January 31, 2020

3357 words 16 mins read

Paper Group AWR 449

Chameleon: Learning Model Initializations Across Tasks With Different Schemas. Multi-Label Image Recognition with Graph Convolutional Networks. Similarity Learning for Authorship Verification in Social Media. ELF: Embedded Localisation of Features in pre-trained CNN. WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia. …

Chameleon: Learning Model Initializations Across Tasks With Different Schemas


Title	Chameleon: Learning Model Initializations Across Tasks With Different Schemas
Authors	Lukas Brinkmeyer, Rafael Rego Drumond, Randolf Scholz, Josif Grabocka, Lars Schmidt-Thieme
Abstract	Parametric models, and particularly neural networks, require weight initialization as a starting point for gradient-based optimization. Recent work shows that a specific initial parameter set can be learned from a population of supervised learning tasks. Using this initial parameter set leads to faster convergence for new tasks (model-agnostic meta-learning). Currently, methods for learning model initializations are limited to a population of tasks sharing the same schema, i.e., the same number, order, type and semantics of predictor and target variables. In this paper, we address the problem of meta-learning parameter initialization across tasks with different schemas, i.e., if the number of predictors varies across tasks, while they still share some variables. We propose Chameleon, a model that learns to align different predictor schemas to a common representation. In experiments on 26 data sets of the OpenML-CC18 benchmark, we show that Chameleon successfully can learn parameter initializations across tasks with different schemas.
Tasks	Meta-Learning
Published	2019-09-30
URL	https://arxiv.org/abs/1909.13576v3
PDF	https://arxiv.org/pdf/1909.13576v3.pdf
PWC	https://paperswithcode.com/paper/chameleon-learning-model-initializations
Repo	https://github.com/radrumond/Chameleon
Framework	tf

Multi-Label Image Recognition with Graph Convolutional Networks


Title	Multi-Label Image Recognition with Graph Convolutional Networks
Authors	Zhao-Min Chen, Xiu-Shen Wei, Peng Wang, Yanwen Guo
Abstract	The task of multi-label image recognition is to predict a set of object labels that present in an image. As objects normally co-occur in an image, it is desirable to model the label dependencies to improve the recognition performance. To capture and explore such important dependencies, we propose a multi-label classification model based on Graph Convolutional Network (GCN). The model builds a directed graph over the object labels, where each node (label) is represented by word embeddings of a label, and GCN is learned to map this label graph into a set of inter-dependent object classifiers. These classifiers are applied to the image descriptors extracted by another sub-net, enabling the whole network to be end-to-end trainable. Furthermore, we propose a novel re-weighted scheme to create an effective label correlation matrix to guide information propagation among the nodes in GCN. Experiments on two multi-label image recognition datasets show that our approach obviously outperforms other existing state-of-the-art methods. In addition, visualization analyses reveal that the classifiers learned by our model maintain meaningful semantic topology.
Tasks	Multi-Label Classification, Word Embeddings
Published	2019-04-07
URL	http://arxiv.org/abs/1904.03582v1
PDF	http://arxiv.org/pdf/1904.03582v1.pdf
PWC	https://paperswithcode.com/paper/multi-label-image-recognition-with-graph
Repo	https://github.com/sonvx/upsanddowns_www16
Framework	none


Title	Similarity Learning for Authorship Verification in Social Media
Authors	Benedikt Boenninghoff, Robert M. Nickel, Steffen Zeiler, Dorothea Kolossa
Abstract	Authorship verification tries to answer the question if two documents with unknown authors were written by the same author or not. A range of successful technical approaches has been proposed for this task, many of which are based on traditional linguistic features such as n-grams. These algorithms achieve good results for certain types of written documents like books and novels. Forensic authorship verification for social media, however, is a much more challenging task since messages tend to be relatively short, with a large variety of different genres and topics. At this point, traditional methods based on features like n-grams have had limited success. In this work, we propose a new neural network topology for similarity learning that significantly improves the performance on the author verification task with such challenging data sets.
Tasks
Published	2019-08-20
URL	https://arxiv.org/abs/1908.07844v1
PDF	https://arxiv.org/pdf/1908.07844v1.pdf
PWC	https://paperswithcode.com/paper/190807844
Repo	https://github.com/boenninghoff/AdHominem
Framework	tf

