Paper Group ANR 1773
Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusion. Man-in-the-Middle Attacks against Machine Learning Classifiers via Malicious Generative Models. On Application of Learning to Rank for E-Commerce Search. A Domain Generalization Perspective on Listwise Context Modeling. QGAN: Quantized Generative Adversarial Networks. U …
Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusion
| Title | Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusion |
| Authors | Xin Deng, Pier Luigi Dragotti |
| Abstract | In this paper, we propose a novel deep convolutional neural network to solve the general multi-modal image restoration (MIR) and multi-modal image fusion (MIF) problems. Different from other methods based on deep learning, our network architecture is designed by drawing inspirations from a new proposed multi-modal convolutional sparse coding (MCSC) model. The key feature of the proposed network is that it can automatically split the common information shared among different modalities, from the unique information that belongs to each single modality, and is therefore denoted with CU-Net, i.e., Common and Unique information splitting network. Specifically, the CU-Net is composed of three modules, i.e., the unique feature extraction module (UFEM), common feature preservation module (CFPM), and image reconstruction module (IRM). The architecture of each module is derived from the corresponding part in the MCSC model, which consists of several learned convolutional sparse coding (LCSC) blocks. Extensive numerical results verify the effectiveness of our method on a variety of MIR and MIF tasks, including RGB guided depth image super-resolution, flash guided non-flash image denoising, multi-focus and multi-exposure image fusion. |
| Tasks | Denoising, Image Denoising, Image Reconstruction, Image Restoration, Image Super-Resolution, Super-Resolution |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.04066v1 |
| https://arxiv.org/pdf/1910.04066v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-convolutional-neural-network-for-multi |
| Repo | |
| Framework | |
Man-in-the-Middle Attacks against Machine Learning Classifiers via Malicious Generative Models
| Title | Man-in-the-Middle Attacks against Machine Learning Classifiers via Malicious Generative Models |
| Authors | Derui, Wang, Chaoran Li, Sheng Wen, Surya Nepal, Yang Xiang |
| Abstract | Deep Neural Networks (DNNs) are vulnerable to deliberately crafted adversarial examples. In the past few years, many efforts have been spent on exploring query-optimisation attacks to find adversarial examples of either black-box or white-box DNN models, as well as the defending countermeasures against those attacks. In this work, we explore vulnerabilities of DNN models under the umbrella of Man-in-the-Middle (MitM) attacks, which has not been investigated before. From the perspective of an MitM adversary, the aforementioned adversarial example attacks are not viable anymore. First, such attacks must acquire the outputs from the models by multiple times before actually launching attacks, which is difficult for the MitM adversary in practice. Second, such attacks are one-off and cannot be directly generalised onto new data examples, which decreases the rate of return for the attacker. In contrast, using generative models to craft adversarial examples on the fly can mitigate the drawbacks. However, the adversarial capability of the generative models, such as Variational Auto-Encoder (VAE), has not been extensively studied. Therefore, given a classifier, we investigate using a VAE decoder to either transform benign inputs to their adversarial counterparts or decode outputs from benign VAE encoders to be adversarial examples. The proposed method can endue more capability to MitM attackers. Based on our evaluation, the proposed attack can achieve above 95% success rate on both MNIST and CIFAR10 datasets, which is better or comparable with state-of-the-art query-optimisation attacks. At the meantime, the attack is 104 times faster than the query-optimisation attacks. |
| Tasks | |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.06838v1 |
| https://arxiv.org/pdf/1910.06838v1.pdf | |
| PWC | https://paperswithcode.com/paper/man-in-the-middle-attacks-against-machine |
| Repo | |
| Framework | |
On Application of Learning to Rank for E-Commerce Search
| Title | On Application of Learning to Rank for E-Commerce Search |
| Authors | Shubhra Kanti Karmaker Santu, Parikshit Sondhi, ChengXiang Zhai |
