Paper Group AWR 100
Representation Tradeoffs for Hyperbolic Embeddings. GANs beyond divergence minimization. Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors. Geometry-Contrastive GAN for Facial Expression Transfer. InstaNAS: Instance-aware Neural Architecture Search. Adversarial Uncertainty Quantification in Physics-Informed Neural Network …
Representation Tradeoffs for Hyperbolic Embeddings
Title | Representation Tradeoffs for Hyperbolic Embeddings |
Authors | Christopher De Sa, Albert Gu, Christopher Ré, Frederic Sala |
Abstract | Hyperbolic embeddings offer excellent quality with few dimensions when embedding hierarchical data structures like synonym or type hierarchies. Given a tree, we give a combinatorial construction that embeds the tree in hyperbolic space with arbitrarily low distortion without using optimization. On WordNet, our combinatorial embedding obtains a mean-average-precision of 0.989 with only two dimensions, while Nickel et al.‘s recent construction obtains 0.87 using 200 dimensions. We provide upper and lower bounds that allow us to characterize the precision-dimensionality tradeoff inherent in any hyperbolic embedding. To embed general metric spaces, we propose a hyperbolic generalization of multidimensional scaling (h-MDS). We show how to perform exact recovery of hyperbolic points from distances, provide a perturbation analysis, and give a recovery result that allows us to reduce dimensionality. The h-MDS approach offers consistently low distortion even with few dimensions across several datasets. Finally, we extract lessons from the algorithms and theory above to design a PyTorch-based implementation that can handle incomplete information and is scalable. |
Tasks | |
Published | 2018-04-10 |
URL | http://arxiv.org/abs/1804.03329v2 |
http://arxiv.org/pdf/1804.03329v2.pdf | |
PWC | https://paperswithcode.com/paper/representation-tradeoffs-for-hyperbolic |
Repo | https://github.com/HazyResearch/hyperbolics |
Framework | pytorch |
GANs beyond divergence minimization
Title | GANs beyond divergence minimization |
Authors | Alexia Jolicoeur-Martineau |
Abstract | Generative adversarial networks (GANs) can be interpreted as an adversarial game between two players, a discriminator D and a generator G, in which D learns to classify real from fake data and G learns to generate realistic data by “fooling” D into thinking that fake data is actually real data. Currently, a dominating view is that G actually learns by minimizing a divergence given that the general objective function is a divergence when D is optimal. However, this view has been challenged due to inconsistencies between theory and practice. In this paper, we discuss of the properties associated with most loss functions for G (e.g., saturating/non-saturating f-GAN, LSGAN, WGAN, etc.). We show that these loss functions are not divergences and do not have the same equilibrium as expected of divergences. This suggests that G does not need to minimize the same objective function as D maximize, nor maximize the objective of D after swapping real data with fake data (non-saturating GAN) but can instead use a wide range of possible loss functions to learn to generate realistic data. We define GANs through two separate and independent D maximization and G minimization steps. We generalize the generator step to four new classes of loss functions, most of which are actual divergences (while traditional G loss functions are not). We test a wide variety of loss functions from these four classes on a synthetic dataset and on CIFAR-10. We observe that most loss functions converge well and provide comparable data generation quality to non-saturating GAN, LSGAN, and WGAN-GP generator loss functions, whether we use divergences or non-divergences. These results suggest that GANs do not conform well to the divergence minimization theory and form a much broader range of models than previously assumed. |
Tasks | |
Published | 2018-09-06 |
URL | http://arxiv.org/abs/1809.02145v1 |
http://arxiv.org/pdf/1809.02145v1.pdf | |
PWC | https://paperswithcode.com/paper/gans-beyond-divergence-minimization |
Repo | https://github.com/AlexiaJM/GANsBeyondDivergenceMin |
Framework | pytorch |
Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors
Title | Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors |
Authors | Rico Jonschkowski, Divyam Rastogi, Oliver Brock |
Abstract | We present differentiable particle filters (DPFs): a differentiable implementation of the particle filter algorithm with learnable motion and measurement models. Since DPFs are end-to-end differentiable, we can efficiently train their models by optimizing end-to-end state estimation performance, rather than proxy objectives such as model accuracy. DPFs encode the structure of recursive state estimation with prediction and measurement update that operate on a probability distribution over states. This structure represents an algorithmic prior that improves learning performance in state estimation problems while enabling explainability of the learned model. Our experiments on simulated and real data show substantial benefits from end-to- end learning with algorithmic priors, e.g. reducing error rates by ~80%. Our experiments also show that, unlike long short-term memory networks, DPFs learn localization in a policy-agnostic way and thus greatly improve generalization. Source code is available at https://github.com/tu-rbo/differentiable-particle-filters . |