ELF: Embedded Localisation of Features in pre-trained CNN


Title	ELF: Embedded Localisation of Features in pre-trained CNN
Authors	Assia Benbihi, Matthieu Geist, Cédric Pradalier
Abstract	This paper introduces a novel feature detector based only on information embedded inside a CNN trained on standard tasks (e.g. classification). While previous works already show that the features of a trained CNN are suitable descriptors, we show here how to extract the feature locations from the network to build a detector. This information is computed from the gradient of the feature map with respect to the input image. This provides a saliency map with local maxima on relevant keypoint locations. Contrary to recent CNN-based detectors, this method requires neither supervised training nor finetuning. We evaluate how repeatable and how matchable the detected keypoints are with the repeatability and matching scores. Matchability is measured with a simple descriptor introduced for the sake of the evaluation. This novel detector reaches similar performances on the standard evaluation HPatches dataset, as well as comparable robustness against illumination and viewpoint changes on Webcam and photo-tourism images. These results show that a CNN trained on a standard task embeds feature location information that is as relevant as when the CNN is specifically trained for feature detection.
Tasks
Published	2019-07-07
URL	https://arxiv.org/abs/1907.03261v1
PDF	https://arxiv.org/pdf/1907.03261v1.pdf
PWC	https://paperswithcode.com/paper/elf-embedded-localisation-of-features-in-pre
Repo	https://github.com/ELF-det/elf
Framework	none

WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia


Title	WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia
Authors	Holger Schwenk, Vishrav Chaudhary, Shuo Sun, Hongyu Gong, Francisco Guzmán
Abstract	We present an approach based on multilingual sentence embeddings to automatically extract parallel sentences from the content of Wikipedia articles in 85 languages, including several dialects or low-resource languages. We do not limit the the extraction process to alignments with English, but systematically consider all possible language pairs. In total, we are able to extract 135M parallel sentences for 1620 different language pairs, out of which only 34M are aligned with English. This corpus of parallel sentences is freely available at https://github.com/facebookresearch/LASER/tree/master/tasks/WikiMatrix. To get an indication on the quality of the extracted bitexts, we train neural MT baseline systems on the mined data only for 1886 languages pairs, and evaluate them on the TED corpus, achieving strong BLEU scores for many language pairs. The WikiMatrix bitexts seem to be particularly interesting to train MT systems between distant languages without the need to pivot through English.
Tasks	Sentence Embeddings
Published	2019-07-10
URL	https://arxiv.org/abs/1907.05791v2
PDF	https://arxiv.org/pdf/1907.05791v2.pdf
PWC	https://paperswithcode.com/paper/wikimatrix-mining-135m-parallel-sentences-in
Repo	https://github.com/jrfilocao/LASER-Thesis
Framework	pytorch

Unsupervised Deep Learning for Bayesian Brain MRI Segmentation


Title	Unsupervised Deep Learning for Bayesian Brain MRI Segmentation
Authors	Adrian V. Dalca, Evan Yu, Polina Golland, Bruce Fischl, Mert R. Sabuncu, Juan Eugenio Iglesias
Abstract	Probabilistic atlas priors have been commonly used to derive adaptive and robust brain MRI segmentation algorithms. Widely-used neuroimage analysis pipelines rely heavily on these techniques, which are often computationally expensive. In contrast, there has been a recent surge of approaches that leverage deep learning to implement segmentation tools that are computationally efficient at test time. However, most of these strategies rely on learning from manually annotated images. These supervised deep learning methods are therefore sensitive to the intensity profiles in the training dataset. To develop a deep learning-based segmentation model for a new image dataset (e.g., of different contrast), one usually needs to create a new labeled training dataset, which can be prohibitively expensive, or rely on suboptimal ad hoc adaptation or augmentation approaches. In this paper, we propose an alternative strategy that combines a conventional probabilistic atlas-based segmentation with deep learning, enabling one to train a segmentation model for new MRI scans without the need for any manually segmented images. Our experiments include thousands of brain MRI scans and demonstrate that the proposed method achieves good accuracy for a brain MRI segmentation task for different MRI contrasts, requiring only approximately 15 seconds at test time on a GPU. The code is freely available at http://voxelmorph.mit.edu.
Tasks	Brain Image Segmentation, Brain Segmentation, Few-Shot Semantic Segmentation, Image Registration, Zero Shot Segmentation
Published	2019-04-25
URL	https://arxiv.org/abs/1904.11319v2
PDF	https://arxiv.org/pdf/1904.11319v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-deep-learning-for-bayesian-brain
Repo	https://github.com/voxelmorph/voxelmorph
Framework	tf


