Paper Group ANR 35
Online Reinforcement Learning in Stochastic Games. Aspect-augmented Adversarial Networks for Domain Adaptation. What were you expecting? Using Expectancy Features to Predict Expressive Performances of Classical Piano Music. Interactively Transferring CNN Patterns for Part Localization. Interpreting CNN Knowledge via an Explanatory Graph. Class Corr …
Online Reinforcement Learning in Stochastic Games
| Title | Online Reinforcement Learning in Stochastic Games |
| Authors | Chen-Yu Wei, Yi-Te Hong, Chi-Jen Lu |
| Abstract | We study online reinforcement learning in average-reward stochastic games (SGs). An SG models a two-player zero-sum game in a Markov environment, where state transitions and one-step payoffs are determined simultaneously by a learner and an adversary. We propose the UCSG algorithm that achieves a sublinear regret compared to the game value when competing with an arbitrary opponent. This result improves previous ones under the same setting. The regret bound has a dependency on the diameter, which is an intrinsic value related to the mixing property of SGs. If we let the opponent play an optimistic best response to the learner, UCSG finds an $\varepsilon$-maximin stationary policy with a sample complexity of $\tilde{\mathcal{O}}\left(\text{poly}(1/\varepsilon)\right)$, where $\varepsilon$ is the gap to the best policy. |
| Tasks | |
| Published | 2017-12-02 |
| URL | http://arxiv.org/abs/1712.00579v1 |
| http://arxiv.org/pdf/1712.00579v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-reinforcement-learning-in-stochastic |
| Repo | |
| Framework | |
Aspect-augmented Adversarial Networks for Domain Adaptation
| Title | Aspect-augmented Adversarial Networks for Domain Adaptation |
| Authors | Yuan Zhang, Regina Barzilay, Tommi Jaakkola |
| Abstract | We introduce a neural method for transfer learning between two (source and target) classification tasks or aspects over the same domain. Rather than training on target labels, we use a few keywords pertaining to source and target aspects indicating sentence relevance instead of document class labels. Documents are encoded by learning to embed and softly select relevant sentences in an aspect-dependent manner. A shared classifier is trained on the source encoded documents and labels, and applied to target encoded documents. We ensure transfer through aspect-adversarial training so that encoded documents are, as sets, aspect-invariant. Experimental results demonstrate that our approach outperforms different baselines and model variants on two datasets, yielding an improvement of 27% on a pathology dataset and 5% on a review dataset. |
| Tasks | Domain Adaptation, Transfer Learning |
| Published | 2017-01-01 |
| URL | http://arxiv.org/abs/1701.00188v2 |
| http://arxiv.org/pdf/1701.00188v2.pdf | |
| PWC | https://paperswithcode.com/paper/aspect-augmented-adversarial-networks-for |
| Repo | |
| Framework | |
What were you expecting? Using Expectancy Features to Predict Expressive Performances of Classical Piano Music
| Title | What were you expecting? Using Expectancy Features to Predict Expressive Performances of Classical Piano Music |
| Authors | Carlos Cancino-Chacón, Maarten Grachten, David R. W. Sears, Gerhard Widmer |
| Abstract | In this paper we present preliminary work examining the relationship between the formation of expectations and the realization of musical performances, paying particular attention to expressive tempo and dynamics. To compute features that reflect what a listener is expecting to hear, we employ a computational model of auditory expectation called the Information Dynamics of Music model (IDyOM). We then explore how well these expectancy features – when combined with score descriptors using the Basis-Function modeling approach – can predict expressive tempo and dynamics in a dataset of Mozart piano sonata performances. Our results suggest that using expectancy features significantly improves the predictions for tempo. |
| Tasks | |
| Published | 2017-09-11 |
| URL | http://arxiv.org/abs/1709.03629v1 |
| http://arxiv.org/pdf/1709.03629v1.pdf | |
| PWC | https://paperswithcode.com/paper/what-were-you-expecting-using-expectancy |
| Repo | |
| Framework | |
Interactively Transferring CNN Patterns for Part Localization
