL can be used to represent and reason about processes that exhibit uncertainty expressible by distinguishing “normal” from” surprising” events. RankPL allows (iterated) revision of rankings over alternative program states and supports various types of reasoning, including abduction and causal inference. We present the language, its denotational semantics, and a number of practical examples. We also discuss an implementation of RankPL that is available for download.
Tasks	Causal Inference, Probabilistic Programming
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07226v1
PDF	http://arxiv.org/pdf/1705.07226v1.pdf
PWC	https://paperswithcode.com/paper/rankpl-a-qualitative-probabilistic
Repo	https://github.com/tjitze/RankPL
Framework	none

PassGAN: A Deep Learning Approach for Password Guessing


Title	PassGAN: A Deep Learning Approach for Password Guessing
Authors	Briland Hitaj, Paolo Gasti, Giuseppe Ateniese, Fernando Perez-Cruz
Abstract	State-of-the-art password guessing tools, such as HashCat and John the Ripper, enable users to check billions of passwords per second against password hashes. In addition to performing straightforward dictionary attacks, these tools can expand password dictionaries using password generation rules, such as concatenation of words (e.g., “password123456”) and leet speak (e.g., “password” becomes “p4s5w0rd”). Although these rules work well in practice, expanding them to model further passwords is a laborious task that requires specialized expertise. To address this issue, in this paper we introduce PassGAN, a novel approach that replaces human-generated password rules with theory-grounded machine learning algorithms. Instead of relying on manual password analysis, PassGAN uses a Generative Adversarial Network (GAN) to autonomously learn the distribution of real passwords from actual password leaks, and to generate high-quality password guesses. Our experiments show that this approach is very promising. When we evaluated PassGAN on two large password datasets, we were able to surpass rule-based and state-of-the-art machine learning password guessing tools. However, in contrast with the other tools, PassGAN achieved this result without any a-priori knowledge on passwords or common password structures. Additionally, when we combined the output of PassGAN with the output of HashCat, we were able to match 51%-73% more passwords than with HashCat alone. This is remarkable, because it shows that PassGAN can autonomously extract a considerable number of password properties that current state-of-the art rules do not encode.
Tasks
Published	2017-09-01
URL	http://arxiv.org/abs/1709.00440v3
PDF	http://arxiv.org/pdf/1709.00440v3.pdf
PWC	https://paperswithcode.com/paper/passgan-a-deep-learning-approach-for-password
Repo	https://github.com/achen04/passwordcracking
Framework	none

Bolt: Accelerated Data Mining with Fast Vector Compression


Title	Bolt: Accelerated Data Mining with Fast Vector Compression
Authors	Davis W Blalock, John V Guttag
Abstract	Vectors of data are at the heart of machine learning and data mining. Recently, vector quantization methods have shown great promise in reducing both the time and space costs of operating on vectors. We introduce a vector quantization algorithm that can compress vectors over 12x faster than existing techniques while also accelerating approximate vector operations such as distance and dot product computations by up to 10x. Because it can encode over 2GB of vectors per second, it makes vector quantization cheap enough to employ in many more circumstances. For example, using our technique to compute approximate dot products in a nested loop can multiply matrices faster than a state-of-the-art BLAS implementation, even when our algorithm must first compress the matrices. In addition to showing the above speedups, we demonstrate that our approach can accelerate nearest neighbor search and maximum inner product search by over 100x compared to floating point operations and up to 10x compared to other vector quantization methods. Our approximate Euclidean distance and dot product computations are not only faster than those of related algorithms with slower encodings, but also faster than Hamming distance computations, which have direct hardware support on the tested platforms. We also assess the errors of our algorithm’s approximate distances and dot products, and find that it is competitive with existing, slower vector quantization algorithms.
Tasks	Quantization
Published	2017-06-30
URL	http://arxiv.org/abs/1706.10283v1
PDF	http://arxiv.org/pdf/1706.10283v1.pdf
PWC	https://paperswithcode.com/paper/bolt-accelerated-data-mining-with-fast-vector
Repo	https://github.com/dblalock/bolt
Framework	none