Title	Garbage In, Garbage Out? Do Machine Learning Application Papers in Social Computing Report Where Human-Labeled Training Data Comes From?
Authors	R. Stuart Geiger, Kevin Yu, Yanlai Yang, Mindy Dai, Jie Qiu, Rebekah Tang, Jenny Huang
Abstract	Many machine learning projects for new application areas involve teams of humans who label data for a particular purpose, from hiring crowdworkers to the paper’s authors labeling the data themselves. Such a task is quite similar to (or a form of) structured content analysis, which is a longstanding methodology in the social sciences and humanities, with many established best practices. In this paper, we investigate to what extent a sample of machine learning application papers in social computing — specifically papers from ArXiv and traditional publications performing an ML classification task on Twitter data — give specific details about whether such best practices were followed. Our team conducted multiple rounds of structured content analysis of each paper, making determinations such as: Does the paper report who the labelers were, what their qualifications were, whether they independently labeled the same items, whether inter-rater reliability metrics were disclosed, what level of training and/or instructions were given to labelers, whether compensation for crowdworkers is disclosed, and if the training data is publicly available. We find a wide divergence in whether such practices were followed and documented. Much of machine learning research and education focuses on what is done once a “gold standard” of training data is available, but we discuss issues around the equally-important aspect of whether such data is reliable in the first place.
Tasks
Published	2019-12-17
URL	https://arxiv.org/abs/1912.08320v1
PDF	https://arxiv.org/pdf/1912.08320v1.pdf
PWC	https://paperswithcode.com/paper/garbage-in-garbage-out-do-machine-learning
Repo	https://github.com/staeiou/gigo-fat2020
Framework	none

The PGM-index: a multicriteria, compressed and learned approach to data indexing


Title	The PGM-index: a multicriteria, compressed and learned approach to data indexing
Authors	Paolo Ferragina, Giorgio Vinciguerra
Abstract	The recent introduction of learned indexes has shaken the foundations of the decades-old field of indexing data structures. Combining, or even replacing, classic design elements such as B-tree nodes with machine learning models has proven to give outstanding improvements in the space footprint and time efficiency of data systems. However, these novel approaches are based on heuristics, thus they lack any guarantees both in their time and space requirements. We propose the Piecewise Geometric Model index (shortly, PGM-index), which achieves guaranteed I/O-optimality in query operations, learns an optimal number of linear models, and its peculiar recursive construction makes it a purely learned data structure, rather than a hybrid of traditional and learned indexes (such as RMI and FITing-tree). We show that the PGM-index improves the space of the FITing-tree by 63.3% and of the B-tree by more than four orders of magnitude, while achieving their same or even better query time efficiency. We complement this result by proposing three variants of the PGM-index. First, we design a compressed PGM-index that further reduces its space footprint by exploiting the repetitiveness at the level of the learned linear models it is composed of. Second, we design a PGM-index that adapts itself to the distribution of the queries, thus resulting in the first known distribution-aware learned index to date. Finally, given its flexibility in the offered space-time trade-offs, we propose the multicriteria PGM-index that efficiently auto-tune itself in a few seconds over hundreds of millions of keys to the possibly evolving space-time constraints imposed by the application of use. We remark to the reader that this paper is an extended and improved version of our previous paper titled “Superseding traditional indexes by orchestrating learning and geometry” (arXiv:1903.00507).
Tasks
Published	2019-10-14
URL	https://arxiv.org/abs/1910.06169v1
PDF	https://arxiv.org/pdf/1910.06169v1.pdf
PWC	https://paperswithcode.com/paper/the-pgm-index-a-multicriteria-compressed-and
Repo	https://github.com/gvinciguerra/PGM-index
Framework	none

BasketballGAN: Generating Basketball Play Simulation Through Sketching


Title	BasketballGAN: Generating Basketball Play Simulation Through Sketching
Authors	Hsin-Ying Hsieh, Chieh-Yu Chen, Yu-Shuen Wang, Jung-Hong Chuang
Abstract	We present a data-driven basketball set play simulation. Given an offensive set play sketch, our method simulates potential scenarios that may occur in the game. The simulation provides coaches and players with insights on how a given set play can be executed. To achieve the goal, we train a conditional adversarial network on NBA movement data to imitate the behaviors of how players move around the court through two major components: a generator that learns to generate natural player movements based on a latent noise and a user sketched set play; and a discriminator that is used to evaluate the realism of the basketball play. To improve the quality of simulation, we minimize 1.) a dribbler loss to prevent the ball from drifting away from the dribbler; 2.) a defender loss to prevent the dribbler from not being defended; 3.) a ball passing loss to ensure the straightness of passing trajectories; and 4) an acceleration loss to minimize unnecessary players’ movements. To evaluate our system, we objectively compared real and simulated basketball set plays. Besides, a subjective test was conducted to judge whether a set play was real or generated by our network. On average, the mean correct rates to the binary tests were 56.17 %. Experiment results and the evaluations demonstrated the effectiveness of our system.
Tasks
Published	2019-09-16
URL	https://arxiv.org/abs/1909.07088v2
PDF	https://arxiv.org/pdf/1909.07088v2.pdf
PWC	https://paperswithcode.com/paper/basketballgan-generating-basketball-play
Repo	https://github.com/chychen/BasketballGAN
Framework	tf