| Title | Interactively Transferring CNN Patterns for Part Localization |
| Authors | Quanshi Zhang, Ruiming Cao, Shengming Zhang, Mark Redmonds, Ying Nian Wu, Song-Chun Zhu |
| Abstract | In the scenario of one/multi-shot learning, conventional end-to-end learning strategies without sufficient supervision are usually not powerful enough to learn correct patterns from noisy signals. Thus, given a CNN pre-trained for object classification, this paper proposes a method that first summarizes the knowledge hidden inside the CNN into a dictionary of latent activation patterns, and then builds a new model for part localization by manually assembling latent patterns related to the target part via human interactions. We use very few (e.g., three) annotations of a semantic object part to retrieve certain latent patterns from conv-layers to represent the target part. We then visualize these latent patterns and ask users to further remove incorrect patterns, in order to refine part representation. With the guidance of human interactions, our method exhibited superior performance of part localization in experiments. |
| Tasks | Object Classification |
| Published | 2017-08-05 |
| URL | http://arxiv.org/abs/1708.01783v2 |
| http://arxiv.org/pdf/1708.01783v2.pdf | |
| PWC | https://paperswithcode.com/paper/interactively-transferring-cnn-patterns-for |
| Repo | |
| Framework | |
Interpreting CNN Knowledge via an Explanatory Graph
| Title | Interpreting CNN Knowledge via an Explanatory Graph |
| Authors | Quanshi Zhang, Ruiming Cao, Feng Shi, Ying Nian Wu, Song-Chun Zhu |
| Abstract | This paper learns a graphical model, namely an explanatory graph, which reveals the knowledge hierarchy hidden inside a pre-trained CNN. Considering that each filter in a conv-layer of a pre-trained CNN usually represents a mixture of object parts, we propose a simple yet efficient method to automatically disentangles different part patterns from each filter, and construct an explanatory graph. In the explanatory graph, each node represents a part pattern, and each edge encodes co-activation relationships and spatial relationships between patterns. More importantly, we learn the explanatory graph for a pre-trained CNN in an unsupervised manner, i.e., without a need of annotating object parts. Experiments show that each graph node consistently represents the same object part through different images. We transfer part patterns in the explanatory graph to the task of part localization, and our method significantly outperforms other approaches. |
| Tasks | |
| Published | 2017-08-05 |
| URL | http://arxiv.org/abs/1708.01785v3 |
| http://arxiv.org/pdf/1708.01785v3.pdf | |
| PWC | https://paperswithcode.com/paper/interpreting-cnn-knowledge-via-an-explanatory |
| Repo | |
| Framework | |
Class Correlation affects Single Object Localization using Pre-trained ConvNets
| Title | Class Correlation affects Single Object Localization using Pre-trained ConvNets |
| Authors | Pokkalla Harsha Vardhan, Kunal Sekhri, Dipan K. Pal, Marios Savvides |
| Abstract | The problem of object localization has become one of the mainstream problems of vision. Most of the algorithms proposed involve the design for the model to be specifically for localizing objects. In this paper, we explore whether a pre-trained canonical ConvNet (without fine-tuning) trained purely for object classification on one dataset with global image level labels can be used to localize objects in images containing a single instance on a separate dataset while generalizing to novel classes. We propose a simple algorithm involving cropping and blackening out regions in the image space called Explicit Image Space based Search (EISS) for locating the most responsive regions in an image in the context of object localization. EISS brings to light the interesting phenomenon of a ConvNets responding more to features within objects as opposed to object level descriptors, as the classes in the training data get more correlated (visually/semantically similar). |
| Tasks | Object Classification, Object Localization |
| Published | 2017-10-26 |
| URL | http://arxiv.org/abs/1710.09685v2 |
| http://arxiv.org/pdf/1710.09685v2.pdf | |
| PWC | https://paperswithcode.com/paper/class-correlation-affects-single-object |
