Paper Group ANR 948
Early recurrence enables figure border ownership. Post-Earthquake Assessment of Buildings Using Deep Learning. Learning from Multiple Complementary Labels. Private Learning Implies Online Learning: An Efficient Reduction. Dual Adversarial Co-Learning for Multi-Domain Text Classification. Void region segmentation in ball grid array using u-net appro …
Early recurrence enables figure border ownership
| Title | Early recurrence enables figure border ownership |
| Authors | Paria Mehrani, John K. Tsotsos |
| Abstract | The face-vase illusion introduced by Rubin demonstrates how one can switch back and forth between two different interpretations depending on how the figure outlines are assigned [1]. This border ownership assignment is an important step in the perception of forms. Zhou et al. [2] found neurons in the visual cortex whose responses not only depend on the local features present in their classical receptive fields, but also on their contextual information. Various models proposed that feedback from higher ventral areas or lateral connections could provide the required contextual information. However, some studies [3, 4, 5] ruled out the plausibility of models exclusively based on lateral connections. In addition, further evidence [6] suggests that ventral feedback even from V4 is not fast enough to provide context to border ownership neurons in either V1 or V2. As a result, the border ownership assignment mechanism in the brain is a mystery yet to be solved. Here, we test with computational simulations the hypothesis that the dorsal stream provides the global information to border ownership cells in the ventral stream. Our proposed model incorporates early recurrence from the dorsal pathway as well as lateral modulations within the ventral stream. Our simulation experiments show that our model border ownership neurons, similar to their biological counterparts, exhibit different responses to figures on either side of the border. |
| Tasks | |
| Published | 2019-01-10 |
| URL | https://arxiv.org/abs/1901.03201v2 |
| https://arxiv.org/pdf/1901.03201v2.pdf | |
| PWC | https://paperswithcode.com/paper/early-recurrence-enables-figure-border |
| Repo | |
| Framework | |
Post-Earthquake Assessment of Buildings Using Deep Learning
| Title | Post-Earthquake Assessment of Buildings Using Deep Learning |
| Authors | Dhananjay Nahata, Harish Kumar Mulchandani, Suraj Bansal, G Muthukumar |
| Abstract | Classification of the extent of damage suffered by a building in a seismic event is crucial from the safety perspective and repairing work. In this study, authors have proposed a CNN based autonomous damage detection model. Over 1200 images of different types of buildings-1000 for training and 200 for testing classified into 4 categories according to the extent of damage suffered. Categories are namely, no damage, minor damage, major damage, and collapse. Trained network tested by the application of various algorithms with different learning rates. The most optimum results were obtained on the application of VGG16 transfer learning model with a learning rate of 1e-5 as it gave a training accuracy of 97.85% and validation accuracy of up to 89.38%. The model developed has real-time application in the event of an earthquake. |
| Tasks | Transfer Learning |
| Published | 2019-07-18 |
| URL | https://arxiv.org/abs/1907.07877v1 |
| https://arxiv.org/pdf/1907.07877v1.pdf | |
| PWC | https://paperswithcode.com/paper/post-earthquake-assessment-of-buildings-using |
| Repo | |
| Framework | |
Learning from Multiple Complementary Labels
| Title | Learning from Multiple Complementary Labels |
| Authors | Lei Feng, Bo An |
| Abstract | Complementary-label learning is a new weakly-supervised learning framework that solves the problem where each training example is supplied with a complementary label, which only specifies one of the classes that the example does \textsl{not} belong to. Although a few works have demonstrated that an unbiased estimator of the original classification risk can be obtained from only complementarily labeled data, they are all restricted to the case where each example is associated with exactly one complementary label. It would be more promising to learn from multiple complementary labels simultaneously, as the supervision information would be richer if more complementary labels are provided. So far, whether there exists an unbiased risk estimator for learning from multiple complementary labels simultaneously is still unknown. In this paper, we will give an affirmative answer by deriving the first unbiased risk estimator for learning from multiple complementary labels. In addition, we further theoretically analyze the estimation error bound of our proposed approach, and show that the optimal parametric convergence rate is achieved. Finally, we experimentally demonstrate the effectiveness of the proposed approach. |
