Paper Group NANR 277
Flow Guided Recurrent Neural Encoder for Video Salient Object Detection. Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection. A Spline Theory of Deep Learning. The MADAR Arabic Dialect Corpus and Lexicon. Unsupervised Adversarial Anomaly Detection using One-Class Support Vector Machines. Optimal Structured …
Flow Guided Recurrent Neural Encoder for Video Salient Object Detection
| Title | Flow Guided Recurrent Neural Encoder for Video Salient Object Detection |
| Authors | Guanbin Li, Yuan Xie, Tianhao Wei, Keze Wang, Liang Lin |
| Abstract | Image saliency detection has recently witnessed significant progress due to deep convolutional neural networks. However, extending state-of-the-art saliency detectors from image to video is challenging. The performance of salient object detection suffers from object or camera motion and the dramatic change of the appearance contrast in videos. In this paper, we present flow guided recurrent neural encoder(FGRNE), an accurate and end-to-end learning framework for video salient object detection. It works by enhancing the temporal coherence of the per-frame feature by exploiting both motion information in terms of optical flow and sequential feature evolution encoding in terms of LSTM networks. It can be considered as a universal framework to extend any FCN based static saliency detector to video salient object detection. Intensive experimental results verify the effectiveness of each part of FGRNE and confirm that our proposed method significantly outperforms state-of-the-art methods on the public benchmarks of DAVIS and FBMS. |
| Tasks | Object Detection, Optical Flow Estimation, Saliency Detection, Salient Object Detection, Video Salient Object Detection |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Li_Flow_Guided_Recurrent_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Flow_Guided_Recurrent_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/flow-guided-recurrent-neural-encoder-for |
| Repo | |
| Framework | |
Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection
| Title | Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection |
| Authors | Taylor Mordan, Nicolas Thome, Gilles Henaff, Matthieu Cord |
| Abstract | Multi-Task Learning (MTL) is appealing for deep learning regularization. In this paper, we tackle a specific MTL context denoted as primary MTL, where the ultimate goal is to improve the performance of a given primary task by leveraging several other auxiliary tasks. Our main methodological contribution is to introduce ROCK, a new generic multi-modal fusion block for deep learning tailored to the primary MTL context. ROCK architecture is based on a residual connection, which makes forward prediction explicitly impacted by the intermediate auxiliary representations. The auxiliary predictor’s architecture is also specifically designed to our primary MTL context, by incorporating intensive pooling operators for maximizing complementarity of intermediate representations. Extensive experiments on NYUv2 dataset (object detection with scene classification, depth prediction, and surface normal estimation as auxiliary tasks) validate the relevance of the approach and its superiority to flat MTL approaches. Our method outperforms state-of-the-art object detection models on NYUv2 dataset by a large margin, and is also able to handle large-scale heterogeneous inputs (real and synthetic images) with missing annotation modalities. |
| Tasks | Depth Estimation, Multi-Task Learning, Object Detection, Scene Classification |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7406-revisiting-multi-task-learning-with-rock-a-deep-residual-auxiliary-block-for-visual-detection |
| http://papers.nips.cc/paper/7406-revisiting-multi-task-learning-with-rock-a-deep-residual-auxiliary-block-for-visual-detection.pdf | |
| PWC | https://paperswithcode.com/paper/revisiting-multi-task-learning-with-rock-a |
| Repo | |
| Framework | |
A Spline Theory of Deep Learning
| Title | A Spline Theory of Deep Learning |
| Authors | Randall Balestriero, baraniuk |
| Abstract | We build a rigorous bridge between deep networks (DNs) and approximation theory via spline functions and operators. Our key result is that a large class of DNs can be written as a composition of max-affine spline operators (MASOs), which provide a powerful portal through which to view and analyze their inner workings. For instance, conditioned on the input signal, the output of a MASO DN can be written as a simple affine transformation of the input. This implies that a DN constructs a set of signal-dependent, class-specific templates against which the signal is compared via a simple inner product; we explore the links to the classical theory of optimal classification via matched filters and the effects of data memorization. Going further, we propose a simple penalty term that can be added to the cost function of any DN learning algorithm to force the templates to be orthogonal with each other; this leads to significantly improved classification performance and reduced overfitting with no change to the DN architecture. The spline partition of the input signal space opens up a new geometric avenue to study how DNs organize signals in a hierarchical fashion. As an application, we develop and validate a new distance metric for signals that quantifies the difference between their partition encodings. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2302 |
