Paper Group NAWR 8
Non-Uniform Subset Selection for Active Learning in Structured Data. A Neural Local Coherence Model. L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space. Powered Outer Probabilistic Clustering. State-Frequency Memory Recurrent Neural Networks. Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data. Impr …
Non-Uniform Subset Selection for Active Learning in Structured Data
| Title | Non-Uniform Subset Selection for Active Learning in Structured Data |
| Authors | Sujoy Paul, Jawadul H. Bappy, Amit Roy-Chowdhury |
| Abstract | Several works have shown that relationships between data points (i.e., context) in structured data can be exploited to obtain better recognition performance. In this paper, we explore a different, but related, problem: how can these interrelationships be used to efficiently learn and continuously update a recognition model, with minimal human labeling effort. Towards this goal, we propose an active learning framework to select an optimal subset of data points for manual labeling by exploiting the relationships between them. We construct a graph from the unlabeled data to represent the underlying structure, such that each node represents a data point, and edges represent the inter-relationships between them. Thereafter, considering the flow of beliefs in this graph, we choose those samples for labeling which minimize the joint entropy of the nodes of the graph. This results in significant reduction in manual labeling effort without compromising recognition performance. Our method chooses non-uniform number of samples from each batch of streaming data depending on its information content. Also, the submodular property of our objective function makes it computationally efficient to optimize. The proposed framework is demonstrated in various applications, including document analysis, scene-object recognition, and activity recognition. |
| Tasks | Active Learning, Activity Recognition, Object Recognition |
| Published | 2017-06-01 |
| URL | https://intra.ece.ucr.edu/~supaul/Webpage_files/CVPR2017_1.pdf |
| https://intra.ece.ucr.edu/~supaul/Webpage_files/CVPR2017_1.pdf | |
| PWC | https://paperswithcode.com/paper/non-uniform-subset-selection-for-active-1 |
| Repo | https://github.com/sujoyp/context-active-learning |
| Framework | none |
A Neural Local Coherence Model
| Title | A Neural Local Coherence Model |
| Authors | Dat Tien Nguyen, Shafiq Joty |
| Abstract | We propose a local coherence model based on a convolutional neural network that operates over the entity grid representation of a text. The model captures long range entity transitions along with entity-specific features without loosing generalization, thanks to the power of distributed representation. We present a pairwise ranking method to train the model in an end-to-end fashion on a task and learn task-specific high level features. Our evaluation on three different coherence assessment tasks demonstrates that our model achieves state of the art results outperforming existing models by a good margin. |
| Tasks | Text Generation |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1121/ |
| https://www.aclweb.org/anthology/P17-1121 | |
| PWC | https://paperswithcode.com/paper/a-neural-local-coherence-model |
| Repo | https://github.com/datienguyen/cnn_coherence |
| Framework | none |
L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space
| Title | L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space |
| Authors | Yurun Tian, Bin Fan, Fuchao Wu |
| Abstract | The research focus of designing local patch descriptors has gradually shifted from handcrafted ones (e.g., SIFT) to learned ones. In this paper, we propose to learn high per- formance descriptor in Euclidean space via the Convolu- tional Neural Network (CNN). Our method is distinctive in four aspects: (i) We propose a progressive sampling strat- egy which enables the network to access billions of train- ing samples in a few epochs. (ii) Derived from the ba- sic concept of local patch matching problem, we empha- size the relative distance between descriptors. (iii) Extra supervision is imposed on the intermediate feature maps. (iv) Compactness of the descriptor is taken into account. The proposed network is named as L2-Net since the out- put descriptor can be matched in Euclidean space by L2 distance. L2-Net achieves state-of-the-art performance on the Brown datasets [16], Oxford dataset [18] and the new- ly proposed Hpatches dataset [11]. The good generaliza- tion ability shown by experiments indicates that L2-Net can serve as a direct substitution of the existing handcrafted de- scriptors. The pre-trained L2-Net is publicly available. |
