Paper Group NANR 263
A Variational Pan-Sharpening With Local Gradient Constraints. Learning what and where to attend with humans in the loop. Development of a General Purpose Sentiment Lexicon for Igbo Language. Comparison of temporal, technical and cognitive dimension measurements for post-editing effort. Augmenting Named Entity Recognition with Commonsense Knowledge. …
A Variational Pan-Sharpening With Local Gradient Constraints
| Title | A Variational Pan-Sharpening With Local Gradient Constraints |
| Authors | Xueyang Fu, Zihuang Lin, Yue Huang, Xinghao Ding |
| Abstract | Pan-sharpening aims at fusing spectral and spatial information, which are respectively contained in the multispectral (MS) image and panchromatic (PAN) image, to produce a high resolution multi-spectral (HRMS) image. In this paper, a new variational model based on a local gradient constraint for pan-sharpening is proposed. Different with previous methods that only use global constraints to preserve spatial information, we first consider gradient difference of PAN and HRMS images in different local patches and bands. Then a more accurate spatial preservation based on local gradient constraints is incorporated into the objective to fully utilize spatial information contained in the PAN image. The objective is formulated as a convex optimization problem which minimizes two leastsquares terms and thus very simple and easy to implement. A fast algorithm is also designed to improve efficiency. Experiments show that our method outperforms previous variational algorithms and achieves better generalization than recent deep learning methods. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Fu_A_Variational_Pan-Sharpening_With_Local_Gradient_Constraints_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Fu_A_Variational_Pan-Sharpening_With_Local_Gradient_Constraints_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-variational-pan-sharpening-with-local |
| Repo | |
| Framework | |
Learning what and where to attend with humans in the loop
| Title | Learning what and where to attend with humans in the loop |
| Authors | Drew Linsley, Dan Shiebler, Sven Eberhardt, Thomas Serre |
| Abstract | Most recent gains in visual recognition have originated from the inclusion of attention mechanisms in deep convolutional networks (DCNs). Because these networks are optimized for object recognition, they learn where to attend using only a weak form of supervision derived from image class labels. Here, we demonstrate the benefit of using stronger supervisory signals by teaching DCNs to attend to image regions that humans deem important for object recognition. We first describe a large-scale online experiment (ClickMe) used to supplement ImageNet with nearly half a million human-derived “top-down” attention maps. Using human psychophysics, we confirm that the identified top-down features from ClickMe are more diagnostic than “bottom-up” saliency features for rapid image categorization. As a proof of concept, we extend a state-of-the-art attention network and demonstrate that adding ClickMe supervision significantly improves its accuracy and yields visual features that are more interpretable and more similar to those used by human observers. |
| Tasks | Image Categorization, Object Recognition |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJgLg3R9KQ |
| https://openreview.net/pdf?id=BJgLg3R9KQ | |
| PWC | https://paperswithcode.com/paper/learning-what-and-where-to-attend-with-humans |
| Repo | |
| Framework | |
Development of a General Purpose Sentiment Lexicon for Igbo Language
| Title | Development of a General Purpose Sentiment Lexicon for Igbo Language |
| Authors | Emeka Ogbuju, Moses Onyesolu |
| Abstract | There are publicly available general purpose sentiment lexicons in some high resource languages but very few exist in the low resource languages. This makes it difficult to directly perform sentiment analysis tasks in such languages. The objective of this work is to create a general purpose sentiment lexicon for Igbo language that can determine the sentiment of documents written in Igbo language without having to translate it to English language. The material used was an automatically translated Liu{'}s lexicon and manual addition of Igbo native words. The result of this work is a general purpose lexicon {–} IgboSentilex. The performance was tested on the BBC Igbo news channel. It returned an average polarity agreement of 95{%} with other general purpose sentiment lexicons. |
| Tasks | Sentiment Analysis |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3601/ |
| https://www.aclweb.org/anthology/W19-3601 | |
| PWC | https://paperswithcode.com/paper/development-of-a-general-purpose-sentiment |
| Repo | |
| Framework | |
Comparison of temporal, technical and cognitive dimension measurements for post-editing effort
| Title | Comparison of temporal, technical and cognitive dimension measurements for post-editing effort |
| Authors | Cristina Cumbreno, Nora Aranberri |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7003/ |
| https://www.aclweb.org/anthology/W19-7003 | |
| PWC | https://paperswithcode.com/paper/comparison-of-temporal-technical-and |
| Repo | |
| Framework | |
Augmenting Named Entity Recognition with Commonsense Knowledge
| Title | Augmenting Named Entity Recognition with Commonsense Knowledge |