| Abstract | E-Commerce (E-Com) search is an emerging important new application of information retrieval. Learning to Rank (LETOR) is a general effective strategy for optimizing search engines, and is thus also a key technology for E-Com search. While the use of LETOR for web search has been well studied, its use for E-Com search has not yet been well explored. In this paper, we discuss the practical challenges in applying learning to rank methods to E-Com search, including the challenges in feature representation, obtaining reliable relevance judgments, and optimally exploiting multiple user feedback signals such as click rates, add-to-cart ratios, order rates, and revenue. We study these new challenges using experiments on industry data sets and report several interesting findings that can provide guidance on how to optimally apply LETOR to E-Com search: First, popularity-based features defined solely on product items are very useful and LETOR methods were able to effectively optimize their combination with relevance-based features. Second, query attribute sparsity raises challenges for LETOR, and selecting features to reduce/avoid sparsity is beneficial. Third, while crowdsourcing is often useful for obtaining relevance judgments for Web search, it does not work as well for E-Com search due to difficulty in eliciting sufficiently fine grained relevance judgments. Finally, among the multiple feedback signals, the order rate is found to be the most robust training objective, followed by click rate, while add-to-cart ratio seems least robust, suggesting that an effective practical strategy may be to initially use click rates for training and gradually shift to using order rates as they become available. |
| Tasks | Information Retrieval, Learning-To-Rank |
| Published | 2019-03-01 |
| URL | http://arxiv.org/abs/1903.04263v1 |
| http://arxiv.org/pdf/1903.04263v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-application-of-learning-to-rank-for-e |
| Repo | |
| Framework | |
A Domain Generalization Perspective on Listwise Context Modeling
| Title | A Domain Generalization Perspective on Listwise Context Modeling |
| Authors | Lin Zhu, Yihong Chen, Bowen He |
| Abstract | As one of the most popular techniques for solving the ranking problem in information retrieval, Learning-to-rank (LETOR) has received a lot of attention both in academia and industry due to its importance in a wide variety of data mining applications. However, most of existing LETOR approaches choose to learn a single global ranking function to handle all queries, and ignore the substantial differences that exist between queries. In this paper, we propose a domain generalization strategy to tackle this problem. We propose Query-Invariant Listwise Context Modeling (QILCM), a novel neural architecture which eliminates the detrimental influence of inter-query variability by learning \textit{query-invariant} latent representations, such that the ranking system could generalize better to unseen queries. We evaluate our techniques on benchmark datasets, demonstrating that QILCM outperforms previous state-of-the-art approaches by a substantial margin. |
| Tasks | Domain Generalization, Information Retrieval, Learning-To-Rank |
| Published | 2019-02-12 |
| URL | http://arxiv.org/abs/1902.04484v1 |
| http://arxiv.org/pdf/1902.04484v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-domain-generalization-perspective-on |
| Repo | |
| Framework | |
QGAN: Quantized Generative Adversarial Networks
| Title | QGAN: Quantized Generative Adversarial Networks |
| Authors | Peiqi Wang, Dongsheng Wang, Yu Ji, Xinfeng Xie, Haoxuan Song, XuXin Liu, Yongqiang Lyu, Yuan Xie |
| Abstract | The intensive computation and memory requirements of generative adversarial neural networks (GANs) hinder its real-world deployment on edge devices such as smartphones. Despite the success in model reduction of CNNs, neural network quantization methods have not yet been studied on GANs, which are mainly faced with the issues of both the effectiveness of quantization algorithms and the instability of training GAN models. In this paper, we start with an extensive study on applying existing successful methods to quantize GANs. Our observation reveals that none of them generates samples with reasonable quality because of the underrepresentation of quantized values in model weights, and the generator and discriminator networks show different sensitivities upon quantization methods. Motivated by these observations, we develop a novel quantization method for GANs based on EM algorithms, named as QGAN. We also propose a multi-precision algorithm to help find the optimal number of bits of quantized GAN models in conjunction with corresponding result qualities. Experiments on CIFAR-10 and CelebA show that QGAN can quantize GANs to even 1-bit or 2-bit representations with results of quality comparable to original models. |
| Tasks | Quantization |
| Published | 2019-01-24 |
| URL | http://arxiv.org/abs/1901.08263v1 |
| http://arxiv.org/pdf/1901.08263v1.pdf | |
| PWC | https://paperswithcode.com/paper/qgan-quantized-generative-adversarial |
| Repo | |
| Framework | |
Universal Approximation with Certified Networks
| Title | Universal Approximation with Certified Networks |
| Authors | Maximilian Baader, Matthew Mirman, Martin Vechev |
| Abstract | Training neural networks to be certifiably robust is critical to ensure their safety against adversarial attacks. However, it is currently very difficult to train a neural network that is both accurate and certifiably robust. In this work we take a step towards addressing this challenge. We prove that for every continuous function $f$, there exists a network $n$ such that: (i) $n$ approximates $f$ arbitrarily close, and (ii) simple interval bound propagation of a region $B$ through $n$ yields a result that is arbitrarily close to the optimal output of $f$ on $B$. Our result can be seen as a Universal Approximation Theorem for interval-certified ReLU networks. To the best of our knowledge, this is the first work to prove the existence of accurate, interval-certified networks. |
