Paper Group NANR 157
The effects of neural resource constraints on early visual representations. lingvis.io - A Linguistic Visual Analytics Framework. Unsupervised Collaborative Learning of Keyframe Detection and Visual Odometry Towards Monocular Deep SLAM. A Case for Object Compositionality in Deep Generative Models of Images. Beyond Volumetric Albedo – A Surface Opt …
The effects of neural resource constraints on early visual representations
| Title | The effects of neural resource constraints on early visual representations |
| Authors | Jack Lindsey, Samuel A. Ocko, Surya Ganguli, Stephane Deny |
| Abstract | The vertebrate visual system is hierarchically organized to process visual information in successive stages. Neural representations vary drastically across the first stages of visual processing. At the output of the retina, ganglion cell receptive fields (RFs) exhibit a clear antagonistic center-surround structure, whereas in the primary visual cortex (V1), typical RFs are sharply tuned to a precise orientation. There is currently no theory explaining these differences in representations across layers. Here, using a deep convolutional neural network trained on image recognition as a model of the visual system, we show that such differences in representation can emerge as a direct consequence of different neural resource constraints on the retinal and cortical networks, and for the first time we find a single model from which both geometries spontaneously emerge at the appropriate stages of visual processing. The key constraint is a reduced number of neurons at the retinal output, consistent with the anatomy of the optic nerve as a stringent bottleneck. Second, we find that, for simple downstream cortical networks, visual representations at the retinal output emerge as non-linear and lossy feature detectors, whereas they emerge as linear and faithful encoders of the visual scene for complex brains. This result predicts that the retinas of small vertebrates (e.g. salamander, frog) should perform sophisticated nonlinear computations, extracting features directly relevant to behavior, whereas retinas of large animals such as primates should mostly encode the visual scene linearly and respond to a much broader range of stimuli. These predictions could reconcile the two seemingly incompatible views of the retina as either performing feature extraction or efficient coding of natural scenes, by suggesting that all vertebrates lie on a spectrum between these two objectives, depending on the degree of neural resources allocated to their visual system. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=S1xq3oR5tQ |
| https://openreview.net/pdf?id=S1xq3oR5tQ | |
| PWC | https://paperswithcode.com/paper/the-effects-of-neural-resource-constraints-on |
| Repo | |
| Framework | |
lingvis.io - A Linguistic Visual Analytics Framework
| Title | lingvis.io - A Linguistic Visual Analytics Framework |
| Authors | Mennatallah El-Assady, Wolfgang Jentner, Fabian Sperrle, Rita Sevastjanova, Annette Hautli-Janisz, Miriam Butt, Daniel Keim |
| Abstract | We present a modular framework for the rapid-prototyping of linguistic, web-based, visual analytics applications. Our framework gives developers access to a rich set of machine learning and natural language processing steps, through encapsulating them into micro-services and combining them into a computational pipeline. This processing pipeline is auto-configured based on the requirements of the visualization front-end, making the linguistic processing and visualization design, detached independent development tasks. This paper describes the constellation and modality of our framework, which continues to support the efficient development of various human-in-the-loop, linguistic visual analytics research techniques and applications. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-3003/ |
| https://www.aclweb.org/anthology/P19-3003 | |
| PWC | https://paperswithcode.com/paper/lingvisio-a-linguistic-visual-analytics |
| Repo | |
| Framework | |
Unsupervised Collaborative Learning of Keyframe Detection and Visual Odometry Towards Monocular Deep SLAM
| Title | Unsupervised Collaborative Learning of Keyframe Detection and Visual Odometry Towards Monocular Deep SLAM |
| Authors | Lu Sheng, Dan Xu, Wanli Ouyang, Xiaogang Wang |