| Tasks | |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Tian_L2-Net_Deep_Learning_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Tian_L2-Net_Deep_Learning_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/l2-net-deep-learning-of-discriminative-patch |
| Repo | https://github.com/yuruntian/L2-Net |
| Framework | none |
Powered Outer Probabilistic Clustering
| Title | Powered Outer Probabilistic Clustering |
| Authors | Peter Taraba |
| Abstract | Clustering is one of the most important concepts for unsupervised learning in machine learning. While there are numerous clustering algorithms already, many, including the popular one — k-means algorithm, require the number of clusters to be specified in advance, a huge drawback. Some studies use the silhouette coefficient to determine the optimal number of clusters. In this study, we introduce a novel algorithm called Powered Outer Probabilistic Clustering, show how it works through back-propagation (starting with many clusters and ending with an optimal number of clusters), and show that the algorithm converges to the expected (optimal) number of clusters on theoretical examples. |
| Tasks | |
| Published | 2017-10-25 |
| URL | http://www.iaeng.org/publication/WCECS2017/WCECS2017_pp394-398.pdf |
| http://www.iaeng.org/publication/WCECS2017/WCECS2017_pp394-398.pdf | |
| PWC | https://paperswithcode.com/paper/powered-outer-probabilistic-clustering |
| Repo | https://github.com/pepe78/POPC-examples |
| Framework | none |
State-Frequency Memory Recurrent Neural Networks
| Title | State-Frequency Memory Recurrent Neural Networks |
| Authors | Hao Hu, Guo-Jun Qi |
| Abstract | Modeling temporal sequences plays a fundamental role in various modern applications and has drawn more and more attentions in the machine learning community. Among those efforts on improving the capability to represent temporal data, the Long Short-Term Memory (LSTM) has achieved great success in many areas. Although the LSTM can capture long-range dependency in the time domain, it does not explicitly model the pattern occurrences in the frequency domain that plays an important role in tracking and predicting data points over various time cycles. We propose the State-Frequency Memory (SFM), a novel recurrent architecture that allows to separate dynamic patterns across different frequency components and their impacts on modeling the temporal contexts of input sequences. By jointly decomposing memorized dynamics into state-frequency components, the SFM is able to offer a fine-grained analysis of temporal sequences by capturing the dependency of uncovered patterns in both time and frequency domains. Evaluations on several temporal modeling tasks demonstrate the SFM can yield competitive performances, in particular as compared with the state-of-the-art LSTM models. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=515 |
| http://proceedings.mlr.press/v70/hu17c/hu17c.pdf | |
| PWC | https://paperswithcode.com/paper/state-frequency-memory-recurrent-neural |
| Repo | https://github.com/dlarsen5/AdaptiveSFM |
| Framework | tf |
Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data
| Title | Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data |
| Authors | Jiaxuan You, Xiaocheng Li, Melvin Low, David Lobell, Stefano Ermon |
| Abstract | Agricultural monitoring, especially in developing countries, can help prevent famine and support humanitarian efforts. A central challenge is yield estimation, i.e., predicting crop yields before harvest. We introduce a scalable, accurate, and inexpensive method to predict crop yields using publicly available remote sensing data. Our approach improves existing techniques in three ways. First, we forego hand-crafted features traditionally used in the remote sensing community and propose an approach based on modern representation learning ideas. We also introduce a novel dimensionality reduction technique that allows us to train a Convolutional Neural Network or Long-short Term Memory network and automatically learn useful features even when labeled training data are scarce. Finally, we incorporate a Gaussian Process component to explicitly model the spatio-temporal structure of the data and further improve accuracy. We evaluate our approach on county-level soybean yield prediction in the U.S. and show that it outperforms competing techniques. |
| Tasks | Dimensionality Reduction, Representation Learning |
| Published | 2017-02-12 |
| URL | https://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14435 |
| https://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/viewFile/14435/14067 | |
| PWC | https://paperswithcode.com/paper/deep-gaussian-process-for-crop-yield |