| Tasks | |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1909.13846v2 |
| https://arxiv.org/pdf/1909.13846v2.pdf | |
| PWC | https://paperswithcode.com/paper/universal-approximation-with-certified-1 |
| Repo | |
| Framework | |
Policy Learning for Fairness in Ranking
| Title | Policy Learning for Fairness in Ranking |
| Authors | Ashudeep Singh, Thorsten Joachims |
| Abstract | Conventional Learning-to-Rank (LTR) methods optimize the utility of the rankings to the users, but they are oblivious to their impact on the ranked items. However, there has been a growing understanding that the latter is important to consider for a wide range of ranking applications (e.g. online marketplaces, job placement, admissions). To address this need, we propose a general LTR framework that can optimize a wide range of utility metrics (e.g. NDCG) while satisfying fairness of exposure constraints with respect to the items. This framework expands the class of learnable ranking functions to stochastic ranking policies, which provides a language for rigorously expressing fairness specifications. Furthermore, we provide a new LTR algorithm called Fair-PG-Rank for directly searching the space of fair ranking policies via a policy-gradient approach. Beyond the theoretical evidence in deriving the framework and the algorithm, we provide empirical results on simulated and real-world datasets verifying the effectiveness of the approach in individual and group-fairness settings. |
| Tasks | Learning-To-Rank |
| Published | 2019-02-11 |
| URL | https://arxiv.org/abs/1902.04056v2 |
| https://arxiv.org/pdf/1902.04056v2.pdf | |
| PWC | https://paperswithcode.com/paper/policy-learning-for-fairness-in-ranking |
| Repo | |
| Framework | |
CEREBRUM: a fast and fully-volumetric Convolutional Encoder-decodeR for weakly-supervised sEgmentation of BRain strUctures from out-of-the-scanner MRI
| Title | CEREBRUM: a fast and fully-volumetric Convolutional Encoder-decodeR for weakly-supervised sEgmentation of BRain strUctures from out-of-the-scanner MRI |
| Authors | Dennis Bontempi, Sergio Benini, Alberto Signoroni, Michele Svanera, Lars Muckli |
| Abstract | Many functional and structural neuroimaging studies call for accurate morphometric segmentation of different brain structures starting from image intensity values of MRI scans. Current automatic (multi-) atlas-based segmentation strategies often lack accuracy on difficult-to-segment brain structures and, since these methods rely on atlas-to-scan alignment, they may take long processing times. Recently, methods deploying solutions based on Convolutional Neural Networks (CNNs) are making the direct analysis of out-of-the-scanner data feasible. However, current CNN-based solutions partition the test volume into 2D or 3D patches, which are processed independently. This entails a loss of global contextual information thereby negatively impacting the segmentation accuracy. In this work, we design and test an optimised end-to-end CNN architecture that makes the exploitation of global spatial information computationally tractable, allowing to process a whole MRI volume at once. We adopt a weakly supervised learning strategy by exploiting a large dataset composed by 947 out-of-the-scanner (3 Tesla T1-weighted 1mm isotropic MP-RAGE 3D sequences) MR Images. The resulting model is able to produce accurate multi-structure segmentation results in only few seconds. Different quantitative measures demonstrate an improved accuracy of our solution when compared to state-of-the-art techniques. Moreover, through a randomised survey involving expert neuroscientists, we show that subjective judgements clearly prefer our solution with respect to the widely adopted atlas-based FreeSurfer software. |
| Tasks | |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.05085v2 |
| https://arxiv.org/pdf/1909.05085v2.pdf | |
| PWC | https://paperswithcode.com/paper/cerebrum-a-convolutional-encoder-decoder-for |
| Repo | |
| Framework | |
Half a Percent of Labels is Enough: Efficient Animal Detection in UAV Imagery using Deep CNNs and Active Learning
| Title | Half a Percent of Labels is Enough: Efficient Animal Detection in UAV Imagery using Deep CNNs and Active Learning |
| Authors | Benjamin Kellenberger, Diego Marcos, Sylvain Lobry, Devis Tuia |
| Abstract | We present an Active Learning (AL) strategy for re-using a deep Convolutional Neural Network (CNN)-based object detector on a new dataset. This is of particular interest for wildlife conservation: given a set of images acquired with an Unmanned Aerial Vehicle (UAV) and manually labeled gound truth, our goal is to train an animal detector that can be re-used for repeated acquisitions, e.g. in follow-up years. Domain shifts between datasets typically prevent such a direct model application. We thus propose to bridge this gap using AL and introduce a new criterion called Transfer Sampling (TS). TS uses Optimal Transport to find corresponding regions between the source and the target datasets in the space of CNN activations. The CNN scores in the source dataset are used to rank the samples according to their likelihood of being animals, and this ranking is transferred to the target dataset. Unlike conventional AL criteria that exploit model uncertainty, TS focuses on very confident samples, thus allowing a quick retrieval of true positives in the target dataset, where positives are typically extremely rare and difficult to find by visual inspection. We extend TS with a new window cropping strategy that further accelerates sample retrieval. Our experiments show that with both strategies combined, less than half a percent of oracle-provided labels are enough to find almost 80% of the animals in challenging sets of UAV images, beating all baselines by a margin. |