| Repo | |
| Framework | |
Shearlet-based compressed sensing for fast 3D cardiac MR imaging using iterative reweighting
| Title | Shearlet-based compressed sensing for fast 3D cardiac MR imaging using iterative reweighting |
| Authors | Jackie Ma, Maximilian März, Stephanie Funk, Jeanette Schulz-Menger, Gitta Kutyniok, Tobias Schaeffter, Christoph Kolbitsch |
| Abstract | High-resolution three-dimensional (3D) cardiovascular magnetic resonance (CMR) is a valuable medical imaging technique, but its widespread application in clinical practice is hampered by long acquisition times. Here we present a novel compressed sensing (CS) reconstruction approach using shearlets as a sparsifying transform allowing for fast 3D CMR (3DShearCS). Shearlets are mathematically optimal for a simplified model of natural images and have been proven to be more efficient than classical systems such as wavelets. Data is acquired with a 3D Radial Phase Encoding (RPE) trajectory and an iterative reweighting scheme is used during image reconstruction to ensure fast convergence and high image quality. In our in-vivo cardiac MRI experiments we show that the proposed method 3DShearCS has lower relative errors and higher structural similarity compared to the other reconstruction techniques especially for high undersampling factors, i.e. short scan times. In this paper, we further show that 3DShearCS provides improved depiction of cardiac anatomy (measured by assessing the sharpness of coronary arteries) and two clinical experts qualitatively analyzed the image quality. |
| Tasks | Image Reconstruction |
| Published | 2017-05-01 |
| URL | http://arxiv.org/abs/1705.00463v1 |
| http://arxiv.org/pdf/1705.00463v1.pdf | |
| PWC | https://paperswithcode.com/paper/shearlet-based-compressed-sensing-for-fast-3d |
| Repo | |
| Framework | |
A New Coherence-Penalized Minimal Path Model with Application to Retinal Vessel Centerline Delineation
| Title | A New Coherence-Penalized Minimal Path Model with Application to Retinal Vessel Centerline Delineation |
| Authors | Da Chen, Laurent D. Cohen |
| Abstract | In this paper, we propose a new minimal path model for minimally interactive retinal vessel centerline extraction. The main contribution lies at the construction of a novel coherence-penalized Riemannian metric in a lifted space, dependently of the local geometry of tubularity and an external scalar-valued reference feature map. The globally minimizing curves associated to the proposed metric favour to pass through a set of retinal vessel segments with low variations of the feature map, thus can avoid the short branches combination problem and shortcut problem, commonly suffered by the existing minimal path models in the application of retinal imaging. We validate our model on a series of retinal vessel patches obtained from the DRIVE and IOSTAR datasets, showing that our model indeed get promising results. |
| Tasks | |
| Published | 2017-10-17 |
| URL | http://arxiv.org/abs/1710.06194v1 |
| http://arxiv.org/pdf/1710.06194v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-coherence-penalized-minimal-path-model |
| Repo | |
| Framework | |
Detecting Noteheads in Handwritten Scores with ConvNets and Bounding Box Regression
| Title | Detecting Noteheads in Handwritten Scores with ConvNets and Bounding Box Regression |
| Authors | Jan Hajič Jr., Pavel Pecina |
| Abstract | Noteheads are the interface between the written score and music. Each notehead on the page signifies one note to be played, and detecting noteheads is thus an unavoidable step for Optical Music Recognition. Noteheads are clearly distinct objects, however, the variety of music notation handwriting makes noteheads harder to identify, and while handwritten music notation symbol {\em classification} is a well-studied task, symbol {\em detection} has usually been limited to heuristics and rule-based systems instead of machine learning methods better suited to deal with the uncertainties in handwriting. We present ongoing work on a simple notehead detector using convolutional neural networks for pixel classification and bounding box regression that achieves a detection f-score of 0.97 on binary score images in the MUSCIMA++ dataset, does not require staff removal, and is applicable to a variety of handwriting styles and levels of musical complexity. |