| Repo | https://github.com/JiaxuanYou/crop_yield_prediction |
| Framework | tf |
Improved Word Representation Learning with Sememes
| Title | Improved Word Representation Learning with Sememes |
| Authors | Yilin Niu, Ruobing Xie, Zhiyuan Liu, Maosong Sun |
| Abstract | Sememes are minimum semantic units of word meanings, and the meaning of each word sense is typically composed by several sememes. Since sememes are not explicit for each word, people manually annotate word sememes and form linguistic common-sense knowledge bases. In this paper, we present that, word sememe information can improve word representation learning (WRL), which maps words into a low-dimensional semantic space and serves as a fundamental step for many NLP tasks. The key idea is to utilize word sememes to capture exact meanings of a word within specific contexts accurately. More specifically, we follow the framework of Skip-gram and present three sememe-encoded models to learn representations of sememes, senses and words, where we apply the attention scheme to detect word senses in various contexts. We conduct experiments on two tasks including word similarity and word analogy, and our models significantly outperform baselines. The results indicate that WRL can benefit from sememes via the attention scheme, and also confirm our models being capable of correctly modeling sememe information. |
| Tasks | Common Sense Reasoning, Language Modelling, Machine Translation, Representation Learning, Sentiment Analysis, Word Embeddings, Word Sense Disambiguation, Word Sense Induction |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1187/ |
| https://www.aclweb.org/anthology/P17-1187 | |
| PWC | https://paperswithcode.com/paper/improved-word-representation-learning-with |
| Repo | https://github.com/thunlp/SE-WRL |
| Framework | none |
3D Point Cloud Registration for Localization Using a Deep Neural Network Auto-Encoder
| Title | 3D Point Cloud Registration for Localization Using a Deep Neural Network Auto-Encoder |
| Authors | Gil Elbaz, Tamar Avraham, Anath Fischer |
| Abstract | We present an algorithm for registration between a large-scale point cloud and a close-proximity scanned point cloud, providing a localization solution that is fully independent of prior information about the initial positions of the two point cloud coordinate systems. The algorithm, denoted LORAX, selects super-points–local subsets of points–and describes the geometric structure of each with a low-dimensional descriptor. These descriptors are then used to infer potential matching regions for an efficient coarse registration process, followed by a fine-tuning stage. The set of super-points is selected by covering the point clouds with overlapping spheres, and then filtering out those of low-quality or nonsalient regions. The descriptors are computed using state-of-the-art unsupervised machine learning, utilizing the technology of deep neural network based auto-encoders. Abstract This novel framework provides a strong alternative to the common practice of using manually designed key-point descriptors for coarse point cloud registration. Utilizing super-points instead of key-points allows the available geometrical data to be better exploited to find the correct transformation. Encoding local 3D geometric structures using a deep neural network auto-encoder instead of traditional descriptors continues the trend seen in other computer vision applications and indeed leads to superior results. The algorithm is tested on challenging point cloud registration datasets, and its advantages over previous approaches as well as its robustness to density changes, noise, and missing data are shown. |
| Tasks | Point Cloud Registration |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Elbaz_3D_Point_Cloud_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Elbaz_3D_Point_Cloud_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/3d-point-cloud-registration-for-localization |
| Repo | https://github.com/gilbaz/LORAX |
| Framework | none |
A phoneme clustering algorithm based on the obligatory contour principle
| Title | A phoneme clustering algorithm based on the obligatory contour principle |
| Authors | Mans Hulden |