| Tasks | Active Learning |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.07319v1 |
| https://arxiv.org/pdf/1907.07319v1.pdf | |
| PWC | https://paperswithcode.com/paper/half-a-percent-of-labels-is-enough-efficient |
| Repo | |
| Framework | |
Natural Image Manipulation for Autoregressive Models Using Fisher Scores
| Title | Natural Image Manipulation for Autoregressive Models Using Fisher Scores |
| Authors | Wilson Yan, Jonathan Ho, Pieter Abbeel |
| Abstract | Deep autoregressive models are one of the most powerful models that exist today which achieve state-of-the-art bits per dim. However, they lie at a strict disadvantage when it comes to controlled sample generation compared to latent variable models. Latent variable models such as VAEs and normalizing flows allow meaningful semantic manipulations in latent space, which autoregressive models do not have. In this paper, we propose using Fisher scores as a method to extract embeddings from an autoregressive model to use for interpolation and show that our method provides more meaningful sample manipulation compared to alternate embeddings such as network activations. |
| Tasks | Latent Variable Models |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1912.05015v1 |
| https://arxiv.org/pdf/1912.05015v1.pdf | |
| PWC | https://paperswithcode.com/paper/natural-image-manipulation-for-autoregressive |
| Repo | |
| Framework | |
The Use of Deep Learning for Symbolic Integration: A Review of (Lample and Charton, 2019)
| Title | The Use of Deep Learning for Symbolic Integration: A Review of (Lample and Charton, 2019) |
| Authors | Ernest Davis |
| Abstract | Lample and Charton (2019) describe a system that uses deep learning technology to compute symbolic, indefinite integrals, and to find symbolic solutions to first- and second-order ordinary differential equations, when the solutions are elementary functions. They found that, over a particular test set, the system could find solutions more successfully than sophisticated packages for symbolic mathematics such as Mathematica run with a long time-out. This is an impressive accomplishment, as far as it goes. However, the system can handle only a quite limited subset of the problems that Mathematica deals with, and the test set has significant built-in biases. Therefore the claim that this outperforms Mathematica on symbolic integration needs to be very much qualified. |
| Tasks | |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.05752v2 |
| https://arxiv.org/pdf/1912.05752v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-use-of-deep-learning-for-symbolic |
| Repo | |
| Framework | |
Using Structured Input and Modularity for Improved Learning
| Title | Using Structured Input and Modularity for Improved Learning |
| Authors | Zehra Sura, Tong Chen, Hyojin Sung |
| Abstract | We describe a method for utilizing the known structure of input data to make learning more efficient. Our work is in the domain of programming languages, and we use deep neural networks to do program analysis. Computer programs include a lot of structural information (such as loop nests, conditional blocks, and data scopes), which is pertinent to program analysis. In this case, the neural network has to learn to recognize the structure, and also learn the target function for the problem. However, the structural information in this domain is readily accessible to software with the availability of compiler tools and parsers for well-defined programming languages. Our method for utilizing the known structure of input data includes: (1) pre-processing the input data to expose relevant structures, and (2) constructing neural networks by incorporating the structure of the input data as an integral part of the network design. The method has the effect of modularizing the neural network which helps break down complexity, and results in more efficient training of the overall network. We apply this method to an example code analysis problem, and show that it can achieve higher accuracy with a smaller network size and fewer training examples. Further, the method is robust, performing equally well on input data with different distributions. |
| Tasks | |
| Published | 2019-03-29 |
| URL | http://arxiv.org/abs/1903.12366v1 |
| http://arxiv.org/pdf/1903.12366v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-structured-input-and-modularity-for |
| Repo | |
| Framework | |
Distillation Strategies for Proximal Policy Optimization
| Title | Distillation Strategies for Proximal Policy Optimization |
| Authors | Sam Green, Craig M. Vineyard, Çetin Kaya Koç |
