Paper Group NAWR 35
Hierarchical Encoding of Sequential Data With Compact and Sub-Linear Storage Cost. An OCR system for the Unified Northern Alphabet. Learning Emphasis Selection for Written Text in Visual Media from Crowd-Sourced Label Distributions. APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs. What a neural language m …
Hierarchical Encoding of Sequential Data With Compact and Sub-Linear Storage Cost
| Title | Hierarchical Encoding of Sequential Data With Compact and Sub-Linear Storage Cost |
| Authors | Huu Le, Ming Xu, Tuan Hoang, Michael Milford |
| Abstract | Snapshot-based visual localization is an important problem in several computer vision and robotics applications such as Simultaneous Localization And Mapping (SLAM). To achieve real-time performance in very large-scale environments with massive amounts of training and map data, techniques such as approximate nearest neighbor search (ANN) algorithms are used. While several state-of-the-art variants of quantization and indexing techniques have demonstrated to be efficient in practice, their theoretical memory cost still scales at least linearly with the training data (i.e., O(n) where n is the number of instances in the database), since each data point must be associated with at least one code vector. To address these limitations, in this paper we present a totally new hierarchical encoding approach that enables a sub-linear storage scale. The algorithm exploits the widespread sequential nature of sensor information streams in robotics and autonomous vehicle applications and achieves, both theoretically and experimentally, sub-linear scalability in storage required for a given environment size. Furthermore, the associated query time of our algorithm is also of sub-linear complexity. We benchmark the performance of the proposed algorithm on several real-world benchmark datasets and experimentally validate the theoretical sub-linearity of our approach, while also showing that our approach yields competitive absolute storage performance as well. |
| Tasks | Quantization, Simultaneous Localization and Mapping, Visual Localization |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Le_Hierarchical_Encoding_of_Sequential_Data_With_Compact_and_Sub-Linear_Storage_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Le_Hierarchical_Encoding_of_Sequential_Data_With_Compact_and_Sub-Linear_Storage_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-encoding-of-sequential-data-with |
| Repo | https://github.com/intellhave/HESSL |
| Framework | none |
An OCR system for the Unified Northern Alphabet
| Title | An OCR system for the Unified Northern Alphabet |
| Authors | Niko Partanen, Michael Rie{\ss}ler |
| Abstract | |
| Tasks | Optical Character Recognition |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0307/ |
| https://www.aclweb.org/anthology/W19-0307 | |
| PWC | https://paperswithcode.com/paper/an-ocr-system-for-the-unified-northern |
| Repo | https://github.com/langdoc/iwclul2019 |
| Framework | none |
Learning Emphasis Selection for Written Text in Visual Media from Crowd-Sourced Label Distributions
| Title | Learning Emphasis Selection for Written Text in Visual Media from Crowd-Sourced Label Distributions |
| Authors | Amirreza Shirani, Franck Dernoncourt, Paul Asente, Nedim Lipka, Seokhwan Kim, Jose Echevarria, Thamar Solorio |
| Abstract | In visual communication, text emphasis is used to increase the comprehension of written text to convey the author{'}s intent. We study the problem of emphasis selection, i.e. choosing candidates for emphasis in short written text, to enable automated design assistance in authoring. Without knowing the author{'}s intent and only considering the input text, multiple emphasis selections are valid. We propose a model that employs end-to-end label distribution learning (LDL) on crowd-sourced data and predicts a selection distribution, capturing the inter-subjectivity (common-sense) in the audience as well as the ambiguity of the input. We compare the model with several baselines in which the problem is transformed to single-label learning by mapping label distributions to absolute labels via majority voting. |
| Tasks | Common Sense Reasoning |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1112/ |
| https://www.aclweb.org/anthology/P19-1112 | |
| PWC | https://paperswithcode.com/paper/learning-emphasis-selection-for-written-text |
| Repo | https://github.com/RiTUAL-UH/emphasis-2019 |
| Framework | pytorch |
APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs
| Title | APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs |
| Authors | Ran Yi, Yong-Jin Liu, Yu-Kun Lai, Paul L. Rosin |
| Abstract | Significant progress has been made with image stylization using deep learning, especially with generative adversarial networks (GANs). However, existing methods fail to produce high quality artistic portrait drawings. Such drawings have a highly abstract style, containing a sparse set of continuous graphical elements such as lines, and so small artifacts are much more exposed than for painting styles. Moreover, artists tend to use different strategies to draw different facial features and the lines drawn are only loosely related to obvious image features. To address these challenges, we propose APDrawingGAN, a novel GAN based architecture that builds upon hierarchical generators and discriminators combining both a global network (for images as a whole) and local networks (for individual facial regions). This allows dedicated drawing strategies to be learned for different facial features. Since artists’ drawings may not have lines perfectly aligned with image features, we develop a novel loss to measure similarity between generated and artists’ drawings based on distance transforms, leading to improved strokes in portrait drawing. To train APDrawingGAN, we construct an artistic drawing dataset containing high-resolution portrait photos and corresponding professional artistic drawings. Extensive experiments, including a user study, show that APDrawingGAN produces significantly better artistic drawings than state-of-the-art methods. |