| http://proceedings.mlr.press/v80/balestriero18b/balestriero18b.pdf | |
| PWC | https://paperswithcode.com/paper/a-spline-theory-of-deep-learning |
| Repo | |
| Framework | |
The MADAR Arabic Dialect Corpus and Lexicon
| Title | The MADAR Arabic Dialect Corpus and Lexicon |
| Authors | Houda Bouamor, Nizar Habash, Mohammad Salameh, Wajdi Zaghouani, Owen Rambow, Dana Abdulrahim, Ossama Obeid, Salam Khalifa, Fadhl Eryani, Alex Erdmann, er, Kemal Oflazer |
| Abstract | |
| Tasks | Machine Translation, Transliteration |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1535/ |
| https://www.aclweb.org/anthology/L18-1535 | |
| PWC | https://paperswithcode.com/paper/the-madar-arabic-dialect-corpus-and-lexicon |
| Repo | |
| Framework | |
Unsupervised Adversarial Anomaly Detection using One-Class Support Vector Machines
| Title | Unsupervised Adversarial Anomaly Detection using One-Class Support Vector Machines |
| Authors | Prameesha Sandamal Weerasinghe, Tansu Alpcan, Sarah Monazam Erfani, Christopher Leckie |
| Abstract | Anomaly detection discovers regular patterns in unlabeled data and identifies the non-conforming data points, which in some cases are the result of malicious attacks by adversaries. Learners such as One-Class Support Vector Machines (OCSVMs) have been successfully in anomaly detection, yet their performance may degrade significantly in the presence of sophisticated adversaries, who target the algorithm itself by compromising the integrity of the training data. With the rise in the use of machine learning in mission critical day-to-day activities where errors may have significant consequences, it is imperative that machine learning systems are made secure. To address this, we propose a defense mechanism that is based on a contraction of the data, and we test its effectiveness using OCSVMs. The proposed approach introduces a layer of uncertainty on top of the OCSVM learner, making it infeasible for the adversary to guess the specific configuration of the learner. We theoretically analyze the effects of adversarial perturbations on the separating margin of OCSVMs and provide empirical evidence on several benchmark datasets, which show that by carefully contracting the data in low dimensional spaces, we can successfully identify adversarial samples that would not have been identifiable in the original dimensional space. The numerical results show that the proposed method improves OCSVMs performance significantly (2-7%) |
| Tasks | Anomaly Detection |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=BJgd7m0xRZ |
| https://openreview.net/pdf?id=BJgd7m0xRZ | |
| PWC | https://paperswithcode.com/paper/unsupervised-adversarial-anomaly-detection |
| Repo | |
| Framework | |
Optimal Structured Light à La Carte
| Title | Optimal Structured Light à La Carte |
| Authors | Parsa Mirdehghan, Wenzheng Chen, Kiriakos N. Kutulakos |
| Abstract | We consider the problem of automatically generating sequences of structured-light patterns for active stereo triangulation of a static scene. Unlike existing approaches that use predetermined patterns and reconstruction algorithms tied to them, we generate patterns on the fly in response to generic specifications: number of patterns, projector-camera arrangement, workspace constraints, spatial frequency content, etc. Our pattern sequences are specifically optimized to minimize the expected rate of correspondence errors under those specifications for an unknown scene, and are coupled to a sequence-independent algorithm for per-pixel disparity estimation. To achieve this, we derive an objective function that is easy to optimize and follows from first principles within a maximum-likelihood framework. By minimizing it, we demonstrate automatic discovery of pattern sequences, in under three minutes on a laptop, that can outperform state-of-the-art triangulation techniques. |
| Tasks | Disparity Estimation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Mirdehghan_Optimal_Structured_Light_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Mirdehghan_Optimal_Structured_Light_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-structured-light-a-la-carte |
| Repo | |
| Framework | |
Light Field Intrinsics With a Deep Encoder-Decoder Network
| Title | Light Field Intrinsics With a Deep Encoder-Decoder Network |
| Authors | Anna Alperovich, Ole Johannsen, Michael Strecke, Bastian Goldluecke |
| Abstract | We present a fully convolutional autoencoder for light fields, which jointly encodes stacks of horizontal and vertical epipolar plane images through a deep network of residual layers. The complex structure of the light field is thus reduced to a comparatively low-dimensional representation, which can be decoded in a variety of ways. The different pathways of upconvolution we currently support are for disparity estimation and separation of the lightfield into diffuse and specular intrinsic components. The key idea is that we can jointly perform unsupervised training for the autoencoder path of the network, and supervised training for the other decoders. This way, we find features which are both tailored to the respective tasks and generalize well to datasets for which only example light fields are available. We provide an extensive evaluation on synthetic light field data, and show that the network yields good results on previously unseen real world data captured by a Lytro Illum camera and various gantries. |