| Abstract | In this paper we tackle the joint learning problem of keyframe detection and visual odometry towards monocular visual SLAM systems. As an important task in visual SLAM, keyframe selection helps efficient camera relocalization and effective augmentation of visual odometry. To benefit from it, we first present a deep network design for the keyframe selection, which is able to reliably detect keyframes and localize new frames, then an end-to-end unsupervised deep framework further proposed for simultaneously learning the keyframe selection and the visual odometry tasks. As far as we know, it is the first work to jointly optimize these two complementary tasks in a single deep framework. To make the two tasks facilitate each other in the learning, a collaborative optimization loss based on both geometric and visual metrics is proposed. Extensive experiments on publicly available datasets (i.e. KITTI raw dataset and its odometry split) clearly demonstrate the effectiveness of the proposed approach, and new state-of-the-art results are established on the unsupervised depth and pose estimation from monocular videos. |
| Tasks | Camera Relocalization, Pose Estimation, Visual Odometry |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Sheng_Unsupervised_Collaborative_Learning_of_Keyframe_Detection_and_Visual_Odometry_Towards_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Sheng_Unsupervised_Collaborative_Learning_of_Keyframe_Detection_and_Visual_Odometry_Towards_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-collaborative-learning-of |
| Repo | |
| Framework | |
A Case for Object Compositionality in Deep Generative Models of Images
| Title | A Case for Object Compositionality in Deep Generative Models of Images |
| Authors | Sjoerd van Steenkiste, Karol Kurach, Sylvain Gelly |
| Abstract | Deep generative models seek to recover the process with which the observed data was generated. They may be used to synthesize new samples or to subsequently extract representations. Successful approaches in the domain of images are driven by several core inductive biases. However, a bias to account for the compositional way in which humans structure a visual scene in terms of objects has frequently been overlooked. In this work we propose to structure the generator of a GAN to consider objects and their relations explicitly, and generate images by means of composition. This provides a way to efficiently learn a more accurate generative model of real-world images, and serves as an initial step towards learning corresponding object representations. We evaluate our approach on several multi-object image datasets, and find that the generator learns to identify and disentangle information corresponding to different objects at a representational level. A human study reveals that the resulting generative model is better at generating images that are more faithful to the reference distribution. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJgEjiRqYX |
| https://openreview.net/pdf?id=BJgEjiRqYX | |
| PWC | https://paperswithcode.com/paper/a-case-for-object-compositionality-in-deep-1 |
| Repo | |
| Framework | |
Beyond Volumetric Albedo – A Surface Optimization Framework for Non-Line-Of-Sight Imaging
| Title | Beyond Volumetric Albedo – A Surface Optimization Framework for Non-Line-Of-Sight Imaging |
| Authors | Chia-Yin Tsai, Aswin C. Sankaranarayanan, Ioannis Gkioulekas |
| Abstract | Non-line-of-sight (NLOS) imaging is the problem of reconstructing properties of scenes occluded from a sensor, using measurements of light that indirectly travels from the occluded scene to the sensor through intermediate diffuse reflections. We introduce an analysis-by-synthesis framework that can reconstruct complex shape and reflectance of an NLOS object. Our framework deviates from prior work on NLOS reconstruction, by directly optimizing for a surface representation of the NLOS object, in place of commonly employed volumetric representations. At the core of our framework is a new rendering formulation that efficiently computes derivatives of radiometric measurements with respect to NLOS geometry and reflectance, while accurately modeling the underlying light transport physics. By coupling this with stochastic optimization and geometry processing techniques, we are able to reconstruct NLOS surface at a level of detail significantly exceeding what is possible with previous volumetric reconstruction methods. |
| Tasks | Stochastic Optimization |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Tsai_Beyond_Volumetric_Albedo_--_A_Surface_Optimization_Framework_for_Non-Line-Of-Sight_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Tsai_Beyond_Volumetric_Albedo_--_A_Surface_Optimization_Framework_for_Non-Line-Of-Sight_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-volumetric-albedo-a-surface |
| Repo | |
| Framework | |
Structural Approach to Enhancing WordNet with Conceptual Frame Semantics
| Title | Structural Approach to Enhancing WordNet with Conceptual Frame Semantics |
| Authors | Svetlozara Leseva, Ivelina Stoyanova |
