Paper Group NANR 205
Hierarchical Disentanglement of Discriminative Latent Features for Zero-Shot Learning. Generalising Fine-Grained Sketch-Based Image Retrieval. Deconstructing Supertagging into Multi-Task Sequence Prediction. SJTU-NICT at MRP 2019: Multi-Task Learning for End-to-End Uniform Semantic Graph Parsing. Approximation and non-parametric estimation of ResNe …
Hierarchical Disentanglement of Discriminative Latent Features for Zero-Shot Learning
| Title | Hierarchical Disentanglement of Discriminative Latent Features for Zero-Shot Learning |
| Authors | Bin Tong, Chao Wang, Martin Klinkigt, Yoshiyuki Kobayashi, Yuuichi Nonaka |
| Abstract | Most studies in zero-shot learning model the relationship, in the form of a classifier or mapping, between features from images of seen classes and their attributes. Therefore, the degree of a model’s generalization ability for recognizing unseen images is highly constrained by that of image features and attributes. In this paper, we discuss two questions about generalization that are seldom discussed. Are image features trained with samples of seen classes expressive enough to capture the discriminative information for both seen and unseen classes? Is the relationship learned from seen image features and attributes sufficiently generalized to recognize unseen classes. To answer these two questions, we propose a model to learn discriminative and generalizable representations from image features under an auto-encoder framework. The discriminative latent features are learned through a group-wise disentanglement over feature groups with a hierarchical structure. On popular benchmark data sets, a significant improvement over state-of-the-art methods in tasks of typical and generalized zero-shot learning verifies the generalization ability of latent features for recognizing unseen images. |
| Tasks | Zero-Shot Learning |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Tong_Hierarchical_Disentanglement_of_Discriminative_Latent_Features_for_Zero-Shot_Learning_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Tong_Hierarchical_Disentanglement_of_Discriminative_Latent_Features_for_Zero-Shot_Learning_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-disentanglement-of |
| Repo | |
| Framework | |
Generalising Fine-Grained Sketch-Based Image Retrieval
| Title | Generalising Fine-Grained Sketch-Based Image Retrieval |
| Authors | Kaiyue Pang, Ke Li, Yongxin Yang, Honggang Zhang, Timothy M. Hospedales, Tao Xiang, Yi-Zhe Song |
| Abstract | Fine-grained sketch-based image retrieval (FG-SBIR) addresses matching specific photo instance using free-hand sketch as a query modality. Existing models aim to learn an embedding space in which sketch and photo can be directly compared. While successful, they require instance-level pairing within each coarse-grained category as annotated training data. Since the learned embedding space is domain-specific, these models do not generalise well across categories. This limits the practical applicability of FG-SBIR. In this paper, we identify cross-category generalisation for FG-SBIR as a domain generalisation problem, and propose the first solution. Our key contribution is a novel unsupervised learning approach to model a universal manifold of prototypical visual sketch traits. This manifold can then be used to paramaterise the learning of a sketch/photo representation. Model adaptation to novel categories then becomes automatic via embedding the novel sketch in the manifold and updating the representation and retrieval function accordingly. Experiments on the two largest FG-SBIR datasets, Sketchy and QMUL-Shoe-V2, demonstrate the efficacy of our approach in enabling cross-category generalisation of FG-SBIR. |
| Tasks | Image Retrieval, Sketch-Based Image Retrieval |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Pang_Generalising_Fine-Grained_Sketch-Based_Image_Retrieval_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Pang_Generalising_Fine-Grained_Sketch-Based_Image_Retrieval_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/generalising-fine-grained-sketch-based-image |
| Repo | |
| Framework | |
Deconstructing Supertagging into Multi-Task Sequence Prediction
| Title | Deconstructing Supertagging into Multi-Task Sequence Prediction |
| Authors | Zhenqi Zhu, Anoop Sarkar |
| Abstract | Supertagging is a sequence prediction task where each word is assigned a piece of complex syntactic structure called a supertag. We provide a novel approach to multi-task learning for Tree Adjoining Grammar (TAG) supertagging by deconstructing these complex supertags in order to define a set of related but auxiliary sequence prediction tasks. Our multi-task prediction framework is trained over the exactly same training data used to train the original supertagger where each auxiliary task provides an alternative view on the original prediction task. Our experimental results show that our multi-task approach significantly improves TAG supertagging with a new state-of-the-art accuracy score of 91.39{%} on the Penn Treebank supertagging dataset. |
| Tasks | Multi-Task Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1002/ |
| https://www.aclweb.org/anthology/K19-1002 | |
| PWC | https://paperswithcode.com/paper/deconstructing-supertagging-into-multi-task |
| Repo | |
| Framework | |
SJTU-NICT at MRP 2019: Multi-Task Learning for End-to-End Uniform Semantic Graph Parsing
| Title | SJTU-NICT at MRP 2019: Multi-Task Learning for End-to-End Uniform Semantic Graph Parsing |