| Tasks | Disparity Estimation, Lightfield |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Alperovich_Light_Field_Intrinsics_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Alperovich_Light_Field_Intrinsics_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/light-field-intrinsics-with-a-deep-encoder |
| Repo | |
| Framework | |
Harnessing Popularity in Social Media for Extractive Summarization of Online Conversations
| Title | Harnessing Popularity in Social Media for Extractive Summarization of Online Conversations |
| Authors | Ryuji Kano, Yasuhide Miura, Motoki Taniguchi, Yan-Ying Chen, Francine Chen, Tomoko Ohkuma |
| Abstract | We leverage a popularity measure in social media as a distant label for extractive summarization of online conversations. In social media, users can vote, share, or bookmark a post they prefer. The number of these actions is regarded as a measure of popularity. However, popularity is not determined solely by content of a post, e.g., a text or an image it contains, but is highly based on its contexts, e.g., timing, and authority. We propose Disjunctive model that computes the contribution of content and context separately. For evaluation, we build a dataset where the informativeness of comments is annotated. We evaluate the results with ranking metrics, and show that our model outperforms the baseline models which directly use popularity as a measure of informativeness. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1144/ |
| https://www.aclweb.org/anthology/D18-1144 | |
| PWC | https://paperswithcode.com/paper/harnessing-popularity-in-social-media-for |
| Repo | |
| Framework | |
Identifying Aggression and Toxicity in Comments using Capsule Network
| Title | Identifying Aggression and Toxicity in Comments using Capsule Network |
| Authors | Saurabh Srivastava, Prerna Khurana, Vartika Tewari |
| Abstract | Aggression and related activities like trolling, hate speech etc. involve toxic comments in various forms. These are common scenarios in today{'}s time and websites react by shutting down their comment sections. To tackle this, an algorithmic solution is preferred to human moderation which is slow and expensive. In this paper, we propose a single model capsule network with focal loss to achieve this task which is suitable for production environment. Our model achieves competitive results over other strong baseline methods, which show its effectiveness and that focal loss exhibits significant improvement in such cases where class imbalance is a regular issue. Additionally, we show that the problem of extensive data preprocessing, data augmentation can be tackled by capsule networks implicitly. We achieve an overall ROC AUC of 98.46 on Kaggle-toxic comment dataset and show that it beats other architectures by a good margin. As comments tend to be written in more than one language, and transliteration is a common problem, we further show that our model handles this effectively by applying our model on TRAC shared task dataset which contains comments in code-mixed Hindi-English. |
| Tasks | Data Augmentation, Transliteration, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4412/ |
| https://www.aclweb.org/anthology/W18-4412 | |
| PWC | https://paperswithcode.com/paper/identifying-aggression-and-toxicity-in |
| Repo | |
| Framework | |
Experiments on Morphological Reinflection: CoNLL-2018 Shared Task
| Title | Experiments on Morphological Reinflection: CoNLL-2018 Shared Task |
| Authors | Rishabh Jain, Anil Kumar Singh |
| Abstract | |
| Tasks | Machine Translation, Morphological Inflection |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-3005/ |
| https://www.aclweb.org/anthology/K18-3005 | |
| PWC | https://paperswithcode.com/paper/experiments-on-morphological-reinflection |
| Repo | |
| Framework | |
Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation
| Title | Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation |
| Authors | Wenqi Ren, Jiawei Zhang, Lin Ma, Jinshan Pan, Xiaochun Cao, Wangmeng Zuo, Wei Liu, Ming-Hsuan Yang |
| Abstract | In this paper, we present a deep convolutional neural network to capture the inherent properties of image degradation, which can handle different kernels and saturated pixels in a unified framework. The proposed neural network is motivated by the low-rank property of pseudo-inverse kernels. We first compute a generalized low-rank approximation for a large number of blur kernels, and then use separable filters to initialize the convolutional parameters in the network. Our analysis shows that the estimated decomposed matrices contain the most essential information of the input kernel, which ensures the proposed network to handle various blurs in a unified framework and generate high-quality deblurring results. Experimental results on benchmark datasets with noise and saturated pixels demonstrate that the proposed algorithm performs favorably against state-of-the-art methods. |