Tasks | |
Published | 2018-05-28 |
URL | http://arxiv.org/abs/1805.11122v2 |
http://arxiv.org/pdf/1805.11122v2.pdf | |
PWC | https://paperswithcode.com/paper/differentiable-particle-filters-end-to-end |
Repo | https://github.com/tu-rbo/differentiable-particle-filters |
Framework | tf |
Geometry-Contrastive GAN for Facial Expression Transfer
Title | Geometry-Contrastive GAN for Facial Expression Transfer |
Authors | Fengchun Qiao, Naiming Yao, Zirui Jiao, Zhihao Li, Hui Chen, Hongan Wang |
Abstract | In this paper, we propose a Geometry-Contrastive Generative Adversarial Network (GC-GAN) for transferring continuous emotions across different subjects. Given an input face with certain emotion and a target facial expression from another subject, GC-GAN can generate an identity-preserving face with the target expression. Geometry information is introduced into cGANs as continuous conditions to guide the generation of facial expressions. In order to handle the misalignment across different subjects or emotions, contrastive learning is used to transform geometry manifold into an embedded semantic manifold of facial expressions. Therefore, the embedded geometry is injected into the latent space of GANs and control the emotion generation effectively. Experimental results demonstrate that our proposed method can be applied in facial expression transfer even there exist big differences in facial shapes and expressions between different subjects. |
Tasks | |
Published | 2018-02-06 |
URL | http://arxiv.org/abs/1802.01822v2 |
http://arxiv.org/pdf/1802.01822v2.pdf | |
PWC | https://paperswithcode.com/paper/geometry-contrastive-gan-for-facial |
Repo | https://github.com/joffery/GC-GAN |
Framework | tf |
InstaNAS: Instance-aware Neural Architecture Search
Title | InstaNAS: Instance-aware Neural Architecture Search |
Authors | An-Chieh Cheng, Chieh Hubert Lin, Da-Cheng Juan, Wei Wei, Min Sun |
Abstract | Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy. However, a single architecture may not be representative enough for the whole dataset with high diversity and variety. Intuitively, electing domain-expert architectures that are proficient in domain-specific features can further benefit architecture related objectives such as latency. In this paper, we propose InstaNAS—an instance-aware NAS framework—that employs a controller trained to search for a “distribution of architectures” instead of a single architecture; This allows the model to use sophisticated architectures for the difficult samples, which usually comes with large architecture related cost, and shallow architectures for those easy samples. During the inference phase, the controller assigns each of the unseen input samples with a domain expert architecture that can achieve high accuracy with customized inference costs. Experiments within a search space inspired by MobileNetV2 show InstaNAS can achieve up to 48.8% latency reduction without compromising accuracy on a series of datasets against MobileNetV2. |
Tasks | Neural Architecture Search |
Published | 2018-11-26 |
URL | https://arxiv.org/abs/1811.10201v3 |
https://arxiv.org/pdf/1811.10201v3.pdf | |
PWC | https://paperswithcode.com/paper/instanas-instance-aware-neural-architecture |
Repo | https://github.com/AnjieZheng/InstaNAS |
Framework | none |
Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
Title | Adversarial Uncertainty Quantification in Physics-Informed Neural Networks |
Authors | Yibo Yang, Paris Perdikaris |
Abstract | We present a deep learning framework for quantifying and propagating uncertainty in systems governed by non-linear differential equations using physics-informed neural networks. Specifically, we employ latent variable models to construct probabilistic representations for the system states, and put forth an adversarial inference procedure for training them on data, while constraining their predictions to satisfy given physical laws expressed by partial differential equations. Such physics-informed constraints provide a regularization mechanism for effectively training deep generative models as surrogates of physical systems in which the cost of data acquisition is high, and training data-sets are typically small. This provides a flexible framework for characterizing uncertainty in the outputs of physical systems due to randomness in their inputs or noise in their observations that entirely bypasses the need for repeatedly sampling expensive experiments or numerical simulators. We demonstrate the effectiveness of our approach through a series of examples involving uncertainty propagation in non-linear conservation laws, and the discovery of constitutive laws for flow through porous media directly from noisy data. |
Tasks | Latent Variable Models |
Published | 2018-11-09 |
URL | http://arxiv.org/abs/1811.04026v1 |