| Tasks | Image Stylization |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Yi_APDrawingGAN_Generating_Artistic_Portrait_Drawings_From_Face_Photos_With_Hierarchical_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Yi_APDrawingGAN_Generating_Artistic_Portrait_Drawings_From_Face_Photos_With_Hierarchical_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/apdrawinggan-generating-artistic-portrait |
| Repo | https://github.com/yiranran/APDrawingGAN |
| Framework | pytorch |
What a neural language model tells us about spatial relations
| Title | What a neural language model tells us about spatial relations |
| Authors | Mehdi Ghanimifard, Simon Dobnik |
| Abstract | Understanding and generating spatial descriptions requires knowledge about what objects are related, their functional interactions, and where the objects are geometrically located. Different spatial relations have different functional and geometric bias. The wide usage of neural language models in different areas including generation of image description motivates the study of what kind of knowledge is encoded in neural language models about individual spatial relations. With the premise that the functional bias of relations is expressed in their word distributions, we construct multi-word distributional vector representations and show that these representations perform well on intrinsic semantic reasoning tasks, thus confirming our premise. A comparison of our vector representations to human semantic judgments indicates that different bias (functional or geometric) is captured in different data collection tasks which suggests that the contribution of the two meaning modalities is dynamic, related to the context of the task. |
| Tasks | Language Modelling |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1608/ |
| https://www.aclweb.org/anthology/W19-1608 | |
| PWC | https://paperswithcode.com/paper/what-a-neural-language-model-tells-us-about |
| Repo | https://github.com/GU-CLASP/what_nlm_srels |
| Framework | none |
Toward better boundary preserved supervoxel segmentation for 3D point clouds
| Title | Toward better boundary preserved supervoxel segmentation for 3D point clouds |
| Authors | Yangbin Lin, Cheng Wang, Dawei Zhai, Wei Li, Jonathan Li |
| Abstract | Supervoxels provide a more natural and compact representation of three dimensional point clouds, and enable the operations to be performed on regions rather than on the scattered points. Many state-of-the-art supervoxel segmentation methods adopt fixed resolution for each supervoxel, and rely on the initialization of seed points. As a result, they may not preserve well the boundaries of the point cloud with a non-uniform density. In this paper, we present a simple but effective supervoxel segmentation method for point clouds, which formalizes supervoxel segmentation as a subset selection problem. We develop an heuristic algorithm that utilizes local information to efficiently solve the subset selection problem. The proposed method can produce supervoxels with adaptive resolutions, and dose not rely the selection of seed points. The method is fully tested on three publicly available point cloud segmentation benchmarks, which cover the major point cloud types. The experimental results show that compared with the state-of-the-art supervoxel segmentation methods, the supervoxels extracted using our method preserve the object boundaries and small structures more effectively, which is reflected in a higher boundary recall and lower under-segmentation error. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.sciencedirect.com/science/article/abs/pii/S0924271618301370 |
| https://www.researchgate.net/publication/325334638_Toward_better_boundary_preserved_supervoxel_segmentation_for_3D_point_clouds | |
| PWC | https://paperswithcode.com/paper/toward-better-boundary-preserved-supervoxel |
| Repo | https://github.com/yblin/Supervoxel-for-3D-point-clouds |
| Framework | none |
Quantum Embedding of Knowledge for Reasoning
| Title | Quantum Embedding of Knowledge for Reasoning |
| Authors | Dinesh Garg, Shajith Ikbal Mohamed, Santosh K. Srivastava, Harit Vishwakarma, Hima Karanam, L Venkata Subramaniam |
| Abstract | Statistical Relational Learning (SRL) methods are the most widely used techniques to generate distributional representations of the symbolic Knowledge Bases (KBs). These methods embed any given KB into a vector space by exploiting statistical similarities among its entities and predicates but without any guarantee of preserving the underlying logical structure of the KB. This, in turn, results in poor performance of logical reasoning tasks that are solved using such distributional representations. We present a novel approach called Embed2Reason (E2R) that embeds a symbolic KB into a vector space in a logical structure preserving manner. This approach is inspired by the theory of Quantum Logic. Such an embedding allows answering membership based complex logical reasoning queries with impressive accuracy improvements over popular SRL baselines. |