No-Regret Learning in Unknown Games with Correlated Payoffs


Title	No-Regret Learning in Unknown Games with Correlated Payoffs
Authors	Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour, Andreas Krause
Abstract	We consider the problem of learning to play a repeated multi-agent game with an unknown reward function. Single player online learning algorithms attain strong regret bounds when provided with full information feedback, which unfortunately is unavailable in many real-world scenarios. Bandit feedback alone, i.e., observing outcomes only for the selected action, yields substantially worse performance. In this paper, we consider a natural model where, besides a noisy measurement of the obtained reward, the player can also observe the opponents’ actions. This feedback model, together with a regularity assumption on the reward function, allows us to exploit the correlations among different game outcomes by means of Gaussian processes (GPs). We propose a novel confidence-bound based bandit algorithm GP-MW, which utilizes the GP model for the reward function and runs a multiplicative weight (MW) method. We obtain novel kernel-dependent regret bounds that are comparable to the known bounds in the full information setting, while substantially improving upon the existing bandit results. We experimentally demonstrate the effectiveness of GP-MW in random matrix games, as well as real-world problems of traffic routing and movie recommendation. In our experiments, GP-MW consistently outperforms several baselines, while its performance is often comparable to methods that have access to full information feedback.
Tasks	Gaussian Processes
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08540v2
PDF	https://arxiv.org/pdf/1909.08540v2.pdf
PWC	https://paperswithcode.com/paper/no-regret-learning-in-unknown-games-with
Repo	https://github.com/sessap/noregretgames
Framework	none

MMED: A Multi-domain and Multi-modality Event Dataset


Title	MMED: A Multi-domain and Multi-modality Event Dataset
Authors	Zhenguo Yang, Zehang Lin, Min Cheng, Qing Li, Wenyin Liu
Abstract	In this work, we construct and release a multi-domain and multi-modality event dataset (MMED), containing 25,165 textual news articles collected from hundreds of news media sites (e.g., Yahoo News, Google News, CNN News.) and 76,516 image posts shared on Flickr social media, which are annotated according to 412 real-world events. The dataset is collected to explore the problem of organizing heterogeneous data contributed by professionals and amateurs in different data domains, and the problem of transferring event knowledge obtained from one data domain to heterogeneous data domain, thus summarizing the data with different contributors. We hope that the release of the MMED dataset can stimulate innovate research on related challenging problems, such as event discovery, cross-modal (event) retrieval, and visual question answering, etc.
Tasks	Question Answering, Visual Question Answering
Published	2019-04-04
URL	http://arxiv.org/abs/1904.02354v2
PDF	http://arxiv.org/pdf/1904.02354v2.pdf
PWC	https://paperswithcode.com/paper/mmed-a-multi-domain-and-multi-modality-event
Repo	https://github.com/zhengyang5/ACM-MMSys19-MMED400
Framework	none

Computing Tight Differential Privacy Guarantees Using FFT


Title	Computing Tight Differential Privacy Guarantees Using FFT
Authors	Antti Koskela, Joonas Jälkö, Antti Honkela
Abstract	Differentially private (DP) machine learning has recently become popular. The privacy loss of DP algorithms is commonly reported using $(\varepsilon,\delta)$-DP. In this paper, we propose a numerical accountant for evaluating the privacy loss for algorithms with continuous one dimensional output. This accountant can be applied to the subsampled multidimensional Gaussian mechanism which underlies the popular DP stochastic gradient descent. The proposed method is based on a numerical approximation of an integral formula which gives the exact $(\varepsilon,\delta)$-values. The approximation is carried out by discretising the integral and by evaluating discrete convolutions using the fast Fourier transform algorithm. We give both theoretical error bounds and numerical error estimates for the approximation. Experimental comparisons with state-of-the-art techniques demonstrate significant improvements in bound tightness and/or computation time. Python code for the method can be found in Github (https://github.com/DPBayes/PLD-Accountant/).
Tasks
Published	2019-06-07
URL	https://arxiv.org/abs/1906.03049v2
PDF	https://arxiv.org/pdf/1906.03049v2.pdf
PWC	https://paperswithcode.com/paper/computing-exact-guarantees-for-differential
Repo	https://github.com/DPBayes/PLD-Accountant
Framework	none