http://arxiv.org/pdf/1811.04026v1.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-uncertainty-quantification-in |
Repo | https://github.com/PredictiveIntelligenceLab/UQPINNs |
Framework | none |
Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
Title | Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer |
Authors | Juncen Li, Robin Jia, He He, Percy Liang |
Abstract | We consider the task of text attribute transfer: transforming a sentence to alter a specific attribute (e.g., sentiment) while preserving its attribute-independent content (e.g., changing “screen is just the right size” to “screen is too small”). Our training data includes only sentences labeled with their attribute (e.g., positive or negative), but not pairs of sentences that differ only in their attributes, so we must learn to disentangle attributes from attribute-independent content in an unsupervised way. Previous work using adversarial methods has struggled to produce high-quality outputs. In this paper, we propose simpler methods motivated by the observation that text attributes are often marked by distinctive phrases (e.g., “too small”). Our strongest method extracts content words by deleting phrases associated with the sentence’s original attribute value, retrieves new phrases associated with the target attribute, and uses a neural model to fluently combine these into a final output. On human evaluation, our best method generates grammatical and appropriate responses on 22% more inputs than the best previous system, averaged over three attribute transfer datasets: altering sentiment of reviews on Yelp, altering sentiment of reviews on Amazon, and altering image captions to be more romantic or humorous. |
Tasks | Image Captioning, Style Transfer, Text Attribute Transfer |
Published | 2018-04-17 |
URL | http://arxiv.org/abs/1804.06437v1 |
http://arxiv.org/pdf/1804.06437v1.pdf | |
PWC | https://paperswithcode.com/paper/delete-retrieve-generate-a-simple-approach-to |
Repo | https://github.com/davidgolub/charizard |
Framework | pytorch |
Pruning Deep Neural Networks using Partial Least Squares
Title | Pruning Deep Neural Networks using Partial Least Squares |
Authors | Artur Jordao, Ricardo Kloss, Fernando Yamada, William Robson Schwartz |
Abstract | Modern pattern recognition methods are based on convolutional networks since they are able to learn complex patterns that benefit the classification. However, convolutional networks are computationally expensive and require a considerable amount of memory, which limits their deployment on low-power and resource-constrained systems. To handle these problems, recent approaches have proposed pruning strategies that find and remove unimportant neurons (i.e., filters) in these networks. Despite achieving remarkable results, existing pruning approaches are ineffective since the accuracy of the original network is degraded. In this work, we propose a novel approach to efficiently remove filters from convolutional networks. Our approach estimates the filter importance based on its relationship with the class label on a low-dimensional space. This relationship is computed using Partial Least Squares (PLS) and Variable Importance in Projection (VIP). Our method is able to reduce up to 67% of the floating point operations (FLOPs) without penalizing the network accuracy. With a negligible drop in accuracy, we can reduce up to 90% of FLOPs. Additionally, sometimes the method is even able to improve the accuracy compared to original, unpruned, network. We show that employing PLS+VIP as the criterion for detecting the filters to be removed is better than recent feature selection techniques, which have been employed by state-of-the-art pruning methods. Finally, we show that the proposed method achieves the highest FLOPs reduction and the smallest drop in accuracy when compared to state-of-the-art pruning approaches. Codes are available at: https://github.com/arturjordao/PruningNeuralNetworks |
Tasks | Feature Selection |
Published | 2018-10-17 |
URL | https://arxiv.org/abs/1810.07610v3 |
https://arxiv.org/pdf/1810.07610v3.pdf | |
PWC | https://paperswithcode.com/paper/pruning-deep-neural-networks-using-partial |
Repo | https://github.com/arturjordao/PruningNeuralNetworks |
Framework | tf |
MISSION: Ultra Large-Scale Feature Selection using Count-Sketches
Title | MISSION: Ultra Large-Scale Feature Selection using Count-Sketches |
Authors | Amirali Aghazadeh, Ryan Spring, Daniel LeJeune, Gautam Dasarathy, Anshumali Shrivastava, Richard G. Baraniuk |
Abstract | Feature selection is an important challenge in machine learning. It plays a crucial role in the explainability of machine-driven decisions that are rapidly permeating throughout modern society. Unfortunately, the explosion in the size and dimensionality of real-world datasets poses a severe challenge to standard feature selection algorithms. Today, it is not uncommon for datasets to have billions of dimensions. At such scale, even storing the feature vector is impossible, causing most existing feature selection methods to fail. Workarounds like feature hashing, a standard approach to large-scale machine learning, helps with the computational feasibility, but at the cost of losing the interpretability of features. In this paper, we present MISSION, a novel framework for ultra large-scale feature selection that performs stochastic gradient descent while maintaining an efficient representation of the features in memory using a Count-Sketch data structure. MISSION retains the simplicity of feature hashing without sacrificing the interpretability of the features while using only O(log^2(p)) working memory. We demonstrate that MISSION accurately and efficiently performs feature selection on real-world, large-scale datasets with billions of dimensions. |