| Abstract | This paper explores a divisive hierarchical clustering algorithm based on the well-known Obligatory Contour Principle in phonology. The purpose is twofold: to see if such an algorithm could be used for unsupervised classification of phonemes or graphemes in corpora, and to investigate whether this purported universal constraint really holds for several classes of phonological distinctive features. The algorithm achieves very high accuracies in an unsupervised setting of inferring a consonant-vowel distinction, and also has a strong tendency to detect coronal phonemes in an unsupervised fashion. Remaining classes, however, do not correspond as neatly to phonological distinctive feature splits. While the results offer only mixed support for a universal Obligatory Contour Principle, the algorithm can be very useful for many NLP tasks due to the high accuracy in revealing consonant/vowel/coronal distinctions. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-1030/ |
| https://www.aclweb.org/anthology/K17-1030 | |
| PWC | https://paperswithcode.com/paper/a-phoneme-clustering-algorithm-based-on-the |
| Repo | https://github.com/cvocp/cvocp |
| Framework | none |
Robust Visual Tracking Using Oblique Random Forests
| Title | Robust Visual Tracking Using Oblique Random Forests |
| Authors | Le Zhang, Jagannadan Varadarajan, Ponnuthurai Nagaratnam Suganthan, Narendra Ahuja, Pierre Moulin |
| Abstract | Random forest has emerged as a powerful classification technique with promising results in various vision tasks including image classification, pose estimation and object detection. However, current techniques have shown little improvements in visual tracking as they mostly rely on piece wise orthogonal hyperplanes to create decision nodes and lack a robust incremental learning mechanism that is much needed for online tracking. In this paper, we propose a discriminative tracker based on a novel incremental oblique random forest. Unlike conventional orthogonal decision trees that use a single feature and heuristic measures to obtain a split at each node, we propose to use a more powerful proximal SVM to obtain oblique hyperplanes to capture the geometric structure of the data better. The resulting decision surface is not restricted to be axis aligned and hence has the ability to represent and classify the input data better. Furthermore, in order to generalize to online tracking scenarios, we derive incremental update steps that enable the hyperplanes in each node to be updated recursively, efficiently and in a closed-form fashion. We demonstrate the effectiveness of our method using two large scale benchmark datasets (OTB-51 and OTB-100) and show that our method gives competitive results on several challenging cases by relying on simple HOG features as well as in combination with more sophisticated deep neural network based models. The implementations of the proposed random forest are available at https://github.com/ZhangLeUestc/ Incremental-Oblique-Random-Forest. |
| Tasks | Image Classification, Object Detection, Pose Estimation, Visual Tracking |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Zhang_Robust_Visual_Tracking_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Zhang_Robust_Visual_Tracking_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/robust-visual-tracking-using-oblique-random |
| Repo | https://github.com/ZhangLeUestc/Incremental-Oblique-Random-Forest |
| Framework | none |
Bayesian GAN
| Title | Bayesian GAN |
| Authors | Yunus Saatci, Andrew G. Wilson |
| Abstract | Generative adversarial networks (GANs) can implicitly learn rich distributions over images, audio, and data which are hard to model with an explicit likelihood. We present a practical Bayesian formulation for unsupervised and semi-supervised learning with GANs. Within this framework, we use stochastic gradient Hamiltonian Monte Carlo to marginalize the weights of the generator and discriminator networks. The resulting approach is straightforward and obtains good performance without any standard interventions such as feature matching or mini-batch discrimination. By exploring an expressive posterior over the parameters of the generator, the Bayesian GAN avoids mode-collapse, produces interpretable and diverse candidate samples, and provides state-of-the-art quantitative results for semi-supervised learning on benchmarks including SVHN, CelebA, and CIFAR-10, outperforming DCGAN, Wasserstein GANs, and DCGAN ensembles. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6953-bayesian-gan |
| http://papers.nips.cc/paper/6953-bayesian-gan.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-gan-1 |
| Repo | https://github.com/andrewgordonwilson/bayesgan |
| Framework | tf |
Predicting Salient Face in Multiple-Face Videos
| Title | Predicting Salient Face in Multiple-Face Videos |
| Authors | Yufan Liu, Songyang Zhang, Mai Xu, Xuming He |