| Tasks | |
| Published | 2019-12-30 |
| URL | https://arxiv.org/abs/1912.12927v1 |
| https://arxiv.org/pdf/1912.12927v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-multiple-complementary-labels |
| Repo | |
| Framework | |
Private Learning Implies Online Learning: An Efficient Reduction
| Title | Private Learning Implies Online Learning: An Efficient Reduction |
| Authors | Alon Gonen, Elad Hazan, Shay Moran |
| Abstract | We study the relationship between the notions of differentially private learning and online learning in games. Several recent works have shown that differentially private learning implies online learning, but an open problem of Neel, Roth, and Wu \cite{NeelAaronRoth2018} asks whether this implication is {\it efficient}. Specifically, does an efficient differentially private learner imply an efficient online learner? In this paper we resolve this open question in the context of pure differential privacy. We derive an efficient black-box reduction from differentially private learning to online learning from expert advice. |
| Tasks | |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11311v4 |
| https://arxiv.org/pdf/1905.11311v4.pdf | |
| PWC | https://paperswithcode.com/paper/private-learning-implies-online-learning-an |
| Repo | |
| Framework | |
Dual Adversarial Co-Learning for Multi-Domain Text Classification
| Title | Dual Adversarial Co-Learning for Multi-Domain Text Classification |
| Authors | Yuan Wu, Yuhong Guo |
| Abstract | In this paper we propose a novel dual adversarial co-learning approach for multi-domain text classification (MDTC). The approach learns shared-private networks for feature extraction and deploys dual adversarial regularizations to align features across different domains and between labeled and unlabeled data simultaneously under a discrepancy based co-learning framework, aiming to improve the classifiers’ generalization capacity with the learned features. We conduct experiments on multi-domain sentiment classification datasets. The results show the proposed approach achieves the state-of-the-art MDTC performance. |
| Tasks | Sentiment Analysis, Text Classification |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1909.08203v1 |
| https://arxiv.org/pdf/1909.08203v1.pdf | |
| PWC | https://paperswithcode.com/paper/dual-adversarial-co-learning-for-multi-domain |
| Repo | |
| Framework | |
Void region segmentation in ball grid array using u-net approach and synthetic data
| Title | Void region segmentation in ball grid array using u-net approach and synthetic data |
| Authors | Vijay Kumar Neeluru, Vikas Ahuja |
| Abstract | The quality inspection of solder balls by detecting and measuring the void is important to improve the board yield issues in electronic circuits. In general, the inspection is carried out manually, based on 2D or 3D X-ray images. For high quality inspection, it is difficult to detect and measure voids accurately with high repeatability through the manual inspection and the process is time consuming. In need of high quality and fast inspection, various approaches were proposed, but, due to the various challenges like vias, reflections from the plating or vias, inconsistent lighting, noise and void-like artifacts makes these approaches difficult to work in all these challenging conditions. In recent times, deep learning approaches are providing the outstanding accuracy in various computer vision tasks. Considering the need of high quality and fast inspection, in this paper, we applied U-Net to segment the void regions in soldering balls. As it is difficult to get the annotated dataset covering all the variations of void, we proposed an approach to generated the synthetic dataset. The proposed approach is able to segment the voids and can be easily scaled to various electronic products. |
| Tasks | |
| Published | 2019-07-07 |
| URL | https://arxiv.org/abs/1907.04222v1 |
| https://arxiv.org/pdf/1907.04222v1.pdf | |
| PWC | https://paperswithcode.com/paper/void-region-segmentation-in-ball-grid-array |
| Repo | |
| Framework | |
Multi-Label Learning with Deep Forest
| Title | Multi-Label Learning with Deep Forest |
| Authors | Liang Yang, Xi-Zhu Wu, Yuan Jiang, Zhi-Hua Zhou |