| Abstract | This paper outlines procedures for enhancing WordNet with conceptual information from FrameNet. The mapping of the two resources is non-trivial. We define a number of techniques for the validation of the consistency of the mapping and the extension of its coverage which make use of the structure of both resources and the systematic relations between synsets in WordNet and between frames in FrameNet, as well as between synsets and frames). We present a case study on causativity, a relation which provides enhancement complementary to the one using hierarchical relations, by means of linking in a systematic way large parts of the lexicon. We show how consistency checks and denser relations may be implemented on the basis of this relation. We, then, propose new frames based on causative-inchoative correspondences and in conclusion touch on the possibilities for defining new frames based on the types of specialisation that takes place from parent to child synset. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1074/ |
| https://www.aclweb.org/anthology/R19-1074 | |
| PWC | https://paperswithcode.com/paper/structural-approach-to-enhancing-wordnet-with |
| Repo | |
| Framework | |
Semi-supervised Domain Adaptation for Dependency Parsing
| Title | Semi-supervised Domain Adaptation for Dependency Parsing |
| Authors | Zhenghua Li, Xue Peng, Min Zhang, Rui Wang, Luo Si |
| Abstract | During the past decades, due to the lack of sufficient labeled data, most studies on cross-domain parsing focus on unsupervised domain adaptation, assuming there is no target-domain training data. However, unsupervised approaches make limited progress so far due to the intrinsic difficulty of both domain adaptation and parsing. This paper tackles the semi-supervised domain adaptation problem for Chinese dependency parsing, based on two newly-annotated large-scale domain-aware datasets. We propose a simple domain embedding approach to merge the source- and target-domain training data, which is shown to be more effective than both direct corpus concatenation and multi-task learning. In order to utilize unlabeled target-domain data, we employ the recent contextualized word representations and show that a simple fine-tuning procedure can further boost cross-domain parsing accuracy by large margin. |
| Tasks | Dependency Parsing, Domain Adaptation, Multi-Task Learning, Unsupervised Domain Adaptation |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1229/ |
| https://www.aclweb.org/anthology/P19-1229 | |
| PWC | https://paperswithcode.com/paper/semi-supervised-domain-adaptation-for |
| Repo | |
| Framework | |
Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects
| Title | Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects |
| Authors | Jianmo Ni, Jiacheng Li, Julian McAuley |
| Abstract | Several recent works have considered the problem of generating reviews (or {}tips{'}) as a form of explanation as to why a recommendation might match a customer{'}s interests. While promising, we demonstrate that existing approaches struggle (in terms of both quality and content) to generate justifications that are relevant to users{'} decision-making process. We seek to introduce new datasets and methods to address the recommendation justification task. In terms of data, we first propose an {}extractive{'} approach to identify review segments which justify users{'} intentions; this approach is then used to distantly label massive review corpora and construct large-scale personalized recommendation justification datasets. In terms of generation, we are able to design two personalized generation models with this data: (1) a reference-based Seq2Seq model with aspect-planning which can generate justifications covering different aspects, and (2) an aspect-conditional masked language model which can generate diverse justifications based on templates extracted from justification histories. We conduct experiments on two real-world datasets which show that our model is capable of generating convincing and diverse justifications. |
| Tasks | Decision Making, Language Modelling |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1018/ |
| https://www.aclweb.org/anthology/D19-1018 | |
| PWC | https://paperswithcode.com/paper/justifying-recommendations-using-distantly |
| Repo | |
| Framework | |
L-HSAB: A Levantine Twitter Dataset for Hate Speech and Abusive Language
| Title | L-HSAB: A Levantine Twitter Dataset for Hate Speech and Abusive Language |
| Authors | Hala Mulki, Hatem Haddad, Chedi Bechikh Ali, Halima Alshabani |
| Abstract | Hate speech and abusive language have become a common phenomenon on Arabic social media. Automatic hate speech and abusive detection systems can facilitate the prohibition of toxic textual contents. The complexity, informality and ambiguity of the Arabic dialects hindered the provision of the needed resources for Arabic abusive/hate speech detection research. In this paper, we introduce the first publicly-available Levantine Hate Speech and Abusive (L-HSAB) Twitter dataset with the objective to be a benchmark dataset for automatic detection of online Levantine toxic contents. We, further, provide a detailed review of the data collection steps and how we design the annotation guidelines such that a reliable dataset annotation is guaranteed. This has been later emphasized through the comprehensive evaluation of the annotations as the annotation agreement metrics of Cohen{'}s Kappa (k) and Krippendorff{'}s alpha (α) indicated the consistency of the annotations. |