Fisher GAN


Title	Fisher GAN
Authors	Youssef Mroueh, Tom Sercu
Abstract	Generative Adversarial Networks (GANs) are powerful models for learning complex distributions. Stable training of GANs has been addressed in many recent works which explore different metrics between distributions. In this paper we introduce Fisher GAN which fits within the Integral Probability Metrics (IPM) framework for training GANs. Fisher GAN defines a critic with a data dependent constraint on its second order moments. We show in this paper that Fisher GAN allows for stable and time efficient training that does not compromise the capacity of the critic, and does not need data independent constraints such as weight clipping. We analyze our Fisher IPM theoretically and provide an algorithm based on Augmented Lagrangian for Fisher GAN. We validate our claims on both image sample generation and semi-supervised classification using Fisher GAN.
Tasks
Published	2017-05-26
URL	http://arxiv.org/abs/1705.09675v3
PDF	http://arxiv.org/pdf/1705.09675v3.pdf
PWC	https://paperswithcode.com/paper/fisher-gan
Repo	https://github.com/tomsercu/FisherGAN
Framework	pytorch

Gradient descent GAN optimization is locally stable


Title	Gradient descent GAN optimization is locally stable
Authors	Vaishnavh Nagarajan, J. Zico Kolter
Abstract	Despite the growing prominence of generative adversarial networks (GANs), optimization in GANs is still a poorly understood topic. In this paper, we analyze the “gradient descent” form of GAN optimization i.e., the natural setting where we simultaneously take small gradient steps in both generator and discriminator parameters. We show that even though GAN optimization does not correspond to a convex-concave game (even for simple parameterizations), under proper conditions, equilibrium points of this optimization procedure are still \emph{locally asymptotically stable} for the traditional GAN formulation. On the other hand, we show that the recently proposed Wasserstein GAN can have non-convergent limit cycles near equilibrium. Motivated by this stability analysis, we propose an additional regularization term for gradient descent GAN updates, which \emph{is} able to guarantee local stability for both the WGAN and the traditional GAN, and also shows practical promise in speeding up convergence and addressing mode collapse.
Tasks
Published	2017-06-13
URL	http://arxiv.org/abs/1706.04156v3
PDF	http://arxiv.org/pdf/1706.04156v3.pdf
PWC	https://paperswithcode.com/paper/gradient-descent-gan-optimization-is-locally
Repo	https://github.com/locuslab/gradient_regularized_gan
Framework	tf

CASENet: Deep Category-Aware Semantic Edge Detection


Title	CASENet: Deep Category-Aware Semantic Edge Detection
Authors	Zhiding Yu, Chen Feng, Ming-Yu Liu, Srikumar Ramalingam
Abstract	Boundary and edge cues are highly beneficial in improving a wide variety of vision tasks such as semantic segmentation, object recognition, stereo, and object proposal generation. Recently, the problem of edge detection has been revisited and significant progress has been made with deep learning. While classical edge detection is a challenging binary problem in itself, the category-aware semantic edge detection by nature is an even more challenging multi-label problem. We model the problem such that each edge pixel can be associated with more than one class as they appear in contours or junctions belonging to two or more semantic classes. To this end, we propose a novel end-to-end deep semantic edge learning architecture based on ResNet and a new skip-layer architecture where category-wise edge activations at the top convolution layer share and are fused with the same set of bottom layer features. We then propose a multi-label loss function to supervise the fused activations. We show that our proposed architecture benefits this problem with better performance, and we outperform the current state-of-the-art semantic edge detection methods by a large margin on standard data sets such as SBD and Cityscapes.
Tasks	Edge Detection, Object Proposal Generation, Semantic Segmentation
Published	2017-05-27
URL	http://arxiv.org/abs/1705.09759v1
PDF	http://arxiv.org/pdf/1705.09759v1.pdf
PWC	https://paperswithcode.com/paper/casenet-deep-category-aware-semantic-edge
Repo	https://github.com/Lavender105/DFF
Framework	pytorch