Paper Group ANR 103
Swarm Intelligence in Semi-supervised Classification. Semi-automatic definite description annotation: a first report. Deep Learning for Lung Cancer Detection: Tackling the Kaggle Data Science Bowl 2017 Challenge. Model Distillation with Knowledge Transfer from Face Classification to Alignment and Verification. Risk Stratification of Lung Nodules Us …
Swarm Intelligence in Semi-supervised Classification
| Title | Swarm Intelligence in Semi-supervised Classification |
| Authors | Shahira Shaaban Azab, Hesham Ahmed Hefny |
| Abstract | This Paper represents a literature review of Swarm intelligence algorithm in the area of semi-supervised classification. There are many research papers for applying swarm intelligence algorithms in the area of machine learning. Some algorithms of SI are applied in the area of ML either solely or hybrid with other ML algorithms. SI algorithms are also used for tuning parameters of ML algorithm, or as a backbone for ML algorithms. This paper introduces a brief literature review for applying swarm intelligence algorithms in the field of semi-supervised learning |
| Tasks | |
| Published | 2017-06-03 |
| URL | http://arxiv.org/abs/1706.00998v1 |
| http://arxiv.org/pdf/1706.00998v1.pdf | |
| PWC | https://paperswithcode.com/paper/swarm-intelligence-in-semi-supervised |
| Repo | |
| Framework | |
Semi-automatic definite description annotation: a first report
| Title | Semi-automatic definite description annotation: a first report |
| Authors | Danillo da Silva Rocha, Alex Gwo Jen Lan, Ivandre Paraboni |
| Abstract | Studies in Referring Expression Generation (REG) often make use of corpora of definite descriptions produced by human subjects in controlled experiments. Experiments of this kind, which are essential for the study of reference phenomena and many others, may however include a considerable amount of noise. Human subjects may easily lack attention, or may simply misunderstand the task at hand and, as a result, the elicited data may include large proportions of ambiguous or ill-formed descriptions. In addition to that, REG corpora are usually collected for the study of semantics-related phenomena, and it is often the case that the elicited descriptions (and their input contexts) need to be annotated with their corresponding semantic properties. This, as in many other fields, may require considerable time and skilled annotators. As a means to tackle both kinds of difficulties - poor data quality and high annotation costs - this work discusses a semi-automatic method for the annotation of definite descriptions produced by human subjects in REG data collection experiments. The method makes use of simple rules to establish associations between words and meanings, and is intended to facilitate the design of experiments that produce REG corpora. |
| Tasks | |
| Published | 2017-12-24 |
| URL | http://arxiv.org/abs/1712.08933v1 |
| http://arxiv.org/pdf/1712.08933v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-automatic-definite-description |
| Repo | |
| Framework | |
Deep Learning for Lung Cancer Detection: Tackling the Kaggle Data Science Bowl 2017 Challenge
| Title | Deep Learning for Lung Cancer Detection: Tackling the Kaggle Data Science Bowl 2017 Challenge |
| Authors | Kingsley Kuan, Mathieu Ravaut, Gaurav Manek, Huiling Chen, Jie Lin, Babar Nazir, Cen Chen, Tse Chiang Howe, Zeng Zeng, Vijay Chandrasekhar |
| Abstract | We present a deep learning framework for computer-aided lung cancer diagnosis. Our multi-stage framework detects nodules in 3D lung CAT scans, determines if each nodule is malignant, and finally assigns a cancer probability based on these results. We discuss the challenges and advantages of our framework. In the Kaggle Data Science Bowl 2017, our framework ranked 41st out of 1972 teams. |
| Tasks | Lung Cancer Diagnosis |
| Published | 2017-05-26 |
| URL | http://arxiv.org/abs/1705.09435v1 |
| http://arxiv.org/pdf/1705.09435v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-lung-cancer-detection |
| Repo | |
| Framework | |
Model Distillation with Knowledge Transfer from Face Classification to Alignment and Verification
| Title | Model Distillation with Knowledge Transfer from Face Classification to Alignment and Verification |
| Authors | Chong Wang, Xipeng Lan, Yangang Zhang |
| Abstract | Knowledge distillation is a potential solution for model compression. The idea is to make a small student network imitate the target of a large teacher network, then the student network can be competitive to the teacher one. Most previous studies focus on model distillation in the classification task, where they propose different architects and initializations for the student network. However, only the classification task is not enough, and other related tasks such as regression and retrieval are barely considered. To solve the problem, in this paper, we take face recognition as a breaking point and propose model distillation with knowledge transfer from face classification to alignment and verification. By selecting appropriate initializations and targets in the knowledge transfer, the distillation can be easier in non-classification tasks. Experiments on the CelebA and CASIA-WebFace datasets demonstrate that the student network can be competitive to the teacher one in alignment and verification, and even surpasses the teacher network under specific compression rates. In addition, to achieve stronger knowledge transfer, we also use a common initialization trick to improve the distillation performance of classification. Evaluations on the CASIA-Webface and large-scale MS-Celeb-1M datasets show the effectiveness of this simple trick. |