| Authors | Zuchao Li, Hai Zhao, Zhuosheng Zhang, Rui Wang, Masao Utiyama, Eiichiro Sumita |
| Abstract | This paper describes our SJTU-NICT{'}s system for participating in the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL). Our system uses a graph-based approach to model a variety of semantic graph parsing tasks. Our main contributions in the submitted system are summarized as follows: 1. Our model is fully end-to-end and is capable of being trained only on the given training set which does not rely on any other extra training source including the companion data provided by the organizer; 2. We extend our graph pruning algorithm to a variety of semantic graphs, solving the problem of excessive semantic graph search space; 3. We introduce multi-task learning for multiple objectives within the same framework. The evaluation results show that our system achieved second place in the overall $F_1$ score and achieved the best $F_1$ score on the DM framework. |
| Tasks | Multi-Task Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-2004/ |
| https://www.aclweb.org/anthology/K19-2004 | |
| PWC | https://paperswithcode.com/paper/sjtu-nict-at-mrp-2019-multi-task-learning-for |
| Repo | |
| Framework | |
Approximation and non-parametric estimation of ResNet-type convolutional neural networks via block-sparse fully-connected neural networks
| Title | Approximation and non-parametric estimation of ResNet-type convolutional neural networks via block-sparse fully-connected neural networks |
| Authors | Kenta Oono, Taiji Suzuki |
| Abstract | We develop new approximation and statistical learning theories of convolutional neural networks (CNNs) via the ResNet-type structure where the channel size, filter size, and width are fixed. It is shown that a ResNet-type CNN is a universal approximator and its expression ability is no worse than fully-connected neural networks (FNNs) with a \textit{block-sparse} structure even if the size of each layer in the CNN is fixed. Our result is general in the sense that we can automatically translate any approximation rate achieved by block-sparse FNNs into that by CNNs. Thanks to the general theory, it is shown that learning on CNNs satisfies optimality in approximation and estimation of several important function classes. As applications, we consider two types of function classes to be estimated: the Barron class and H"older class. We prove the clipped empirical risk minimization (ERM) estimator can achieve the same rate as FNNs even the channel size, filter size, and width of CNNs are constant with respect to the sample size. This is minimax optimal (up to logarithmic factors) for the H"older class. Our proof is based on sophisticated evaluations of the covering number of CNNs and the non-trivial parameter rescaling technique to control the Lipschitz constant of CNNs to be constructed. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HklnzhR9YQ |
| https://openreview.net/pdf?id=HklnzhR9YQ | |
| PWC | https://paperswithcode.com/paper/approximation-and-non-parametric-estimation |
| Repo | |
| Framework | |
Medical Entity Linking using Triplet Network
| Title | Medical Entity Linking using Triplet Network |
| Authors | Ishani Mondal, Sukannya Purkayastha, Sudeshna Sarkar, Pawan Goyal, Jitesh Pillai, Amitava Bhattacharyya, Mahan Gattu, eeshwar |
| Abstract | Entity linking (or Normalization) is an essential task in text mining that maps the entity mentions in the medical text to standard entities in a given Knowledge Base (KB). This task is of great importance in the medical domain. It can also be used for merging different medical and clinical ontologies. In this paper, we center around the problem of disease linking or normalization. This task is executed in two phases: candidate generation and candidate scoring. In this paper, we present an approach to rank the candidate Knowledge Base entries based on their similarity with disease mention. We make use of the Triplet Network for candidate ranking. While the existing methods have used carefully generated sieves and external resources for candidate generation, we introduce a robust and portable candidate generation scheme that does not make use of the hand-crafted rules. Experimental results on the standard benchmark NCBI disease dataset demonstrate that our system outperforms the prior methods by a significant margin. |
| Tasks | Entity Linking |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1912/ |
| https://www.aclweb.org/anthology/W19-1912 | |
| PWC | https://paperswithcode.com/paper/medical-entity-linking-using-triplet-network |
| Repo | |
| Framework | |
Proceedings of the Second Workshop on Shortcomings in Vision and Language
| Title | Proceedings of the Second Workshop on Shortcomings in Vision and Language |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1800/ |
| https://www.aclweb.org/anthology/W19-1800 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-second-workshop-on-14 |
| Repo | |
| Framework | |
Compensation Practice and Job Satisfaction in Selected Consumer Goods in Lagos state Nigeria
| Title | Compensation Practice and Job Satisfaction in Selected Consumer Goods in Lagos state Nigeria |
| Authors | Egbuta, Olive U. Ph.D. |