| Authors | Gaith Dekhili, Tan Ngoc Le, Fatiha Sadat |
| Abstract | Commonsense can be vital in some applications like Natural Language Understanding (NLU), where it is often required to resolve ambiguity arising from implicit knowledge and underspecification. In spite of the remarkable success of neural network approaches on a variety of Natural Language Processing tasks, many of them struggle to react effectively in cases that require commonsense knowledge. In the present research, we take advantage of the availability of the open multilingual knowledge graph ConceptNet, by using it as an additional external resource in Named Entity Recognition (NER). Our proposed architecture involves BiLSTM layers combined with a CRF layer that was augmented with some features such as pre-trained word embedding layers and dropout layers. Moreover, apart from using word representations, we used also character-based representation to capture the morphological and the orthographic information. Our experiments and evaluations showed an improvement in the overall performance with +2.86 in the F1-measure. Commonsense reasonnig has been employed in other studies and NLP tasks but to the best of our knowledge, there is no study relating the integration of a commonsense knowledge base in NER. |
| Tasks | Named Entity Recognition |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3644/ |
| https://www.aclweb.org/anthology/W19-3644 | |
| PWC | https://paperswithcode.com/paper/augmenting-named-entity-recognition-with |
| Repo | |
| Framework | |
Overcoming Catastrophic Forgetting via Model Adaptation
| Title | Overcoming Catastrophic Forgetting via Model Adaptation |
| Authors | Wenpeng Hu, Zhou Lin, Bing Liu, Chongyang Tao, Zhengwei Tao, Jinwen Ma, Dongyan Zhao, Rui Yan |
| Abstract | Learning multiple tasks sequentially is important for the development of AI and lifelong learning systems. However, standard neural network architectures suffer from catastrophic forgetting which makes it difficult to learn a sequence of tasks. Several continual learning methods have been proposed to address the problem. In this paper, we propose a very different approach, called model adaptation, to dealing with the problem. The proposed approach learns to build a model, called the solver, with two sets of parameters. The first set is shared by all tasks learned so far and the second set is dynamically generated to adapt the solver to suit each individual test example in order to classify it. Extensive experiments have been carried out to demonstrate the effectiveness of the proposed approach. |
| Tasks | Continual Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ryGvcoA5YX |
| https://openreview.net/pdf?id=ryGvcoA5YX | |
| PWC | https://paperswithcode.com/paper/overcoming-catastrophic-forgetting-via-model |
| Repo | |
| Framework | |
Kernel RNN Learning (KeRNL)
| Title | Kernel RNN Learning (KeRNL) |
| Authors | Christopher Roth, Ingmar Kanitscheider, Ila Fiete |
| Abstract | We describe Kernel RNN Learning (KeRNL), a reduced-rank, temporal eligibility trace-based approximation to backpropagation through time (BPTT) for training recurrent neural networks (RNNs) that gives competitive performance to BPTT on long time-dependence tasks. The approximation replaces a rank-4 gradient learning tensor, which describes how past hidden unit activations affect the current state, by a simple reduced-rank product of a sensitivity weight and a temporal eligibility trace. In this structured approximation motivated by node perturbation, the sensitivity weights and eligibility kernel time scales are themselves learned by applying perturbations. The rule represents another step toward biologically plausible or neurally inspired ML, with lower complexity in terms of relaxed architectural requirements (no symmetric return weights), a smaller memory demand (no unfolding and storage of states over time), and a shorter feedback time. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ryGfnoC5KQ |
| https://openreview.net/pdf?id=ryGfnoC5KQ | |
| PWC | https://paperswithcode.com/paper/kernel-rnn-learning-kernl |
| Repo | |
| Framework | |
Transition-based DRS Parsing Using Stack-LSTMs
| Title | Transition-based DRS Parsing Using Stack-LSTMs |
| Authors | Kilian Evang |
| Abstract | We present our submission to the IWCS 2019 shared task on semantic parsing, a transition-based parser that uses explicit word-meaning pairings, but no explicit representation of syntax. Parsing decisions are made based on vector representations of parser states, encoded via stack-LSTMs (Ballesteros et al., 2017), as well as some heuristic rules. Our system reaches 70.88{%} f-score in the competition. |
| Tasks | Semantic Parsing |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-1202/ |
| https://www.aclweb.org/anthology/W19-1202 | |
| PWC | https://paperswithcode.com/paper/transition-based-drs-parsing-using-stack |
| Repo | |
| Framework | |
Learning to Control Visual Abstractions for Structured Exploration in Deep Reinforcement Learning
| Title | Learning to Control Visual Abstractions for Structured Exploration in Deep Reinforcement Learning |
| Authors | catalin ionescu, tejas kulkarni, aaron van de oord, andriy mnih, vlad mnih |