| Abstract | In multi-label learning, each instance is associated with multiple labels and the crucial task is how to leverage label correlations in building models. Deep neural network methods usually jointly embed the feature and label information into a latent space to exploit label correlations. However, the success of these methods highly depends on the precise choice of model depth. Deep forest is a recent deep learning framework based on tree model ensembles, which does not rely on backpropagation. We consider the advantages of deep forest models are very appropriate for solving multi-label problems. Therefore we design the Multi-Label Deep Forest (MLDF) method with two mechanisms: measure-aware feature reuse and measure-aware layer growth. The measure-aware feature reuse mechanism reuses the good representation in the previous layer guided by confidence. The measure-aware layer growth mechanism ensures MLDF gradually increase the model complexity by performance measure. MLDF handles two challenging problems at the same time: one is restricting the model complexity to ease the overfitting issue; another is optimizing the performance measure on user’s demand since there are many different measures in the multi-label evaluation. Experiments show that our proposal not only beats the compared methods over six measures on benchmark datasets but also enjoys label correlation discovery and other desired properties in multi-label learning. |
| Tasks | Multi-Label Learning |
| Published | 2019-11-15 |
| URL | https://arxiv.org/abs/1911.06557v1 |
| https://arxiv.org/pdf/1911.06557v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-label-learning-with-deep-forest |
| Repo | |
| Framework | |
Multi-attention Networks for Temporal Localization of Video-level Labels
| Title | Multi-attention Networks for Temporal Localization of Video-level Labels |
| Authors | Lijun Zhang, Srinath Nizampatnam, Ahana Gangopadhyay, Marcos V. Conde |
| Abstract | Temporal localization remains an important challenge in video understanding. In this work, we present our solution to the 3rd YouTube-8M Video Understanding Challenge organized by Google Research. Participants were required to build a segment-level classifier using a large-scale training data set with noisy video-level labels and a relatively small-scale validation data set with accurate segment-level labels. We formulated the problem as a multiple instance multi-label learning and developed an attention-based mechanism to selectively emphasize the important frames by attention weights. The model performance is further improved by constructing multiple sets of attention networks. We further fine-tuned the model using the segment-level data set. Our final model consists of an ensemble of attention/multi-attention networks, deep bag of frames models, recurrent neural networks and convolutional neural networks. It ranked 13th on the private leader board and stands out for its efficient usage of resources. |
| Tasks | Multi-Label Learning, Temporal Localization, Video Understanding |
| Published | 2019-11-15 |
| URL | https://arxiv.org/abs/1911.06866v1 |
| https://arxiv.org/pdf/1911.06866v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-attention-networks-for-temporal |
| Repo | |
| Framework | |
Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology
| Title | Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology |
| Authors | Ran Zmigrod, Sabrina J. Mielke, Hanna Wallach, Ryan Cotterell |
| Abstract | Gender stereotypes are manifest in most of the world’s languages and are consequently propagated or amplified by NLP systems. Although research has focused on mitigating gender stereotypes in English, the approaches that are commonly employed produce ungrammatical sentences in morphologically rich languages. We present a novel approach for converting between masculine-inflected and feminine-inflected sentences in such languages. For Spanish and Hebrew, our approach achieves F1 scores of 82% and 73% at the level of tags and accuracies of 90% and 87% at the level of forms. By evaluating our approach using four different languages, we show that, on average, it reduces gender stereotyping by a factor of 2.5 without any sacrifice to grammaticality. |
| Tasks | Data Augmentation |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04571v2 |
| https://arxiv.org/pdf/1906.04571v2.pdf | |
| PWC | https://paperswithcode.com/paper/counterfactual-data-augmentation-for |
| Repo | |
| Framework | |
Adversarial Partial Multi-Label Learning
| Title | Adversarial Partial Multi-Label Learning |
| Authors | Yan Yan, Yuhong Guo |