| Abstract | Job satisfaction in work organization influences the general efficiency and effectiveness of the whole employees. This is usually the results of the compensation practices that predominate in a firm. This paper examined the Compensation practices and how it affects the job satisfaction of employees of selected consumer goods firms in Lagos State, Nigeria. The paper adopted the survey research design through quantitative research approach. Primary data was used through administration of 300 copies of questionnaires to employees in the selected consumer goods firms. Findings reveal that Compensation practice has a positive and significant effect on Job satisfaction (R = 0.296, Adj. R2 =0.071, p < 0.05, F =11.497). It was found that compensation practice significantly affects job satisfaction of employees of selected consumer goods firms in Nigeria. The paper suggests that managers should always think about what compensation packages really motivate and excite their employees. |
| Tasks | |
| Published | 2019-07-30 |
| URL | https://ijbassnet.com/publication/250/details |
| https://ijbassnet.com/storage/app/publications/5d4018b30e91411564481715.pdf | |
| PWC | https://paperswithcode.com/paper/compensation-practice-and-job-satisfaction-in |
| Repo | |
| Framework | |
development of multi-user TDMA based DSSS system
| Title | development of multi-user TDMA based DSSS system |
| Authors | ameena sajid, saqid ali |
| Abstract | calculate the error probability of spreading factor length of 7,11 and 13 |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://ieeexplore.ieee.org/document/8681019 |
| https://ieeexplore.ieee.org/document/8681019 | |
| PWC | https://paperswithcode.com/paper/development-of-multi-user-tdma-based-dsss |
| Repo | |
| Framework | |
Exploring Deep Multimodal Fusion of Text and Photo for Hate Speech Classification
| Title | Exploring Deep Multimodal Fusion of Text and Photo for Hate Speech Classification |
| Authors | Fan Yang, Xiaochang Peng, Gargi Ghosh, Reshef Shilon, Hao Ma, Eider Moore, Goran Predovic |
| Abstract | Interactions among users on social network platforms are usually positive, constructive and insightful. However, sometimes people also get exposed to objectionable content such as hate speech, bullying, and verbal abuse etc. Most social platforms have explicit policy against hate speech because it creates an environment of intimidation and exclusion, and in some cases may promote real-world violence. As users{'} interactions on today{'}s social networks involve multiple modalities, such as texts, images and videos, in this paper we explore the challenge of automatically identifying hate speech with deep multimodal technologies, extending previous research which mostly focuses on the text signal alone. We present a number of fusion approaches to integrate text and photo signals. We show that augmenting text with image embedding information immediately leads to a boost in performance, while applying additional attention fusion methods brings further improvement. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3502/ |
| https://www.aclweb.org/anthology/W19-3502 | |
| PWC | https://paperswithcode.com/paper/exploring-deep-multimodal-fusion-of-text-and |
| Repo | |
| Framework | |
Reduce & Attribute: Two-Step Authorship Attribution for Large-Scale Problems
| Title | Reduce & Attribute: Two-Step Authorship Attribution for Large-Scale Problems |
| Authors | Michael Tschuggnall, Benjamin Murauer, G{"u}nther Specht |
| Abstract | Authorship attribution is an active research area which has been prevalent for many decades. Nevertheless, the majority of approaches consider problem sizes of a few candidate authors only, making them difficult to apply to recent scenarios incorporating thousands of authors emerging due to the manifold means to digitally share text. In this study, we focus on such large-scale problems and propose to effectively reduce the number of candidate authors before applying common attribution techniques. By utilizing document embeddings, we show on a novel, comprehensive dataset collection that the set of candidate authors can be reduced with high accuracy. Moreover, we show that common authorship attribution methods substantially benefit from a preliminary reduction if thousands of authors are involved. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1089/ |
| https://www.aclweb.org/anthology/K19-1089 | |
| PWC | https://paperswithcode.com/paper/reduce-textbackslash-attribute-two-step |
| Repo | |
| Framework | |
Semi-Supervised Learning With Graph Learning-Convolutional Networks
| Title | Semi-Supervised Learning With Graph Learning-Convolutional Networks |
| Authors | Bo Jiang, Ziyan Zhang, Doudou Lin, Jin Tang, Bin Luo |
| Abstract | Graph Convolutional Neural Networks (graph CNNs) have been widely used for graph data representation and semi-supervised learning tasks. However, existing graph CNNs generally use a fixed graph which may not be optimal for semi-supervised learning tasks. In this paper, we propose a novel Graph Learning-Convolutional Network (GLCN) for graph data representation and semi-supervised learning. The aim of GLCN is to learn an optimal graph structure that best serves graph CNNs for semi-supervised learning by integrating both graph learning and graph convolution in a unified network architecture. The main advantage is that in GLCN both given labels and the estimated labels are incorporated and thus can provide useful ‘weakly’ supervised information to refine (or learn) the graph construction and also to facilitate the graph convolution operation for unknown label estimation. Experimental results on seven benchmarks demonstrate that GLCN significantly outperforms the state-of-the-art traditional fixed structure based graph CNNs. |