| Abstract | Exploration in environments with sparse rewards is a key challenge for reinforcement learning. How do we design agents with generic inductive biases so that they can explore in a consistent manner instead of just using local exploration schemes like epsilon-greedy? We propose an unsupervised reinforcement learning agent which learns a discrete pixel grouping model that preserves spatial geometry of the sensors and implicitly of the environment as well. We use this representation to derive geometric intrinsic reward functions, like centroid coordinates and area, and learn policies to control each one of them with off-policy learning. These policies form a basis set of behaviors (options) which allows us explore in a consistent way and use them in a hierarchical reinforcement learning setup to solve for extrinsically defined rewards. We show that our approach can scale to a variety of domains with competitive performance, including navigation in 3D environments and Atari games with sparse rewards. |
| Tasks | Atari Games, Hierarchical Reinforcement Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJlWXhC5Km |
| https://openreview.net/pdf?id=HJlWXhC5Km | |
| PWC | https://paperswithcode.com/paper/learning-to-control-visual-abstractions-for |
| Repo | |
| Framework | |
Select Via Proxy: Efficient Data Selection For Training Deep Networks
| Title | Select Via Proxy: Efficient Data Selection For Training Deep Networks |
| Authors | Cody Coleman, Stephen Mussmann, Baharan Mirzasoleiman, Peter Bailis, Percy Liang, Jure Leskovec, Matei Zaharia |
| Abstract | At internet scale, applications collect a tremendous amount of data by logging user events, analyzing text, and collecting images. This data powers a variety of machine learning models for tasks such as image classification, language modeling, content recommendation, and advertising. However, training large models over all available data can be computationally expensive, creating a bottleneck in the development of new machine learning models. In this work, we develop a novel approach to efficiently select a subset of training data to achieve faster training with no loss in model predictive performance. In our approach, we first train a small proxy model quickly, which we then use to estimate the utility of individual training data points, and then select the most informative ones for training the large target model. Extensive experiments show that our approach leads to a 1.6x and 1.8x speed-up on CIFAR10 and SVHN by selecting 60% and 50% subsets of the data, while maintaining the predictive performance of the model trained on the entire dataset. |
| Tasks | Image Classification, Language Modelling |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ryzHXnR5Y7 |
| https://openreview.net/pdf?id=ryzHXnR5Y7 | |
| PWC | https://paperswithcode.com/paper/select-via-proxy-efficient-data-selection-for |
| Repo | |
| Framework | |
Maximum Expected Hitting Cost of a Markov Decision Process and Informativeness of Rewards
| Title | Maximum Expected Hitting Cost of a Markov Decision Process and Informativeness of Rewards |
| Authors | Falcon Dai, Matthew Walter |
| Abstract | We propose a new complexity measure for Markov decision processes (MDPs), the maximum expected hitting cost (MEHC). This measure tightens the closely related notion of diameter [JOA10] by accounting for the reward structure. We show that this parameter replaces diameter in the upper bound on the optimal value span of an extended MDP, thus refining the associated upper bounds on the regret of several UCRL2-like algorithms. Furthermore, we show that potential-based reward shaping [NHR99] can induce equivalent reward functions with varying informativeness, as measured by MEHC. By analyzing the change in the maximum expected hitting cost, this work presents a formal understanding of the effect of potential-based reward shaping on regret (and sample complexity) in the undiscounted average reward setting. We further establish that shaping can reduce or increase MEHC by at most a factor of two in a large class of MDPs with finite MEHC and unsaturated optimal average rewards. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8984-maximum-expected-hitting-cost-of-a-markov-decision-process-and-informativeness-of-rewards |
| http://papers.nips.cc/paper/8984-maximum-expected-hitting-cost-of-a-markov-decision-process-and-informativeness-of-rewards.pdf | |
| PWC | https://paperswithcode.com/paper/maximum-expected-hitting-cost-of-a-markov-1 |
| Repo | |
| Framework | |
Adaptively Denoising Proposal Collection forWeakly Supervised Object Localization
| Title | Adaptively Denoising Proposal Collection forWeakly Supervised Object Localization |
| Authors | Wenju Xu, Yuanwei Wu, Wenchi Ma, Guanghui Wang |
| Abstract | In this paper, we address the problem of weakly supervisedobject localization (WSL), which trains a detection network on the datasetwith only image-level annotations. The proposed approach is built on theobservation that the proposal set from the training dataset is a collectionof background, object parts, and objects. Several strategies are taken toadaptively eliminate the noisy proposals and generate pseudo object-levelannotations for the weakly labeled dataset. A multiple instance learning(MIL) algorithm enhanced by mask-out strategy is adopted to collect theclass-specific object proposals, which are then utilized to adapt a pre-trained classification network to a detection network. In addition, thedetection results from the detection network are re-weighted by jointlyconsidering the detection scores and the overlap ratio of proposals in aproposal subset optimization framework. The optimal proposals work asobject-level labels that enable a pseudo-strongly supervised dataset fortraining the detection network. Consequently, we establish a fully adap-tive detection network. Extensive evaluations on the PASCAL VOC 2007and 2012 datasets demonstrate a significant improvement compared withthe state-of-the-art methods. |