| Tasks | Relational Reasoning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8797-quantum-embedding-of-knowledge-for-reasoning |
| http://papers.nips.cc/paper/8797-quantum-embedding-of-knowledge-for-reasoning.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-embedding-of-knowledge-for-reasoning |
| Repo | https://github.com/IBM/e2r |
| Framework | pytorch |
BASNet: Boundary-Aware Salient Object Detection
| Title | BASNet: Boundary-Aware Salient Object Detection |
| Authors | Xuebin Qin, Zichen Zhang, Chenyang Huang, Chao Gao, Masood Dehghan, Martin Jagersand |
| Abstract | Deep Convolutional Neural Networks have been adopted for salient object detection and achieved the state-of-the-art performance. Most of the previous works however focus on region accuracy but not on the boundary quality. In this paper, we propose a predict-refine architecture, BASNet, and a new hybrid loss for Boundary-Aware Salient object detection. Specifically, the architecture is composed of a densely supervised Encoder-Decoder network and a residual refinement module, which are respectively in charge of saliency prediction and saliency map refinement. The hybrid loss guides the network to learn the transformation between the input image and the ground truth in a three-level hierarchy – pixel-, patch- and map- level – by fusing Binary Cross Entropy (BCE), Structural SIMilarity (SSIM) and Intersection-over-Union (IoU) losses. Equipped with the hybrid loss, the proposed predict-refine architecture is able to effectively segment the salient object regions and accurately predict the fine structures with clear boundaries. Experimental results on six public datasets show that our method outperforms the state-of-the-art methods both in terms of regional and boundary evaluation measures. Our method runs at over 25 fps on a single GPU. The code is available at: https://github.com/NathanUA/BASNet. |
| Tasks | Object Detection, Saliency Prediction, Salient Object Detection |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Qin_BASNet_Boundary-Aware_Salient_Object_Detection_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Qin_BASNet_Boundary-Aware_Salient_Object_Detection_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/basnet-boundary-aware-salient-object |
| Repo | https://github.com/NathanUA/BASNet |
| Framework | pytorch |
Zero-training Sentence Embedding via Orthogonal Basis
| Title | Zero-training Sentence Embedding via Orthogonal Basis |
| Authors | Ziyi Yang, Chenguang Zhu, Weizhu Chen |
| Abstract | We propose a simple and robust training-free approach for building sentence representations. Inspired by the Gram-Schmidt Process in geometric theory, we build an orthogonal basis of the subspace spanned by a word and its surrounding context in a sentence. We model the semantic meaning of a word in a sentence based on two aspects. One is its relatedness to the word vector subspace already spanned by its contextual words. The other is its novel semantic meaning which shall be introduced as a new basis vector perpendicular to this existing subspace. Following this motivation, we develop an innovative method based on orthogonal basis to combine pre-trained word embeddings into sentence representation. This approach requires zero training and zero parameters, along with efficient inference performance. We evaluate our approach on 11 downstream NLP tasks. Experimental results show that our model outperforms all existing zero-training alternatives in all the tasks and it is competitive to other approaches relying on either large amounts of labelled data or prolonged training time. |
| Tasks | Sentence Embedding, Word Embeddings |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rJedbn0ctQ |
| https://openreview.net/pdf?id=rJedbn0ctQ | |
| PWC | https://paperswithcode.com/paper/zero-training-sentence-embedding-via-1 |
| Repo | https://github.com/fursovia/geometric_embedding |
| Framework | none |
Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problems
| Title | Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problems |
| Authors | Yi Xu, Rong Jin, Tianbao Yang |
| Abstract | Stochastic Proximal Gradient (SPG) methods have been widely used for solving optimization problems with a simple (possibly non-smooth) regularizer in machine learning and statistics. However, to the best of our knowledge no non-asymptotic convergence analysis of SPG exists for non-convex optimization with a non-smooth and non-convex regularizer. All existing non-asymptotic analysis of SPG for solving non-smooth non-convex problems require the non-smooth regularizer to be a convex function, and hence are not applicable to a non-smooth non-convex regularized problem. This work initiates the analysis to bridge this gap and opens the door to non-asymptotic convergence analysis of non-smooth non-convex regularized problems. We analyze several variants of mini-batch SPG methods for minimizing a non-convex objective that consists of a smooth non-convex loss and a non-smooth non-convex regularizer. Our contributions are two-fold: (i) we show that they enjoy the same complexities as their counterparts for solving convex regularized non-convex problems in terms of finding an approximate stationary point; (ii) we develop more practical variants using dynamic mini-batch size instead of a fixed mini-batch size without requiring the target accuracy level of solution. The significance of our results is that they improve upon the-state-of-art results for solving non-smooth non-convex regularized problems. We also empirically demonstrate the effectiveness of the considered SPG methods in comparison with other peer stochastic methods. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8531-non-asymptotic-analysis-of-stochastic-methods-for-non-smooth-non-convex-regularized-problems |