| Tasks | Face Recognition, Model Compression, Transfer Learning |
| Published | 2017-09-09 |
| URL | http://arxiv.org/abs/1709.02929v2 |
| http://arxiv.org/pdf/1709.02929v2.pdf | |
| PWC | https://paperswithcode.com/paper/model-distillation-with-knowledge-transfer |
| Repo | |
| Framework | |
Risk Stratification of Lung Nodules Using 3D CNN-Based Multi-task Learning
| Title | Risk Stratification of Lung Nodules Using 3D CNN-Based Multi-task Learning |
| Authors | Sarfaraz Hussein, Kunlin Cao, Qi Song, Ulas Bagci |
| Abstract | Risk stratification of lung nodules is a task of primary importance in lung cancer diagnosis. Any improvement in robust and accurate nodule characterization can assist in identifying cancer stage, prognosis, and improving treatment planning. In this study, we propose a 3D Convolutional Neural Network (CNN) based nodule characterization strategy. With a completely 3D approach, we utilize the volumetric information from a CT scan which would be otherwise lost in the conventional 2D CNN based approaches. In order to address the need for a large amount for training data for CNN, we resort to transfer learning to obtain highly discriminative features. Moreover, we also acquire the task dependent feature representation for six high-level nodule attributes and fuse this complementary information via a Multi-task learning (MTL) framework. Finally, we propose to incorporate potential disagreement among radiologists while scoring different nodule attributes in a graph regularized sparse multi-task learning. We evaluated our proposed approach on one of the largest publicly available lung nodule datasets comprising 1018 scans and obtained state-of-the-art results in regressing the malignancy scores. |
| Tasks | Lung Cancer Diagnosis, Multi-Task Learning, Transfer Learning |
| Published | 2017-04-28 |
| URL | http://arxiv.org/abs/1704.08797v1 |
| http://arxiv.org/pdf/1704.08797v1.pdf | |
| PWC | https://paperswithcode.com/paper/risk-stratification-of-lung-nodules-using-3d |
| Repo | |
| Framework | |
Fast Multi-frame Stereo Scene Flow with Motion Segmentation
| Title | Fast Multi-frame Stereo Scene Flow with Motion Segmentation |
| Authors | Tatsunori Taniai, Sudipta N. Sinha, Yoichi Sato |
| Abstract | We propose a new multi-frame method for efficiently computing scene flow (dense depth and optical flow) and camera ego-motion for a dynamic scene observed from a moving stereo camera rig. Our technique also segments out moving objects from the rigid scene. In our method, we first estimate the disparity map and the 6-DOF camera motion using stereo matching and visual odometry. We then identify regions inconsistent with the estimated camera motion and compute per-pixel optical flow only at these regions. This flow proposal is fused with the camera motion-based flow proposal using fusion moves to obtain the final optical flow and motion segmentation. This unified framework benefits all four tasks - stereo, optical flow, visual odometry and motion segmentation leading to overall higher accuracy and efficiency. Our method is currently ranked third on the KITTI 2015 scene flow benchmark. Furthermore, our CPU implementation runs in 2-3 seconds per frame which is 1-3 orders of magnitude faster than the top six methods. We also report a thorough evaluation on challenging Sintel sequences with fast camera and object motion, where our method consistently outperforms OSF [Menze and Geiger, 2015], which is currently ranked second on the KITTI benchmark. |
| Tasks | Motion Segmentation, Optical Flow Estimation, Stereo Matching, Stereo Matching Hand, Visual Odometry |
| Published | 2017-07-05 |
| URL | http://arxiv.org/abs/1707.01307v1 |
| http://arxiv.org/pdf/1707.01307v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-multi-frame-stereo-scene-flow-with |
| Repo | |
| Framework | |
Semi-Supervised QA with Generative Domain-Adaptive Nets
| Title | Semi-Supervised QA with Generative Domain-Adaptive Nets |
| Authors | Zhilin Yang, Junjie Hu, Ruslan Salakhutdinov, William W. Cohen |
| Abstract | We study the problem of semi-supervised question answering—-utilizing unlabeled text to boost the performance of question answering models. We propose a novel training framework, the Generative Domain-Adaptive Nets. In this framework, we train a generative model to generate questions based on the unlabeled text, and combine model-generated questions with human-generated questions for training question answering models. We develop novel domain adaptation algorithms, based on reinforcement learning, to alleviate the discrepancy between the model-generated data distribution and the human-generated data distribution. Experiments show that our proposed framework obtains substantial improvement from unlabeled text. |