Artist Style Transfer Via Quadratic Potential


Title	Artist Style Transfer Via Quadratic Potential
Authors	Rahul Bhalley, Jianlin Su
Abstract	In this paper we address the problem of artist style transfer where the painting style of a given artist is applied on a real world photograph. We train our neural networks in adversarial setting via recently introduced quadratic potential divergence for stable learning process. To further improve the quality of generated artist stylized images we also integrate some of the recently introduced deep learning techniques in our method. To our best knowledge this is the first attempt towards artist style transfer via quadratic potential divergence. We provide some stylized image samples in the supplementary material. The source code for experimentation was written in PyTorch and is available online in my GitHub repository.
Tasks	Style Transfer
Published	2019-02-14
URL	http://arxiv.org/abs/1902.11108v2
PDF	http://arxiv.org/pdf/1902.11108v2.pdf
PWC	https://paperswithcode.com/paper/artist-style-transfer-via-quadratic-potential
Repo	https://github.com/rahulbhalley/cyclegan-qp
Framework	pytorch

SkyNet: A Champion Model for DAC-SDC on Low Power Object Detection


Title	SkyNet: A Champion Model for DAC-SDC on Low Power Object Detection
Authors	Xiaofan Zhang, Cong Hao, Haoming Lu, Jiachen Li, Yuhong Li, Yuchen Fan, Kyle Rupnow, Jinjun Xiong, Thomas Huang, Honghui Shi, Wen-mei Hwu, Deming Chen
Abstract	Developing artificial intelligence (AI) at the edge is always challenging, since edge devices have limited computation capability and memory resources but need to meet demanding requirements, such as real-time processing, high throughput performance, and high inference accuracy. To overcome these challenges, we propose SkyNet, an extremely lightweight DNN with 12 convolutional (Conv) layers and only 1.82 megabyte (MB) of parameters following a bottom-up DNN design approach. SkyNet is demonstrated in the 56th IEEE/ACM Design Automation Conference System Design Contest (DAC-SDC), a low power object detection challenge in images captured by unmanned aerial vehicles (UAVs). SkyNet won the first place award for both the GPU and FPGA tracks of the contest: we deliver 0.731 Intersection over Union (IoU) and 67.33 frames per second (FPS) on a TX2 GPU and deliver 0.716 IoU and 25.05 FPS on an Ultra96 FPGA.
Tasks	Object Detection
Published	2019-06-25
URL	https://arxiv.org/abs/1906.10327v2
PDF	https://arxiv.org/pdf/1906.10327v2.pdf
PWC	https://paperswithcode.com/paper/skynet-a-champion-model-for-dac-sdc-on-low
Repo	https://github.com/TomG008/SkyNet
Framework	pytorch

Cross-Batch Memory for Embedding Learning


Title	Cross-Batch Memory for Embedding Learning
Authors	Xun Wang, Haozhi Zhang, Weilin Huang, Matthew R. Scott
Abstract	Mining informative negative instances are of central importance to deep metric learning (DML). However, the hard-mining ability of existing DML methods is intrinsically limited by mini-batch training, where only a mini-batch of instances are accessible at each iteration. In this paper, we identify a {“slow drift”} phenomena by observing that the embedding features drift exceptionally slow even as the model parameters are updating throughout the training process. It suggests that the features of instances computed at preceding iterations can considerably approximate to their features extracted by current model. We propose a cross-batch memory (XBM) mechanism that memorizes the embeddings of past iterations, allowing the model to collect sufficient hard negative pairs across multiple mini-batches - even over the whole dataset. Our XBM can be directly integrated into general pair-based DML framework. We demonstrate that, without bells and whistles, XBM augmented DML can boost the performance considerably on image retrieval. In particular, with XBM, a simple contrastive loss can have large R@1 improvements of 12%-22.5% on three large-scale datasets, easily surpassing the most sophisticated state-of-the-art methods by a large margin. Our XBM is conceptually simple, easy to implement - using several lines of codes, and is memory efficient - with a negligible 0.2 GB extra GPU memory.
Tasks	Image Retrieval, Metric Learning
Published	2019-12-14
URL	https://arxiv.org/abs/1912.06798v2
PDF	https://arxiv.org/pdf/1912.06798v2.pdf
PWC	https://paperswithcode.com/paper/cross-batch-memory-for-embedding-learning
Repo	https://github.com/bnu-wangxun/Deep_Metric
Framework	pytorch