| Tasks | Hate Speech Detection |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3512/ |
| https://www.aclweb.org/anthology/W19-3512 | |
| PWC | https://paperswithcode.com/paper/l-hsab-a-levantine-twitter-dataset-for-hate |
| Repo | |
| Framework | |
ABARUAH at SemEval-2019 Task 5 : Bi-directional LSTM for Hate Speech Detection
| Title | ABARUAH at SemEval-2019 Task 5 : Bi-directional LSTM for Hate Speech Detection |
| Authors | Arup Baruah, Ferdous Barbhuiya, Kuntal Dey |
| Abstract | In this paper, we present the results obtained using bi-directional long short-term memory (BiLSTM) with and without attention and Logistic Regression (LR) models for SemEval-2019 Task 5 titled {''}HatEval: Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter{''}. This paper presents the results obtained for Subtask A for English language. The results of the BiLSTM and LR models are compared for two different types of preprocessing. One with no stemming performed and no stopwords removed. The other with stemming performed and stopwords removed. The BiLSTM model without attention performed the best for the first test, while the LR model with character n-grams performed the best for the second test. The BiLSTM model obtained an F1 score of 0.51 on the test set and obtained an official ranking of 8/71. |
| Tasks | Hate Speech Detection |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2065/ |
| https://www.aclweb.org/anthology/S19-2065 | |
| PWC | https://paperswithcode.com/paper/abaruah-at-semeval-2019-task-5-bi-directional |
| Repo | |
| Framework | |
Learning multilingual topics through aspect extraction from monolingual texts
| Title | Learning multilingual topics through aspect extraction from monolingual texts |
| Authors | Johannes Huber, Myra Spiliopoulou |
| Abstract | |
| Tasks | Aspect Extraction, Multilingual Word Embeddings, Word Embeddings |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0313/ |
| https://www.aclweb.org/anthology/W19-0313 | |
| PWC | https://paperswithcode.com/paper/learning-multilingual-topics-through-aspect |
| Repo | |
| Framework | |
CIC at SemEval-2019 Task 5: Simple Yet Very Efficient Approach to Hate Speech Detection, Aggressive Behavior Detection, and Target Classification in Twitter
| Title | CIC at SemEval-2019 Task 5: Simple Yet Very Efficient Approach to Hate Speech Detection, Aggressive Behavior Detection, and Target Classification in Twitter |
| Authors | Iqra Ameer, Muhammad Hammad Fahim Siddiqui, Grigori Sidorov, Alex Gelbukh, er |
| Abstract | In recent years, the use of social media has in-creased incredibly. Social media permits Inter-net users a friendly platform to express their views and opinions. Along with these nice and distinct communication chances, it also allows bad things like usage of hate speech. Online automatic hate speech detection in various aspects is a significant scientific problem. This paper presents the Instituto Polit{'e}cnico Nacional (Mexico) approach for the Semeval 2019 Task-5 [Hateval 2019] (Basile et al., 2019) competition for Multilingual Detection of Hate Speech on Twitter. The goal of this paper is to detect (A) Hate speech against immigrants and women, (B) Aggressive behavior and target classification, both for English and Spanish. In the proposed approach, we used a bag of words model with preprocessing (stem-ming and stop words removal). We submitted two different systems with names: (i) CIC-1 and (ii) CIC-2 for Hateval 2019 shared task. We used TF values in the first system and TF-IDF for the second system. The first system, CIC-1 got 2nd rank in subtask B for both English and Spanish languages with EMR score of 0.568 for English and 0.675 for Spanish. The second system, CIC-2 was ranked 4th in sub-task A and 1st in subtask B for Spanish language with a macro-F1 score of 0.727 and EMR score of 0.705 respectively. |
| Tasks | Hate Speech Detection |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2067/ |
| https://www.aclweb.org/anthology/S19-2067 | |
| PWC | https://paperswithcode.com/paper/cic-at-semeval-2019-task-5-simple-yet-very |
| Repo | |
| Framework | |
INF-HatEval at SemEval-2019 Task 5: Convolutional Neural Networks for Hate Speech Detection Against Women and Immigrants on Twitter
| Title | INF-HatEval at SemEval-2019 Task 5: Convolutional Neural Networks for Hate Speech Detection Against Women and Immigrants on Twitter |
| Authors | Alison Ribeiro, N{'a}dia Silva |