| http://papers.nips.cc/paper/8531-non-asymptotic-analysis-of-stochastic-methods-for-non-smooth-non-convex-regularized-problems.pdf | |
| PWC | https://paperswithcode.com/paper/non-asymptotic-analysis-of-stochastic-methods |
| Repo | https://github.com/yxu71/NCNS-regularizer |
| Framework | none |
Crowdsourcing and Aggregating Nested Markable Annotations
| Title | Crowdsourcing and Aggregating Nested Markable Annotations |
| Authors | Chris Madge, Juntao Yu, Jon Chamberlain, Udo Kruschwitz, Silviu Paun, Massimo Poesio |
| Abstract | One of the key steps in language resource creation is the identification of the text segments to be annotated, or markables, which depending on the task may vary from nominal chunks for named entity resolution to (potentially nested) noun phrases in coreference resolution (or mentions) to larger text segments in text segmentation. Markable identification is typically carried out semi-automatically, by running a markable identifier and correcting its output by hand{–}which is increasingly done via annotators recruited through crowdsourcing and aggregating their responses. In this paper, we present a method for identifying markables for coreference annotation that combines high-performance automatic markable detectors with checking with a Game-With-A-Purpose (GWAP) and aggregation using a Bayesian annotation model. The method was evaluated both on news data and data from a variety of other genres and results in an improvement on F1 of mention boundaries of over seven percentage points when compared with a state-of-the-art, domain-independent automatic mention detector, and almost three points over an in-domain mention detector. One of the key contributions of our proposal is its applicability to the case in which markables are nested, as is the case with coreference markables; but the GWAP and several of the proposed markable detectors are task and language-independent and are thus applicable to a variety of other annotation scenarios. |
| Tasks | Coreference Resolution, Entity Resolution |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1077/ |
| https://www.aclweb.org/anthology/P19-1077 | |
| PWC | https://paperswithcode.com/paper/crowdsourcing-and-aggregating-nested-markable |
| Repo | https://github.com/juntaoy/dali-preprocessing-pipeline |
| Framework | none |
Assessing Disparate Impact of Personalized Interventions: Identifiability and Bounds
| Title | Assessing Disparate Impact of Personalized Interventions: Identifiability and Bounds |
| Authors | Nathan Kallus, Angela Zhou |
| Abstract | Personalized interventions in social services, education, and healthcare leverage individual-level causal effect predictions in order to give the best treatment to each individual or to prioritize program interventions for the individuals most likely to benefit. While the sensitivity of these domains compels us to evaluate the fairness of such policies, we show that actually auditing their disparate impacts per standard observational metrics, such as true positive rates, is impossible since ground truths are unknown. Whether our data is experimental or observational, an individual’s actual outcome under an intervention different than that received can never be known, only predicted based on features. We prove how we can nonetheless point-identify these quantities under the additional assumption of monotone treatment response, which may be reasonable in many applications. We further provide a sensitivity analysis for this assumption via sharp partial-identification bounds under violations of monotonicity of varying strengths. We show how to use our results to audit personalized interventions using partially-identified ROC and xROC curves and demonstrate this in a case study of a French job training dataset. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8603-assessing-disparate-impact-of-personalized-interventions-identifiability-and-bounds |
| http://papers.nips.cc/paper/8603-assessing-disparate-impact-of-personalized-interventions-identifiability-and-bounds.pdf | |
| PWC | https://paperswithcode.com/paper/assessing-disparate-impact-of-personalized |
| Repo | https://github.com/CausalML/interventions-disparate-impact-responders |
| Framework | none |
A neurally plausible model for online recognition and postdiction in a dynamical environment
| Title | A neurally plausible model for online recognition and postdiction in a dynamical environment |
| Authors | Li Kevin Wenliang, Maneesh Sahani |