| Tasks | |
| Published | 2017-08-05 |
| URL | http://arxiv.org/abs/1708.01806v1 |
| http://arxiv.org/pdf/1708.01806v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-noteheads-in-handwritten-scores |
| Repo | |
| Framework | |
Similarity Search Over Graphs Using Localized Spectral Analysis
| Title | Similarity Search Over Graphs Using Localized Spectral Analysis |
| Authors | Yariv Aizenbud, Amir Averbuch, Gil Shabat, Guy Ziv |
| Abstract | This paper provides a new similarity detection algorithm. Given an input set of multi-dimensional data points, where each data point is assumed to be multi-dimensional, and an additional reference data point for similarity finding, the algorithm uses kernel method that embeds the data points into a low dimensional manifold. Unlike other kernel methods, which consider the entire data for the embedding, our method selects a specific set of kernel eigenvectors. The eigenvectors are chosen to separate between the data points and the reference data point so that similar data points can be easily identified as being distinct from most of the members in the dataset. |
| Tasks | |
| Published | 2017-07-11 |
| URL | http://arxiv.org/abs/1707.03311v1 |
| http://arxiv.org/pdf/1707.03311v1.pdf | |
| PWC | https://paperswithcode.com/paper/similarity-search-over-graphs-using-localized |
| Repo | |
| Framework | |
Subspace Learning in The Presence of Sparse Structured Outliers and Noise
| Title | Subspace Learning in The Presence of Sparse Structured Outliers and Noise |
| Authors | Shervin Minaee, Yao Wang |
| Abstract | Subspace learning is an important problem, which has many applications in image and video processing. It can be used to find a low-dimensional representation of signals and images. But in many applications, the desired signal is heavily distorted by outliers and noise, which negatively affect the learned subspace. In this work, we present a novel algorithm for learning a subspace for signal representation, in the presence of structured outliers and noise. The proposed algorithm tries to jointly detect the outliers and learn the subspace for images. We present an alternating optimization algorithm for solving this problem, which iterates between learning the subspace and finding the outliers. This algorithm has been trained on a large number of image patches, and the learned subspace is used for image segmentation, and is shown to achieve better segmentation results than prior methods, including least absolute deviation fitting, k-means clustering based segmentation in DjVu, and shape primitive extraction and coding algorithm. |
| Tasks | Semantic Segmentation |
| Published | 2017-03-14 |
| URL | http://arxiv.org/abs/1703.04611v4 |
| http://arxiv.org/pdf/1703.04611v4.pdf | |
| PWC | https://paperswithcode.com/paper/subspace-learning-in-the-presence-of-sparse |
| Repo | |
| Framework | |
Convolutional Neural Network with Word Embeddings for Chinese Word Segmentation
| Title | Convolutional Neural Network with Word Embeddings for Chinese Word Segmentation |
| Authors | Chunqi Wang, Bo Xu |
| Abstract | Character-based sequence labeling framework is flexible and efficient for Chinese word segmentation (CWS). Recently, many character-based neural models have been applied to CWS. While they obtain good performance, they have two obvious weaknesses. The first is that they heavily rely on manually designed bigram feature, i.e. they are not good at capturing n-gram features automatically. The second is that they make no use of full word information. For the first weakness, we propose a convolutional neural model, which is able to capture rich n-gram features without any feature engineering. For the second one, we propose an effective approach to integrate the proposed model with word embeddings. We evaluate the model on two benchmark datasets: PKU and MSR. Without any feature engineering, the model obtains competitive performance – 95.7% on PKU and 97.3% on MSR. Armed with word embeddings, the model achieves state-of-the-art performance on both datasets – 96.5% on PKU and 98.0% on MSR, without using any external labeled resource. |
| Tasks | Chinese Word Segmentation, Feature Engineering, Word Embeddings |
| Published | 2017-11-13 |