| Tasks | Deblurring |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7313-deep-non-blind-deconvolution-via-generalized-low-rank-approximation |
| http://papers.nips.cc/paper/7313-deep-non-blind-deconvolution-via-generalized-low-rank-approximation.pdf | |
| PWC | https://paperswithcode.com/paper/deep-non-blind-deconvolution-via-generalized |
| Repo | |
| Framework | |
Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings
| Title | Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings |
| Authors | Aryan Mokhtari, Hamed Hassani, Amin Karbasi |
| Abstract | In this paper, we showcase the interplay between discrete and continuous optimization in network-structured settings. We propose the first fully decentralized optimization method for a wide class of non-convex objective functions that possess a diminishing returns property. More specifically, given an arbitrary connected network and a global continuous submodular function, formed by a sum of local functions, we develop Decentralized Continuous Greedy (DCG), a message passing algorithm that converges to the tight $(1-1/e)$ approximation factor of the optimum global solution using only local computation and communication. We also provide strong convergence bounds as a function of network size and spectral characteristics of the underlying topology. Interestingly, DCG readily provides a simple recipe for decentralized discrete submodular maximization through the means of continuous relaxations. Formally, we demonstrate that by lifting the local discrete functions to continuous domains and using DCG as an interface we can develop a consensus algorithm that also achieves the tight $(1-1/e)$ approximation guarantee of the global discrete solution once a proper rounding scheme is applied. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2358 |
| http://proceedings.mlr.press/v80/mokhtari18a/mokhtari18a.pdf | |
| PWC | https://paperswithcode.com/paper/decentralized-submodular-maximization |
| Repo | |
| Framework | |
HiDE: a Tool for Unrestricted Literature Based Discovery
| Title | HiDE: a Tool for Unrestricted Literature Based Discovery |
| Authors | Judita Preiss, Mark Stevenson |
| Abstract | As the quantity of publications increases daily, researchers are forced to narrow their attention to their own specialism and are therefore less likely to make new connections with other areas. Literature based discovery (LBD) supports the identification of such connections. A number of LBD tools are available, however, they often suffer from limitations such as constraining possible searches or not producing results in real-time. We introduce HiDE (Hidden Discovery Explorer), an online knowledge browsing tool which allows fast access to hidden knowledge generated from all abstracts in Medline. HiDE is fast enough to allow users to explore the full range of hidden connections generated by an LBD system. The tool employs a novel combination of two approaches to LBD: a graph-based approach which allows hidden knowledge to be generated on a large scale and an inference algorithm to identify the most promising (most likely to be non trivial) information. Available at https://skye.shef.ac.uk/kdisc |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-2008/ |
| https://www.aclweb.org/anthology/C18-2008 | |
| PWC | https://paperswithcode.com/paper/hide-a-tool-for-unrestricted-literature-based |
| Repo | |
| Framework | |
EvalD Reference-Less Discourse Evaluation for WMT18
| Title | EvalD Reference-Less Discourse Evaluation for WMT18 |
| Authors | Ond{\v{r}}ej Bojar, Ji{\v{r}}{'\i} M{'\i}rovsk{'y}, Kate{\v{r}}ina Rysov{'a}, Magdal{'e}na Rysov{'a} |
| Abstract | We present the results of automatic evaluation of discourse in machine translation (MT) outputs using the EVALD tool. EVALD was originally designed and trained to assess the quality of \textit{human} writing, for native speakers and foreign-language learners. MT has seen a tremendous leap in translation quality at the level of sentences and it is thus interesting to see if the human-level evaluation is becoming relevant. |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6432/ |
| https://www.aclweb.org/anthology/W18-6432 | |
| PWC | https://paperswithcode.com/paper/evald-reference-less-discourse-evaluation-for |
| Repo | |
| Framework | |
Predicting Twitter User Demographics from Names Alone
| Title | Predicting Twitter User Demographics from Names Alone |
| Authors | Zach Wood-Doughty, Nicholas Andrews, Rebecca Marvin, Mark Dredze |
| Abstract | Social media analysis frequently requires tools that can automatically infer demographics to contextualize trends. These tools often require hundreds of user-authored messages for each user, which may be prohibitive to obtain when analyzing millions of users. We explore character-level neural models that learn a representation of a user{'}s name and screen name to predict gender and ethnicity, allowing for demographic inference with minimal data. We release trained models1 which may enable new demographic analyses that would otherwise require enormous amounts of data collection |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1114/ |
| https://www.aclweb.org/anthology/W18-1114 | |
| PWC | https://paperswithcode.com/paper/predicting-twitter-user-demographics-from |
| Repo | |
| Framework | |