| Abstract | In this paper, we describe our approach to detect hate speech against women and immigrants on Twitter in a multilingual context, English and Spanish. This challenge was proposed by the SemEval-2019 Task 5, where participants should develop models for hate speech detection, a two-class classification where systems have to predict whether a tweet in English or in Spanish with a given target (women or immigrants) is hateful or not hateful (Task A), and whether the hate speech is directed at a specific person or a group of individuals (Task B). For this, we implemented a Convolutional Neural Networks (CNN) using pre-trained word embeddings (GloVe and FastText) with 300 dimensions. Our proposed model obtained in Task A 0.488 and 0.696 F1-score for English and Spanish, respectively. For Task B, the CNN obtained 0.297 and 0.430 EMR for English and Spanish, respectively. |
| Tasks | Hate Speech Detection, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2074/ |
| https://www.aclweb.org/anthology/S19-2074 | |
| PWC | https://paperswithcode.com/paper/inf-hateval-at-semeval-2019-task-5 |
| Repo | |
| Framework | |
Estimating the Fundamental Matrix Without Point Correspondences With Application to Transmission Imaging
| Title | Estimating the Fundamental Matrix Without Point Correspondences With Application to Transmission Imaging |
| Authors | Tobias Wurfl, Andre Aichert, Nicole Maass, Frank Dennerlein, Andreas Maier |
| Abstract | We present a general method to estimate the fundamental matrix from a pair of images under perspective projection without the need for image point correspondences. Our method is particularly well-suited for transmission imaging, where state-of-the-art feature detection and matching approaches generally do not perform well. Estimation of the fundamental matrix plays a central role in auto-calibration methods for reflection imaging. Such methods are currently not applicable to transmission imaging. Furthermore, our method extends an existing technique proposed for reflection imaging which potentially avoids the outlier-prone feature matching step from an orthographic projection model to a perspective model. Our method exploits the idea that under a linear attenuation model line integrals along corresponding epipolar lines are equal if we compute their derivatives in orthogonal direction to their common epipolar plane. We use the fundamental matrix to parametrize this equality. Our method estimates the matrix by formulating a non-convex optimization problem, minimizing an error in our measurement of this equality. We believe this technique will enable the application of the large body of work on image-based camera pose estimation to transmission imaging leading to more accurate and more general motion compensation and auto-calibration algorithms, particularly in medical X-ray and Computed Tomography imaging. |
| Tasks | Calibration, Motion Compensation, Pose Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Wurfl_Estimating_the_Fundamental_Matrix_Without_Point_Correspondences_With_Application_to_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Wurfl_Estimating_the_Fundamental_Matrix_Without_Point_Correspondences_With_Application_to_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-the-fundamental-matrix-without |
| Repo | |
| Framework | |
Learning Active Contour Models for Medical Image Segmentation
| Title | Learning Active Contour Models for Medical Image Segmentation |
| Authors | Xu Chen, Bryan M. Williams, Srinivasa R. Vallabhaneni, Gabriela Czanner, Rachel Williams, Yalin Zheng |
| Abstract | Image segmentation is an important step in medical image processing and has been widely studied and developed for refinement of clinical analysis and applications. New models based on deep learning have improved results but are restricted to pixel-wise fitting of the segmentation map. Our aim was to tackle this limitation by developing a new model based on deep learning which takes into account the area inside as well as outside the region of interest as well as the size of boundaries during learning. Specifically, we propose a new loss function which incorporates area and size information and integrates this into a dense deep learning model. We evaluated our approach on a dataset of more than 2,000 cardiac MRI scans. Our results show that the proposed loss function outperforms other mainstream loss function Cross-entropy on two common segmentation networks. Our loss function is robust while using different hyperparameter lambda. |
| Tasks | Medical Image Segmentation, Semantic Segmentation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Chen_Learning_Active_Contour_Models_for_Medical_Image_Segmentation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Chen_Learning_Active_Contour_Models_for_Medical_Image_Segmentation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-active-contour-models-for-medical |
| Repo | |
| Framework | |