| Abstract | Humans and other animals are frequently near-optimal in their ability to integrate noisy and ambiguous sensory data to form robust percepts—which are informed both by sensory evidence and by prior expectations about the structure of the environment. It is suggested that the brain does so using the statistical structure provided by an internal model of how latent, causal factors produce the observed patterns. In dynamic environments, such integration often takes the form of \emph{postdiction}, wherein later sensory evidence affects inferences about earlier percepts. As the brain must operate in current time, without the luxury of acausal propagation of information, how does such postdictive inference come about? Here, we propose a general framework for neural probabilistic inference in dynamic models based on the distributed distributional code (DDC) representation of uncertainty, naturally extending the underlying encoding to incorporate implicit probabilistic beliefs about both present and past. We show that, as in other uses of the DDC, an inferential model can be learnt efficiently using samples from an internal model of the world. Applied to stimuli used in the context of psychophysics experiments, the framework provides an online and plausible mechanism for inference, including postdictive effects. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9159-a-neurally-plausible-model-for-online-recognition-and-postdiction-in-a-dynamical-environment |
| http://papers.nips.cc/paper/9159-a-neurally-plausible-model-for-online-recognition-and-postdiction-in-a-dynamical-environment.pdf | |
| PWC | https://paperswithcode.com/paper/a-neurally-plausible-model-for-online |
| Repo | https://github.com/kevin-w-li/ddc_ssm |
| Framework | pytorch |
Diffeomorphic Temporal Alignment Nets
| Title | Diffeomorphic Temporal Alignment Nets |
| Authors | Ron Shapira Weber, Matan Eyal, Nicki Skafte, Oren Shriki, Oren Freifeld |
| Abstract | Time-series analysis is confounded by nonlinear time warping of the data. Traditional methods for joint alignment do not generalize: after aligning a given signal ensemble, they lack a mechanism, that does not require solving a new optimization problem, to align previously-unseen signals. In the multi-class case, they must also first classify the test data before aligning it. Here we propose the Diffeomorphic Temporal alignment Net (DTAN), a learning-based method for time-series joint alignment. Via flexible temporal transformer layers, DTAN learns and applies an input-dependent nonlinear time warping to its input signal. Once learned, DTAN easily aligns previously-unseen signals by its inexpensive forward pass. In a single-class case, the method is unsupervised: the ground-truth alignments are unknown. In the multi-class case, it is semi-supervised in the sense that class labels (but not the ground-truth alignments) are used during learning; in test time, however, the class labels are unknown. As we show, DTAN not only outperforms existing joint-alignment methods in aligning training data but also generalizes well to test data. Our code is available at https://github.com/BGU-CS-VIL/dtan. |
| Tasks | Time Series, Time Series Alignment, Time Series Analysis, Time Series Averaging |
| Published | 2019-12-10 |
| URL | https://neurips.cc/Conferences/2019/Schedule?showEvent=13767 |
| https://www.cs.bgu.ac.il/~orenfr/DTAN/ShapiraWeber_NeurIPS_2019.pdf | |
| PWC | https://paperswithcode.com/paper/diffeomorphic-temporal-alignment-nets |
| Repo | https://github.com/BGU-CS-VIL/dtan |
| Framework | tf |
RecovDB: accurate and efficient missing blocks recovery for large time series
| Title | RecovDB: accurate and efficient missing blocks recovery for large time series |
| Authors | Ines Arous, Mourad Khayati, Philippe Cudré-Mauroux, Ying Zhang, Martin Kersten, Svetlin Stalinlov |
| Abstract | With the emergence of the Internet of Things (IoT), time series data has become ubiquitous in our daily life. Making sense of time series is a topic of great interest in many domains. Existing time series analysis applications generally assume or even require perfect time series (i.e. regular time intervals without unknown values), but real-world time series are rarely so neat. They often contain “holes” of different sizes (i.e. single missing values, or blocks of consecutive missing values) due to some failures or irregular time intervals. Hence, missing value recovery is a prerequisite for many time series analysis applications. In this demo, we present RECOVDB, a relational database system enhanced with advanced matrix decomposition technology for missing blocks recovery. This demo will show the main features of RECOVDB that are important for today’s time series analysis but are lacking in state-of-the-art technologies: i) recovering large missing blocks in multiple time series at once; ii) achieving high recovery accuracy by benefiting from different correlations across time series; iii) maintaining recovery accuracy under increasing size of missing blocks; iv) maintaining recovery efficiency with increasing time series’ lengths and the number of time series; and iv) supporting all these features while being parameter-free. In this paper, we also compare the efficiency and accuracy of RECOVDB against state-of-the-art recovery systems. |
| Tasks | Time Series, Time Series Analysis |
| Published | 2019-04-08 |
| URL | https://exascale.info/assets/pdf/recovdb19.pdf |
| https://exascale.info/assets/pdf/recovdb19.pdf | |
| PWC | https://paperswithcode.com/paper/recovdb-accurate-and-efficient-missing-blocks |
| Repo | https://github.com/eXascaleInfolab/2018-RecovDB |
| Framework | none |