| Tasks | Domain Adaptation, Question Answering |
| Published | 2017-02-07 |
| URL | http://arxiv.org/abs/1702.02206v2 |
| http://arxiv.org/pdf/1702.02206v2.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-qa-with-generative-domain |
| Repo | |
| Framework | |
CoMaL Tracking: Tracking Points at the Object Boundaries
| Title | CoMaL Tracking: Tracking Points at the Object Boundaries |
| Authors | Santhosh K. Ramakrishnan, Swarna Kamlam Ravindran, Anurag Mittal |
| Abstract | Traditional point tracking algorithms such as the KLT use local 2D information aggregation for feature detection and tracking, due to which their performance degrades at the object boundaries that separate multiple objects. Recently, CoMaL Features have been proposed that handle such a case. However, they proposed a simple tracking framework where the points are re-detected in each frame and matched. This is inefficient and may also lose many points that are not re-detected in the next frame. We propose a novel tracking algorithm to accurately and efficiently track CoMaL points. For this, the level line segment associated with the CoMaL points is matched to MSER segments in the next frame using shape-based matching and the matches are further filtered using texture-based matching. Experiments show improvements over a simple re-detect-and-match framework as well as KLT in terms of speed/accuracy on different real-world applications, especially at the object boundaries. |
| Tasks | |
| Published | 2017-06-07 |
| URL | http://arxiv.org/abs/1706.02331v1 |
| http://arxiv.org/pdf/1706.02331v1.pdf | |
| PWC | https://paperswithcode.com/paper/comal-tracking-tracking-points-at-the-object |
| Repo | |
| Framework | |
Plane-extraction from depth-data using a Gaussian mixture regression model
| Title | Plane-extraction from depth-data using a Gaussian mixture regression model |
| Authors | Richard T. Marriott, Alexander Paschevich, Radu Horaud |
| Abstract | We propose a novel algorithm for unsupervised extraction of piecewise planar models from depth-data. Among other applications, such models are a good way of enabling autonomous agents (robots, cars, drones, etc.) to effectively perceive their surroundings and to navigate in three dimensions. We propose to do this by fitting the data with a piecewise-linear Gaussian mixture regression model whose components are skewed over planes, making them flat in appearance rather than being ellipsoidal, by embedding an outlier-trimming process that is formally incorporated into the proposed expectation-maximization algorithm, and by selectively fusing contiguous, coplanar components. Part of our motivation is an attempt to estimate more accurate plane-extraction by allowing each model component to make use of all available data through probabilistic clustering. The algorithm is thoroughly evaluated against a standard benchmark and is shown to rank among the best of the existing state-of-the-art methods. |
| Tasks | |
| Published | 2017-10-05 |
| URL | http://arxiv.org/abs/1710.01925v4 |
| http://arxiv.org/pdf/1710.01925v4.pdf | |
| PWC | https://paperswithcode.com/paper/plane-extraction-from-depth-data-using-a |
| Repo | |
| Framework | |
Fine-Grained Prediction of Syntactic Typology: Discovering Latent Structure with Supervised Learning
| Title | Fine-Grained Prediction of Syntactic Typology: Discovering Latent Structure with Supervised Learning |
| Authors | Dingquan Wang, Jason Eisner |
| Abstract | We show how to predict the basic word-order facts of a novel language given only a corpus of part-of-speech (POS) sequences. We predict how often direct objects follow their verbs, how often adjectives follow their nouns, and in general the directionalities of all dependency relations. Such typological properties could be helpful in grammar induction. While such a problem is usually regarded as unsupervised learning, our innovation is to treat it as supervised learning, using a large collection of realistic synthetic languages as training data. The supervised learner must identify surface features of a language’s POS sequence (hand-engineered or neural features) that correlate with the language’s deeper structure (latent trees). In the experiment, we show: 1) Given a small set of real languages, it helps to add many synthetic languages to the training data. 2) Our system is robust even when the POS sequences include noise. 3) Our system on this task outperforms a grammar induction baseline by a large margin. |
| Tasks | |
| Published | 2017-10-11 |
| URL | http://arxiv.org/abs/1710.03877v1 |
| http://arxiv.org/pdf/1710.03877v1.pdf | |
| PWC | https://paperswithcode.com/paper/fine-grained-prediction-of-syntactic-typology |
| Repo | |
| Framework | |
Learning to Design Games: Strategic Environments in Reinforcement Learning
| Title | Learning to Design Games: Strategic Environments in Reinforcement Learning |
| Authors | Haifeng Zhang, Jun Wang, Zhiming Zhou, Weinan Zhang, Ying Wen, Yong Yu, Wenxin Li |