Tasks | Feature Selection |
Published | 2018-06-12 |
URL | http://arxiv.org/abs/1806.04310v1 |
http://arxiv.org/pdf/1806.04310v1.pdf | |
PWC | https://paperswithcode.com/paper/mission-ultra-large-scale-feature-selection |
Repo | https://github.com/rdspring1/MISSION |
Framework | none |
Multi-focus Noisy Image Fusion using Low-Rank Representation
Title | Multi-focus Noisy Image Fusion using Low-Rank Representation |
Authors | Hui Li, Xiao-Jun Wu, Tariq Durrani |
Abstract | Multi-focus noisy image fusion represents an important task in the field of image fusion which generates a single, clear and focused image from all source images. In this paper, we propose a novel multi-focus noisy image fusion method based on low-rank representation (LRR) which is a powerful tool in representation learning. A multi-scale transform framework is adopted in which source images are decomposed into low frequency and high frequency coefficients, respectively. For low frequency coefficients, the fused low frequency coefficients are determined by a spatial frequency strategy, while the high frequency coefficients are fused by the LRR-based fusion strategy. Finally, the fused image is reconstructed by inverse multi-scale transforms with fused coefficients. Experimental results demonstrate that the proposed algorithm offers state-of-the-art performance even when the source images contain noise. The Code of our fusion method is available at https://github.com/hli1221/imagefusion_noisy_lrr |
Tasks | Representation Learning |
Published | 2018-04-25 |
URL | https://arxiv.org/abs/1804.09325v6 |
https://arxiv.org/pdf/1804.09325v6.pdf | |
PWC | https://paperswithcode.com/paper/multi-focus-noisy-image-fusion-using-low-rank |
Repo | https://github.com/exceptionLi/imagefusion_noisy_lrr |
Framework | none |
Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds using Convolutional Neural Networks
Title | Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds using Convolutional Neural Networks |
Authors | Yizhak Ben-Shabat, Michael Lindenbaum, Anath Fischer |
Abstract | In this paper, we propose a normal estimation method for unstructured 3D point clouds. This method, called Nesti-Net, builds on a new local point cloud representation which consists of multi-scale point statistics (MuPS), estimated on a local coarse Gaussian grid. This representation is a suitable input to a CNN architecture. The normals are estimated using a mixture-of-experts (MoE) architecture, which relies on a data-driven approach for selecting the optimal scale around each point and encourages sub-network specialization. Interesting insights into the network’s resource distribution are provided. The scale prediction significantly improves robustness to different noise levels, point density variations and different levels of detail. We achieve state-of-the-art results on a benchmark synthetic dataset and present qualitative results on real scanned scenes. |
Tasks | |
Published | 2018-12-03 |
URL | http://arxiv.org/abs/1812.00709v1 |
http://arxiv.org/pdf/1812.00709v1.pdf | |
PWC | https://paperswithcode.com/paper/nesti-net-normal-estimation-for-unstructured |
Repo | https://github.com/sitzikbs/Nesti-Net |
Framework | tf |
Training neural audio classifiers with few data
Title | Training neural audio classifiers with few data |
Authors | Jordi Pons, Joan Serrà, Xavier Serra |
Abstract | We investigate supervised learning strategies that improve the training of neural network audio classifiers on small annotated collections. In particular, we study whether (i) a naive regularization of the solution space, (ii) prototypical networks, (iii) transfer learning, or (iv) their combination, can foster deep learning models to better leverage a small amount of training examples. To this end, we evaluate (i-iv) for the tasks of acoustic event recognition and acoustic scene classification, considering from 1 to 100 labeled examples per class. Results indicate that transfer learning is a powerful strategy in such scenarios, but prototypical networks show promising results when one does not count with external or validation data. |
Tasks | Acoustic Scene Classification, Scene Classification, Transfer Learning |
Published | 2018-10-24 |
URL | http://arxiv.org/abs/1810.10274v3 |
http://arxiv.org/pdf/1810.10274v3.pdf | |
PWC | https://paperswithcode.com/paper/training-neural-audio-classifiers-with-few |
Repo | https://github.com/jordipons/neural-classifiers-with-few-audio |
Framework | tf |
Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance
Title | Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance |
Authors | Zhixin Shu, Mihir Sahasrabudhe, Alp Guler, Dimitris Samaras, Nikos Paragios, Iasonas Kokkinos |
Abstract | In this work we introduce Deforming Autoencoders, a generative model for images that disentangles shape from appearance in an unsupervised manner. As in the deformable template paradigm, shape is represented as a deformation between a canonical coordinate system (template') and an observed image, while appearance is modeled in canonical’, template, coordinates, thus discarding variability due to deformations. We introduce novel techniques that allow this approach to be deployed in the setting of autoencoders and show that this method can be used for unsupervised group-wise image alignment. We show experiments with expression morphing in humans, hands, and digits, face manipulation, such as shape and appearance interpolation, as well as unsupervised landmark localization. A more powerful form of unsupervised disentangling becomes possible in template coordinates, allowing us to successfully decompose face images into shading and albedo, and further manipulate face images. |
Tasks | Unsupervised Facial Landmark Detection |
Published | 2018-06-18 |
URL | http://arxiv.org/abs/1806.06503v1 |
http://arxiv.org/pdf/1806.06503v1.pdf | |
PWC | https://paperswithcode.com/paper/deforming-autoencoders-unsupervised |
Repo | https://github.com/zhixinshu/DeformingAutoencoders-pytorch |
Framework | pytorch |
ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search
Title | ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search |
Authors | Shangtong Zhang, Hao Chen, Hengshuai Yao |
Abstract | In this paper, we propose an actor ensemble algorithm, named ACE, for continuous control with a deterministic policy in reinforcement learning. In ACE, we use actor ensemble (i.e., multiple actors) to search the global maxima of the critic. Besides the ensemble perspective, we also formulate ACE in the option framework by extending the option-critic architecture with deterministic intra-option policies, revealing a relationship between ensemble and options. Furthermore, we perform a look-ahead tree search with those actors and a learned value prediction model, resulting in a refined value estimation. We demonstrate a significant performance boost of ACE over DDPG and its variants in challenging physical robot simulators. |
Tasks | Continuous Control |
Published | 2018-11-06 |
URL | http://arxiv.org/abs/1811.02696v1 |
http://arxiv.org/pdf/1811.02696v1.pdf | |
PWC | https://paperswithcode.com/paper/ace-an-actor-ensemble-algorithm-for |
Repo | https://github.com/ShangtongZhang/DeepRL |
Framework | pytorch |
Convolutional Neural Networks for Skull-stripping in Brain MR Imaging using Consensus-based Silver standard Masks
Title | Convolutional Neural Networks for Skull-stripping in Brain MR Imaging using Consensus-based Silver standard Masks |
Authors | Oeslle Lucena, Roberto Souza, Leticia Rittner, Richard Frayne, Roberto Lotufo |
Abstract | Convolutional neural networks (CNN) for medical imaging are constrained by the number of annotated data required in the training stage. Usually, manual annotation is considered to be the “gold standard”. However, medical imaging datasets that include expert manual segmentation are scarce as this step is time-consuming, and therefore expensive. Moreover, single-rater manual annotation is most often used in data-driven approaches making the network optimal with respect to only that single expert. In this work, we propose a CNN for brain extraction in magnetic resonance (MR) imaging, that is fully trained with what we refer to as silver standard masks. Our method consists of 1) developing a dataset with “silver standard” masks as input, and implementing both 2) a tri-planar method using parallel 2D U-Net-based CNNs (referred to as CONSNet) and 3) an auto-context implementation of CONSNet. The term CONSNet refers to our integrated approach, i.e., training with silver standard masks and using a 2D U-Net-based architecture. Our results showed that we outperformed (i.e., larger Dice coefficients) the current state-of-the-art SS methods. Our use of silver standard masks reduced the cost of manual annotation, decreased inter-intra-rater variability, and avoided CNN segmentation super-specialization towards one specific manual annotation guideline that can occur when gold standard masks are used. Moreover, the usage of silver standard masks greatly enlarges the volume of input annotated data because we can relatively easily generate labels for unlabeled data. In addition, our method has the advantage that, once trained, it takes only a few seconds to process a typical brain image volume using modern hardware, such as a high-end graphics processing unit. In contrast, many of the other competitive methods have processing times in the order of minutes. |
Tasks | Skull Stripping |
Published | 2018-04-13 |
URL | http://arxiv.org/abs/1804.04988v1 |
http://arxiv.org/pdf/1804.04988v1.pdf | |
PWC | https://paperswithcode.com/paper/convolutional-neural-networks-for-skull |
Repo | https://github.com/MICLab-Unicamp/CONSNet |
Framework | tf |