| Abstract | Partial multi-label learning (PML), which tackles the problem of learning multi-label prediction models from instances with overcomplete noisy annotations, has recently started gaining attention from the research community. In this paper, we propose a novel adversarial learning model, PML-GAN, under a generalized encoder-decoder framework for partial multi-label learning. The PML-GAN model uses a disambiguation network to identify noisy labels and uses a multi-label prediction network to map the training instances to the disambiguated label vectors, while deploying a generative adversarial network as an inverse mapping from label vectors to data samples in the input feature space. The learning of the overall model corresponds to a minimax adversarial game, which enhances the correspondence of input features with the output labels. Extensive experiments are conducted on multiple datasets, while the proposed model demonstrates the state-of-the-art performance for partial multi-label learning. |
| Tasks | Multi-Label Learning |
| Published | 2019-09-15 |
| URL | https://arxiv.org/abs/1909.06717v1 |
| https://arxiv.org/pdf/1909.06717v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-partial-multi-label-learning |
| Repo | |
| Framework | |
A General Early-Stopping Module for Crowdsourced Ranking
| Title | A General Early-Stopping Module for Crowdsourced Ranking |
| Authors | Caihua Shan, Leong Hou U, Nikos Mamoulis, Reynold Cheng, Xiang Li |
| Abstract | Crowdsourcing can be used to determine a total order for an object set (e.g., the top-10 NBA players) based on crowd opinions. This ranking problem is often decomposed into a set of microtasks (e.g., pairwise comparisons). These microtasks are passed to a large number of workers and their answers are aggregated to infer the ranking. The number of microtasks depends on the budget allocated for the problem. Intuitively, the higher the number of microtask answers, the more accurate the ranking becomes. However, it is often hard to decide the budget required for an accurate ranking. We study how a ranking process can be terminated early, and yet achieve a high-quality ranking and great savings in the budget. We use statistical tools to estimate the quality of the ranking result at any stage of the crowdsourcing process and terminate the process as soon as the desired quality is achieved. Our proposed early-stopping module can be seamlessly integrated with most existing inference algorithms and task assignment methods. We conduct extensive experiments and show that our early-stopping module is better than other existing general stopping criteria. We also implement a prototype system to demonstrate the usability and effectiveness of our approach in practice. |
| Tasks | |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01042v1 |
| https://arxiv.org/pdf/1911.01042v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-general-early-stopping-module-for |
| Repo | |
| Framework | |
Trainable Projected Gradient Detector for Sparsely Spread Code Division Multiple Access
| Title | Trainable Projected Gradient Detector for Sparsely Spread Code Division Multiple Access |
| Authors | Satoshi Takabe, Yuki Yamauchi, Tadashi Wadayama |
| Abstract | Sparsely spread code division multiple access (SCDMA) is a promising non-orthogonal multiple access technique for future wireless communications. In this paper, we propose a novel trainable multiuser detector called sparse trainable projected gradient (STPG) detector, which is based on the notion of deep unfolding. In the STPG detector, trainable parameters are embedded to a projected gradient descent algorithm, which can be trained by standard deep learning techniques such as back propagation and stochastic gradient descent. Advantages of the detector are its low computational cost and small number of trainable parameters, which enables us to treat massive SCDMA systems. In particular, its computational cost is smaller than a conventional belief propagation (BP) detector while the STPG detector exhibits nearly same detection performance with a BP detector. We also propose a scalable joint learning of signature sequences and the STPG detector for signature design. Numerical results show that the joint learning improves multiuser detection performance particular in the low SNR regime. |
| Tasks | |
| Published | 2019-10-23 |
| URL | https://arxiv.org/abs/1910.10336v1 |
| https://arxiv.org/pdf/1910.10336v1.pdf | |
| PWC | https://paperswithcode.com/paper/trainable-projected-gradient-detector-for-1 |
| Repo | |
| Framework | |
Generalized Momentum-Based Methods: A Hamiltonian Perspective
| Title | Generalized Momentum-Based Methods: A Hamiltonian Perspective |
| Authors | Jelena Diakonikolas, Michael I. Jordan |