| Abstract | Vision-based deep reinforcement learning (RL) typically obtains performance benefit by using high capacity and relatively large convolutional neural networks (CNN). However, a large network leads to higher inference costs (power, latency, silicon area, MAC count). Many inference optimizations have been developed for CNNs. Some optimization techniques offer theoretical efficiency, such as sparsity, but designing actual hardware to support them is difficult. On the other hand, distillation is a simple general-purpose optimization technique which is broadly applicable for transferring knowledge from a trained, high capacity teacher network to an untrained, low capacity student network. DQN distillation extended the original distillation idea to transfer information stored in a high performance, high capacity teacher Q-function trained via the Deep Q-Learning (DQN) algorithm. Our work adapts the DQN distillation work to the actor-critic Proximal Policy Optimization algorithm. PPO is simple to implement and has much higher performance than the seminal DQN algorithm. We show that a distilled PPO student can attain far higher performance compared to a DQN teacher. We also show that a low capacity distilled student is generally able to outperform a low capacity agent that directly trains in the environment. Finally, we show that distillation, followed by “fine-tuning” in the environment, enables the distilled PPO student to achieve parity with teacher performance. In general, the lessons learned in this work should transfer to other modern actor-critic RL algorithms. |
| Tasks | Q-Learning |
| Published | 2019-01-23 |
| URL | http://arxiv.org/abs/1901.08128v2 |
| http://arxiv.org/pdf/1901.08128v2.pdf | |
| PWC | https://paperswithcode.com/paper/distillation-strategies-for-proximal-policy |
| Repo | |
| Framework | |
Removable and/or Repeated Units Emerge in Overparametrized Deep Neural Networks
| Title | Removable and/or Repeated Units Emerge in Overparametrized Deep Neural Networks |
| Authors | Stephen Casper, Xavier Boix, Vanessa D’Amario, Ling Guo, Martin Schrimpf, Kasper Vinken, Gabriel Kreiman |
| Abstract | Deep neural networks (DNNs) perform well on a variety of tasks despite the fact that most networks used in practice are vastly overparametrized and even capable of perfectly fitting randomly labeled data. Recent evidence suggests that developing compressible representations is key for adjusting the complexity of overparametrized networks to the task at hand. In this paper, we provide new empirical evidence that supports this hypothesis by identifying two types of units that emerge when the network’s width is increased: removable units which can be dropped out of the network without significant change to the output and repeated units whose activities are highly correlated with other units. The emergence of these units implies capacity constraints as the function the network represents could be expressed by a smaller network without these units. In a series of experiments with AlexNet, ResNet and Inception networks in the CIFAR-10 and ImageNet datasets, and also using shallow networks with synthetic data, we show that DNNs consistently increase either the number of removable units, repeated units, or both at greater widths for a comprehensive set of hyperparameters. These results suggest that the mechanisms by which networks in the deep learning regime adjust their complexity operate at the unit level and highlight the need for additional research into what drives the emergence of such units. |
| Tasks | |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04783v2 |
| https://arxiv.org/pdf/1912.04783v2.pdf | |
| PWC | https://paperswithcode.com/paper/removable-andor-repeated-units-emerge-in |
| Repo | |
| Framework | |
3D Particle Positions from Computer Stereo Vision in PK-4
| Title | 3D Particle Positions from Computer Stereo Vision in PK-4 |
| Authors | Daniel P. Mohr, Peter Huber, Mierk Schwabe, Christina A. Knapek |
| Abstract | Complex plasmas consist of microparticles embedded in a low-temperature plasma containing ions, electrons and neutral particles. The microparticles form a dynamical system that can be used to study a multitude of effects on the level of the constituent particles. The microparticles are usually illuminated with a sheet of laser light, and the scattered light can be observed with digital cameras. Some complex plasma microgravity research facilities use two cameras with an overlapping field of view. An overlapping field of view can be used to combine the resulting images into one and trace the particles in the larger field of view. In previous work this was discussed for the images recorded by the PK-4 Laboratory on board the International Space Station. In that work the width of the laser sheet was, however, not taken into account. In this paper, we will discuss how to improve the transformation of the features into a joint coordinate system, and possibly extract information on the 3D position of particles in the overlap region. |
| Tasks | |
| Published | 2019-12-09 |
| URL | https://arxiv.org/abs/1912.04333v1 |
| https://arxiv.org/pdf/1912.04333v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-particle-positions-from-computer-stereo |
| Repo | |
| Framework | |