| Abstract | In typical reinforcement learning (RL), the environment is assumed given and the goal of the learning is to identify an optimal policy for the agent taking actions through its interactions with the environment. In this paper, we extend this setting by considering the environment is not given, but controllable and learnable through its interaction with the agent at the same time. This extension is motivated by environment design scenarios in the real-world, including game design, shopping space design and traffic signal design. Theoretically, we find a dual Markov decision process (MDP) w.r.t. the environment to that w.r.t. the agent, and derive a policy gradient solution to optimizing the parametrized environment. Furthermore, discontinuous environments are addressed by a proposed general generative framework. Our experiments on a Maze game design task show the effectiveness of the proposed algorithms in generating diverse and challenging Mazes against various agent settings. |
| Tasks | |
| Published | 2017-07-05 |
| URL | https://arxiv.org/abs/1707.01310v5 |
| https://arxiv.org/pdf/1707.01310v5.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-design-games-strategic |
| Repo | |
| Framework | |
Investigating Reinforcement Learning Agents for Continuous State Space Environments
| Title | Investigating Reinforcement Learning Agents for Continuous State Space Environments |
| Authors | David Von Dollen |
| Abstract | Given an environment with continuous state spaces and discrete actions, we investigate using a Double Deep Q-learning Reinforcement Agent to find optimal policies using the LunarLander-v2 OpenAI gym environment. |
| Tasks | Q-Learning |
| Published | 2017-08-08 |
| URL | http://arxiv.org/abs/1708.02378v3 |
| http://arxiv.org/pdf/1708.02378v3.pdf | |
| PWC | https://paperswithcode.com/paper/investigating-reinforcement-learning-agents |
| Repo | |
| Framework | |
Exact Identification of a Quantum Change Point
| Title | Exact Identification of a Quantum Change Point |
| Authors | Gael Sentís, John Calsamiglia, Ramon Munoz-Tapia |
| Abstract | The detection of change points is a pivotal task in statistical analysis. In the quantum realm, it is a new primitive where one aims at identifying the point where a source that supposedly prepares a sequence of particles in identical quantum states starts preparing a mutated one. We obtain the optimal procedure to identify the change point with certainty—naturally at the price of having a certain probability of getting an inconclusive answer. We obtain the analytical form of the optimal probability of successful identification for any length of the particle sequence. We show that the conditional success probabilities of identifying each possible change point show an unexpected oscillatory behaviour. We also discuss local (online) protocols and compare them with the optimal procedure. |
| Tasks | |
| Published | 2017-07-24 |
| URL | http://arxiv.org/abs/1707.07769v2 |
| http://arxiv.org/pdf/1707.07769v2.pdf | |
| PWC | https://paperswithcode.com/paper/exact-identification-of-a-quantum-change |
| Repo | |
| Framework | |
A rational analysis of curiosity
| Title | A rational analysis of curiosity |
| Authors | Rachit Dubey, Thomas L. Griffiths |
| Abstract | We present a rational analysis of curiosity, proposing that people’s curiosity is driven by seeking stimuli that maximize their ability to make appropriate responses in the future. This perspective offers a way to unify previous theories of curiosity into a single framework. Experimental results confirm our model’s predictions, showing how the relationship between curiosity and confidence can change significantly depending on the nature of the environment. |
| Tasks | |
| Published | 2017-05-11 |
| URL | http://arxiv.org/abs/1705.04351v1 |
| http://arxiv.org/pdf/1705.04351v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-rational-analysis-of-curiosity |
| Repo | |
| Framework | |
Unsupervised Ensemble Regression
| Title | Unsupervised Ensemble Regression |
| Authors | Omer Dror, Boaz Nadler, Erhan Bilal, Yuval Kluger |
| Abstract | Consider a regression problem where there is no labeled data and the only observations are the predictions $f_i(x_j)$ of $m$ experts $f_{i}$ over many samples $x_j$. With no knowledge on the accuracy of the experts, is it still possible to accurately estimate the unknown responses $y_{j}$? Can one still detect the least or most accurate experts? In this work we propose a framework to study these questions, based on the assumption that the $m$ experts have uncorrelated deviations from the optimal predictor. Assuming the first two moments of the response are known, we develop methods to detect the best and worst regressors, and derive U-PCR, a novel principal components approach for unsupervised ensemble regression. We provide theoretical support for U-PCR and illustrate its improved accuracy over the ensemble mean and median on a variety of regression problems. |
| Tasks | |
| Published | 2017-03-08 |
| URL | http://arxiv.org/abs/1703.02965v1 |
| http://arxiv.org/pdf/1703.02965v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-ensemble-regression |
| Repo | |
| Framework | |