| Abstract | Although the recent success of convolutional neural network (CNN) advances state-of-the-art saliency prediction in static images, few work has addressed the problem of predicting attention in videos. On the other hand, we find that the attention of different subjects consistently focuses on a single face in each frame of videos involving multiple faces. Therefore, we propose in this paper a novel deep learning (DL) based method to predict salient face in multiple-face videos, which is capable of learning features and transition of salient faces across video frames. In particular, we first learn a CNN for each frame to locate salient face. Taking CNN features as input, we develop a multiple-stream long short-term memory (M-LSTM) network to predict the temporal transition of salient faces in video sequences. To evaluate our DL-based method, we build a new eye-tracking database of multiple-face videos. The experimental results show that our method outperforms the prior state-of-the-art methods in predicting visual attention on faces in multiple-face videos. |
| Tasks | Eye Tracking, Saliency Prediction |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Liu_Predicting_Salient_Face_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Liu_Predicting_Salient_Face_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-salient-face-in-multiple-face |
| Repo | https://github.com/yufanLIU/salient-face-in-MUVFET |
| Framework | tf |
Learning What is Essential in Questions
| Title | Learning What is Essential in Questions |
| Authors | Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Dan Roth |
| Abstract | Question answering (QA) systems are easily distracted by irrelevant or redundant words in questions, especially when faced with long or multi-sentence questions in difficult domains. This paper introduces and studies the notion of essential question terms with the goal of improving such QA solvers. We illustrate the importance of essential question terms by showing that humans{'} ability to answer questions drops significantly when essential terms are eliminated from questions.We then develop a classifier that reliably (90{%} mean average precision) identifies and ranks essential terms in questions. Finally, we use the classifier to demonstrate that the notion of question term essentiality allows state-of-the-art QA solver for elementary-level science questions to make better and more informed decisions,improving performance by up to 5{%}.We also introduce a new dataset of over 2,200 crowd-sourced essential terms annotated science questions. |
| Tasks | Information Retrieval, Question Answering, Semantic Parsing |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-1010/ |
| https://www.aclweb.org/anthology/K17-1010 | |
| PWC | https://paperswithcode.com/paper/learning-what-is-essential-in-questions |
| Repo | https://github.com/allenai/essential-terms |
| Framework | none |
GMS: Grid-based Motion Statistics for Fast, Ultra-Robust Feature Correspondence
| Title | GMS: Grid-based Motion Statistics for Fast, Ultra-Robust Feature Correspondence |
| Authors | JiaWang Bian, Wen-Yan Lin, Yasuyuki Matsushita, Sai-Kit Yeung, Tan-Dat Nguyen, Ming-Ming Cheng |
| Abstract | Incorporating smoothness constraints into feature matching is known to enable ultra-robust matching. However, such formulations are both complex and slow, making them unsuitable for video applications. This paper proposes GMS (Grid-based Motion Statistics), a simple means of encapsulating motion smoothness as the statistical likelihood of a certain number of matches in a region. GMS enables translation of high match numbers into high match quality. This provides a real-time, ultra-robust correspondence system. Evaluation on videos, with low textures, blurs and wide-baselines show GMS consistently out-performs other real-time matchers and can achieve parity with more sophisticated, much slower techniques. |
| Tasks | |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Bian_GMS_Grid-based_Motion_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Bian_GMS_Grid-based_Motion_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/gms-grid-based-motion-statistics-for-fast |
| Repo | https://github.com/JiawangBian/GMS-Feature-Matcher |
| Framework | none |
Representation Learning for Answer Selection with LSTM-Based Importance Weighting
| Title | Representation Learning for Answer Selection with LSTM-Based Importance Weighting |
| Authors | Andreas R{"u}ckl{'e}, Iryna Gurevych |
| Abstract | |
| Tasks | Answer Selection, Community Question Answering, Question Answering, Representation Learning |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6935/ |
| https://www.aclweb.org/anthology/W17-6935 | |
| PWC | https://paperswithcode.com/paper/representation-learning-for-answer-selection |
| Repo | https://github.com/UKPLab/iwcs2017-answer-selection |
| Framework | tf |