| Abstract | We take a Hamiltonian-based perspective to generalize Nesterov’s accelerated gradient descent and Polyak’s heavy ball method to a broad class of momentum methods in the setting of (possibly) constrained minimization in Banach spaces. Our perspective leads to a generic and unifying non-asymptotic analysis of convergence of these methods in both the function value (in the setting of convex optimization) and in the norm of the gradient (in the setting of unconstrained, possibly nonconvex, optimization). The convergence analysis is intuitive and based on the conserved quantities of the time-dependent Hamiltonian that we introduce and that produces generalized momentum methods as its equations of motion. |
| Tasks | |
| Published | 2019-06-02 |
| URL | https://arxiv.org/abs/1906.00436v2 |
| https://arxiv.org/pdf/1906.00436v2.pdf | |
| PWC | https://paperswithcode.com/paper/190600436 |
| Repo | |
| Framework | |
Defending Adversarial Attacks by Correcting logits
| Title | Defending Adversarial Attacks by Correcting logits |
| Authors | Yifeng Li, Lingxi Xie, Ya Zhang, Rui Zhang, Yanfeng Wang, Qi Tian |
| Abstract | Generating and eliminating adversarial examples has been an intriguing topic in the field of deep learning. While previous research verified that adversarial attacks are often fragile and can be defended via image-level processing, it remains unclear how high-level features are perturbed by such attacks. We investigate this issue from a new perspective, which purely relies on logits, the class scores before softmax, to detect and defend adversarial attacks. Our defender is a two-layer network trained on a mixed set of clean and perturbed logits, with the goal being recovering the original prediction. Upon a wide range of adversarial attacks, our simple approach shows promising results with relatively high accuracy in defense, and the defender can transfer across attackers with similar properties. More importantly, our defender can work in the scenarios that image data are unavailable, and enjoys high interpretability especially at the semantic level. |
| Tasks | |
| Published | 2019-06-26 |
| URL | https://arxiv.org/abs/1906.10973v1 |
| https://arxiv.org/pdf/1906.10973v1.pdf | |
| PWC | https://paperswithcode.com/paper/defending-adversarial-attacks-by-correcting |
| Repo | |
| Framework | |
Bootstrapping Method for Developing Part-of-Speech Tagged Corpus in Low Resource Languages Tagset - A Focus on an African Igbo
| Title | Bootstrapping Method for Developing Part-of-Speech Tagged Corpus in Low Resource Languages Tagset - A Focus on an African Igbo |
| Authors | Onyenwe Ikechukwu E, Onyedinma Ebele G, Aniegwu Godwin E, Ezeani Ignatius M |
| Abstract | Most languages, especially in Africa, have fewer or no established part-of-speech (POS) tagged corpus. However, POS tagged corpus is essential for natural language processing (NLP) to support advanced researches such as machine translation, speech recognition, etc. Even in cases where there is no POS tagged corpus, there are some languages for which parallel texts are available online. The task of POS tagging a new language corpus with a new tagset usually face a bootstrapping problem at the initial stages of the annotation process. The unavailability of automatic taggers to help the human annotator makes the annotation process to appear infeasible to quickly produce adequate amounts of POS tagged corpus for advanced NLP research and training the taggers. In this paper, we demonstrate the efficacy of a POS annotation method that employed the services of two automatic approaches to assist POS tagged corpus creation for a novel language in NLP. The two approaches are cross-lingual and monolingual POS tags projection. We used cross-lingual to automatically create an initial ‘errorful’ tagged corpus for a target language via word-alignment. The resources for creating this are derived from a source language rich in NLP resources. A monolingual method is applied to clean the induce noise via an alignment process and to transform the source language tags to the target language tags. We used English and Igbo as our case study. This is possible because there are parallel texts that exist between English and Igbo, and the source language English has available NLP resources. The results of the experiment show a steady improvement in accuracy and rate of tags transformation with score ranges of 6.13% to 83.79% and 8.67% to 98.37% respectively. The rate of tags transformation evaluates the rate at which source language tags are translated to target language tags. |
| Tasks | Machine Translation, Speech Recognition, Word Alignment |
| Published | 2019-03-12 |
| URL | http://arxiv.org/abs/1903.05225v1 |
| http://arxiv.org/pdf/1903.05225v1.pdf | |
| PWC | https://paperswithcode.com/paper/bootstrapping-method-for-developing-part-of |
| Repo | |
| Framework | |