| Tasks | graph construction |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Jiang_Semi-Supervised_Learning_With_Graph_Learning-Convolutional_Networks_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Jiang_Semi-Supervised_Learning_With_Graph_Learning-Convolutional_Networks_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-learning-with-graph-learning |
| Repo | |
| Framework | |
WSOD2: Learning Bottom-Up and Top-Down Objectness Distillation for Weakly-Supervised Object Detection
| Title | WSOD2: Learning Bottom-Up and Top-Down Objectness Distillation for Weakly-Supervised Object Detection |
| Authors | Zhaoyang Zeng, Bei Liu, Jianlong Fu, Hongyang Chao, Lei Zhang |
| Abstract | We study on weakly-supervised object detection (WSOD) which plays a vital role in relieving human involvement from object-level annotations. Predominant works integrate region proposal mechanisms with convolutional neural networks (CNN). Although CNN is proficient in extracting discriminative local features, grand challenges still exist to measure the likelihood of a bounding box containing a complete object (i.e., “objectness”). In this paper, we propose a novel WSOD framework with Objectness Distillation (i.e., WSOD2) by designing a tailored training mechanism for weakly-supervised object detection. Multiple regression targets are specifically determined by jointly considering bottom-up (BU) and top-down (TD) objectness from low-level measurement and CNN confidences with an adaptive linear combination. As bounding box regression can facilitate a region proposal learning to approach its regression target with high objectness during training, deep objectness representation learned from bottom-up evidences can be gradually distilled into CNN by optimization. We explore different adaptive training curves for BU/TD objectness, and show that the proposed WSOD2 can achieve state-of-the-art results. |
| Tasks | Object Detection, Weakly Supervised Object Detection |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zeng_WSOD2_Learning_Bottom-Up_and_Top-Down_Objectness_Distillation_for_Weakly-Supervised_Object_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zeng_WSOD2_Learning_Bottom-Up_and_Top-Down_Objectness_Distillation_for_Weakly-Supervised_Object_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/wsod2-learning-bottom-up-and-top-down-2 |
| Repo | |
| Framework | |
Machine Learning Approach to Fact-Checking in West Slavic Languages
| Title | Machine Learning Approach to Fact-Checking in West Slavic Languages |
| Authors | Pavel P{\v{r}}ib{'a}{\v{n}}, Tom{'a}{\v{s}} Hercig, Josef Steinberger |
| Abstract | Fake news detection and closely-related fact-checking have recently attracted a lot of attention. Automatization of these tasks has been already studied for English. For other languages, only a few studies can be found (e.g. (Baly et al., 2018)), and to the best of our knowledge, no research has been conducted for West Slavic languages. In this paper, we present datasets for Czech, Polish, and Slovak. We also ran initial experiments which set a baseline for further research into this area. |
| Tasks | Fake News Detection |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1113/ |
| https://www.aclweb.org/anthology/R19-1113 | |
| PWC | https://paperswithcode.com/paper/machine-learning-approach-to-fact-checking-in |
| Repo | |
| Framework | |
Guiding Physical Intuition with Neural Stethoscopes
| Title | Guiding Physical Intuition with Neural Stethoscopes |
| Authors | Fabian Fuchs, Oliver Groth, Adam Kosiorek, Alex Bewley, Markus Wulfmeier, Andrea Vedaldi, Ingmar Posner |
| Abstract | Model interpretability and systematic, targeted model adaptation present central challenges in deep learning. In the domain of intuitive physics, we study the task of visually predicting stability of block towers with the goal of understanding and influencing the model’s reasoning. Our contributions are two-fold. Firstly, we introduce neural stethoscopes as a framework for quantifying the degree of importance of specific factors of influence in deep networks as well as for actively promoting and suppressing information as appropriate. In doing so, we unify concepts from multitask learning as well as training with auxiliary and adversarial losses. Secondly, we deploy the stethoscope framework to provide an in-depth analysis of a state-of-the-art deep neural network for stability prediction, specifically examining its physical reasoning. We show that the baseline model is susceptible to being misled by incorrect visual cues. This leads to a performance breakdown to the level of random guessing when training on scenarios where visual cues are inversely correlated with stability. Using stethoscopes to promote meaningful feature extraction increases performance from 51% to 90% prediction accuracy. Conversely, training on an easy dataset where visual cues are positively correlated with stability, the baseline model learns a bias leading to poor performance on a harder dataset. Using an adversarial stethoscope, the network is successfully de-biased, leading to a performance increase from 66% to 88%. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BylctiCctX |
| https://openreview.net/pdf?id=BylctiCctX | |
| PWC | https://paperswithcode.com/paper/guiding-physical-intuition-with-neural |
| Repo | |
| Framework | |