| URL | http://arxiv.org/abs/1711.04411v1 |
| http://arxiv.org/pdf/1711.04411v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-network-with-word |
| Repo | |
| Framework | |
Neural Networks for Information Retrieval
| Title | Neural Networks for Information Retrieval |
| Authors | Tom Kenter, Alexey Borisov, Christophe Van Gysel, Mostafa Dehghani, Maarten de Rijke, Bhaskar Mitra |
| Abstract | Machine learning plays a role in many aspects of modern IR systems, and deep learning is applied in all of them. The fast pace of modern-day research has given rise to many different approaches for many different IR problems. The amount of information available can be overwhelming both for junior students and for experienced researchers looking for new research topics and directions. Additionally, it is interesting to see what key insights into IR problems the new technologies are able to give us. The aim of this full-day tutorial is to give a clear overview of current tried-and-trusted neural methods in IR and how they benefit IR research. It covers key architectures, as well as the most promising future directions. |
| Tasks | Information Retrieval |
| Published | 2017-07-13 |
| URL | http://arxiv.org/abs/1707.04242v1 |
| http://arxiv.org/pdf/1707.04242v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-networks-for-information-retrieval |
| Repo | |
| Framework | |
Expect the unexpected: Harnessing Sentence Completion for Sarcasm Detection
| Title | Expect the unexpected: Harnessing Sentence Completion for Sarcasm Detection |
| Authors | Aditya Joshi, Samarth Agrawal, Pushpak Bhattacharyya, Mark Carman |
| Abstract | The trigram I love being' is expected to be followed by positive words such as happy’. In a sarcastic sentence, however, the word `ignored’ may be observed. The expected and the observed words are, thus, incongruous. We model sarcasm detection as the task of detecting incongruity between an observed and an expected word. In order to obtain the expected word, we use Context2Vec, a sentence completion library based on Bidirectional LSTM. However, since the exact word where such an incongruity occurs may not be known in advance, we present two approaches: an All-words approach (which consults sentence completion for every content word) and an Incongruous words-only approach (which consults sentence completion for the 50% most incongruous content words). The approaches outperform reported values for tweets but not for discussion forum posts. This is likely to be because of redundant consultation of sentence completion for discussion forum posts. Therefore, we consider an oracle case where the exact incongruous word is manually labeled in a corpus reported in past work. In this case, the performance is higher than the all-words approach. This sets up the promise for using sentence completion for sarcasm detection. | |
| Tasks | Sarcasm Detection |
| Published | 2017-07-19 |
| URL | http://arxiv.org/abs/1707.06151v1 |
| http://arxiv.org/pdf/1707.06151v1.pdf | |
| PWC | https://paperswithcode.com/paper/expect-the-unexpected-harnessing-sentence |
| Repo | |
| Framework | |
Robust Clustering for Time Series Using Spectral Densities and Functional Data Analysis
| Title | Robust Clustering for Time Series Using Spectral Densities and Functional Data Analysis |
| Authors | Diego Rivera-García, Luis Angel García-Escudero, Agustín Mayo-Iscar, Joaquín Ortega |
| Abstract | In this work a robust clustering algorithm for stationary time series is proposed. The algorithm is based on the use of estimated spectral densities, which are considered as functional data, as the basic characteristic of stationary time series for clustering purposes. A robust algorithm for functional data is then applied to the set of spectral densities. Trimming techniques and restrictions on the scatter within groups reduce the effect of noise in the data and help to prevent the identification of spurious clusters. The procedure is tested in a simulation study, and is also applied to a real data set. |
| Tasks | Time Series |
| Published | 2017-02-07 |
| URL | http://arxiv.org/abs/1702.02165v1 |
| http://arxiv.org/pdf/1702.02165v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-clustering-for-time-series-using |
| Repo | |
| Framework | |