| Tasks | Denoising, Multiple Instance Learning, Object Localization, Weakly Supervised Object Detection |
| Published | 2019-10-04 |
| URL | https://arxiv.org/1910.02101 |
| https://arxiv.org/pdf/1910.02101.pdf | |
| PWC | https://paperswithcode.com/paper/adaptively-denoising-proposal-collection |
| Repo | |
| Framework | |
Möbius Transformation for Fast Inner Product Search on Graph
| Title | Möbius Transformation for Fast Inner Product Search on Graph |
| Authors | Zhixin Zhou, Shulong Tan, Zhaozhuo Xu, Ping Li |
| Abstract | We present a fast search on graph algorithm for Maximum Inner Product Search (MIPS). This optimization problem is challenging since traditional Approximate Nearest Neighbor (ANN) search methods may not perform efficiently in the non-metric similarity measure. Our proposed method is based on the property that Möbius transformation introduces an isomorphism between a subgraph of l^2-Delaunay graph and Delaunay graph for inner product. Under this observation, we propose a simple but novel graph indexing and searching algorithm to find the optimal solution with the largest inner product with the query. Experiments show our approach leads to significant improvements compared to existing methods. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9032-mobius-transformation-for-fast-inner-product-search-on-graph |
| http://papers.nips.cc/paper/9032-mobius-transformation-for-fast-inner-product-search-on-graph.pdf | |
| PWC | https://paperswithcode.com/paper/mobius-transformation-for-fast-inner-product |
| Repo | |
| Framework | |
AdaNSP: Uncertainty-driven Adaptive Decoding in Neural Semantic Parsing
| Title | AdaNSP: Uncertainty-driven Adaptive Decoding in Neural Semantic Parsing |
| Authors | Xiang Zhang, Shizhu He, Kang Liu, Jun Zhao |
| Abstract | Neural semantic parsers utilize the encoder-decoder framework to learn an end-to-end model for semantic parsing that transduces a natural language sentence to the formal semantic representation. To keep the model aware of the underlying grammar in target sequences, many constrained decoders were devised in a multi-stage paradigm, which decode to the sketches or abstract syntax trees first, and then decode to target semantic tokens. We instead to propose an adaptive decoding method to avoid such intermediate representations. The decoder is guided by model uncertainty and automatically uses deeper computations when necessary. Thus it can predict tokens adaptively. Our model outperforms the state-of-the-art neural models and does not need any expertise like predefined grammar or sketches in the meantime. |
| Tasks | Semantic Parsing |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1418/ |
| https://www.aclweb.org/anthology/P19-1418 | |
| PWC | https://paperswithcode.com/paper/adansp-uncertainty-driven-adaptive-decoding |
| Repo | |
| Framework | |
Group-Wise Deep Object Co-Segmentation With Co-Attention Recurrent Neural Network
| Title | Group-Wise Deep Object Co-Segmentation With Co-Attention Recurrent Neural Network |
| Authors | Bo Li, Zhengxing Sun, Qian Li, Yunjie Wu, Anqi Hu |
| Abstract | Effective feature representations which should not only express the images individual properties, but also reflect the interaction among group images are essentially crucial for real-world co-segmentation. This paper proposes a novel end-to-end deep learning approach for group-wise object co-segmentation with a recurrent network architecture. Specifically, the semantic features extracted from a pre-trained CNN of each image are first processed by single image representation branch to learn the unique properties. Meanwhile, a specially designed Co-Attention Recurrent Unit (CARU) recurrently explores all images to generate the final group representation by using the co-attention between images, and simultaneously suppresses noisy information. The group feature which contains synergetic information is broadcasted to each individual image and fused with multi-scale fine-resolution features to facilitate the inferring of co-segmentation. Moreover, we propose a groupwise training objective to utilize the co-object similarity and figure-ground distinctness as the additional supervision. The whole modules are collaboratively optimized in an end-to-end manner, further improving the robustness of the approach. Comprehensive experiments on three benchmarks can demonstrate the superiority of our approach in comparison with the state-of-the-art methods. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Li_Group-Wise_Deep_Object_Co-Segmentation_With_Co-Attention_Recurrent_Neural_Network_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Li_Group-Wise_Deep_Object_Co-Segmentation_With_Co-Attention_Recurrent_Neural_Network_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/group-wise-deep-object-co-segmentation-with |
| Repo | |
| Framework | |
