Paper Group ANR 1687
A Framework for Building Closed-Domain Chat Dialogue Systems. A Bulirsch-Stoer algorithm using Gaussian processes. Object detection on aerial imagery using CenterNet. Robust Synthesis of Adversarial Visual Examples Using a Deep Image Prior. Facial Micro-Expression Spotting and Recognition using Time Contrasted Feature with Visual Memory. Interval t …
A Framework for Building Closed-Domain Chat Dialogue Systems
| Title | A Framework for Building Closed-Domain Chat Dialogue Systems |
| Authors | Mikio Nakano, Kazunori Komatani |
| Abstract | This paper presents HRIChat, a framework for developing closed-domain chat dialogue systems. Being able to engage in chat dialogues has been found effective for improving communication between humans and dialogue systems. This paper focuses on closed-domain systems because they would be useful when combined with task-oriented dialogue systems in the same domain. HRIChat enables domain-dependent language understanding so that it can deal well with domain-specific utterances. In addition, HRIChat makes it possible to integrate state transition network-based dialogue management and reaction-based dialogue management. FoodChatbot, which is an application in the food and restaurant domain, has been developed and evaluated through a user study. Its results suggest that reasonably good systems can be developed with HRIChat. This paper also reports lessons learned from the development and evaluation of FoodChatbot. |
| Tasks | Dialogue Management, Task-Oriented Dialogue Systems |
| Published | 2019-10-30 |
| URL | https://arxiv.org/abs/1910.13826v2 |
| https://arxiv.org/pdf/1910.13826v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-framework-for-building-closed-domain-chat |
| Repo | |
| Framework | |
A Bulirsch-Stoer algorithm using Gaussian processes
| Title | A Bulirsch-Stoer algorithm using Gaussian processes |
| Authors | Philip G. Breen, Christopher N. Foley |
| Abstract | In this paper, we treat the problem of evaluating the asymptotic error in a numerical integration scheme as one with inherent uncertainty. Adding to the growing field of probabilistic numerics, we show that Gaussian process regression (GPR) can be embedded into a numerical integration scheme to allow for (i) robust selection of the adaptive step-size parameter and; (ii) uncertainty quantification in predictions of putatively converged numerical solutions. We present two examples of our approach using Richardson’s extrapolation technique and the Bulirsch-Stoer algorithm. In scenarios where the error-surface is smooth and bounded, our proposed approach can match the results of the traditional polynomial (parametric) extrapolation methods. In scenarios where the error surface is not well approximated by a finite-order polynomial, e.g. in the vicinity of a pole or in the assessment of a chaotic system, traditional methods can fail, however, the non-parametric GPR approach demonstrates the potential to continue to furnish reasonable solutions in these situations. |
| Tasks | Gaussian Processes |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09892v1 |
| https://arxiv.org/pdf/1905.09892v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-bulirsch-stoer-algorithm-using-gaussian |
| Repo | |
| Framework | |
Object detection on aerial imagery using CenterNet
| Title | Object detection on aerial imagery using CenterNet |
| Authors | Dheeraj Reddy Pailla, Varghese Kollerathu, Sai Saketh Chennamsetty |
| Abstract | Detection and classification of objects in aerial imagery have several applications like urban planning, crop surveillance, and traffic surveillance. However, due to the lower resolution of the objects and the effect of noise in aerial images, extracting distinguishing features for the objects is a challenge. We evaluate CenterNet, a state of the art method for real-time 2D object detection, on the VisDrone2019 dataset. We evaluate the performance of the model with different backbone networks in conjunction with varying resolutions during training and testing. |
| Tasks | Object Detection |
| Published | 2019-08-22 |
| URL | https://arxiv.org/abs/1908.08244v1 |
| https://arxiv.org/pdf/1908.08244v1.pdf | |
| PWC | https://paperswithcode.com/paper/object-detection-on-aerial-imagery-using |
| Repo | |
| Framework | |
Robust Synthesis of Adversarial Visual Examples Using a Deep Image Prior
| Title | Robust Synthesis of Adversarial Visual Examples Using a Deep Image Prior |
| Authors | Thomas Gittings, Steve Schneider, John Collomosse |
| Abstract | We present a novel method for generating robust adversarial image examples building upon the recent deep image prior' (DIP) that exploits convolutional network architectures to enforce plausible texture in image synthesis. Adversarial images are commonly generated by perturbing images to introduce high frequency noise that induces image misclassification, but that is fragile to subsequent digital manipulation of the image. We show that using DIP to reconstruct an image under adversarial constraint induces perturbations that are more robust to affine deformation, whilst remaining visually imperceptible. Furthermore we show that our DIP approach can also be adapted to produce local adversarial patches (adversarial stickers’). We demonstrate robust adversarial examples over a broad gamut of images and object classes drawn from the ImageNet dataset. |
| Tasks | Image Generation |
| Published | 2019-07-03 |
| URL | https://arxiv.org/abs/1907.01996v1 |
| https://arxiv.org/pdf/1907.01996v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-synthesis-of-adversarial-visual |
| Repo | |
| Framework | |
Facial Micro-Expression Spotting and Recognition using Time Contrasted Feature with Visual Memory
| Title | Facial Micro-Expression Spotting and Recognition using Time Contrasted Feature with Visual Memory |
| Authors | Sauradip Nag, Ayan Kumar Bhunia, Aishik Konwer, Partha Pratim Roy |
| Abstract | Facial micro-expressions are sudden involuntary minute muscle movements which reveal true emotions that people try to conceal. Spotting a micro-expression and recognizing it is a major challenge owing to its short duration and intensity. Many works pursued traditional and deep learning based approaches to solve this issue but compromised on learning low-level features and higher accuracy due to unavailability of datasets. This motivated us to propose a novel joint architecture of spatial and temporal network which extracts time-contrasted features from the feature maps to contrast out micro-expression from rapid muscle movements. The usage of time contrasted features greatly improved the spotting of micro-expression from inconspicuous facial movements. Also, we include a memory module to predict the class and intensity of the micro-expression across the temporal frames of the micro-expression clip. Our method achieves superior performance in comparison to other conventional approaches on CASMEII dataset. |
| Tasks | |
| Published | 2019-02-09 |
| URL | http://arxiv.org/abs/1902.03514v2 |
| http://arxiv.org/pdf/1902.03514v2.pdf | |
| PWC | https://paperswithcode.com/paper/facial-micro-expression-spotting-and |
| Repo | |
| Framework | |
Interval timing in deep reinforcement learning agents
| Title | Interval timing in deep reinforcement learning agents |
| Authors | Ben Deverett, Ryan Faulkner, Meire Fortunato, Greg Wayne, Joel Z. Leibo |
| Abstract | The measurement of time is central to intelligent behavior. We know that both animals and artificial agents can successfully use temporal dependencies to select actions. In artificial agents, little work has directly addressed (1) which architectural components are necessary for successful development of this ability, (2) how this timing ability comes to be represented in the units and actions of the agent, and (3) whether the resulting behavior of the system converges on solutions similar to those of biology. Here we studied interval timing abilities in deep reinforcement learning agents trained end-to-end on an interval reproduction paradigm inspired by experimental literature on mechanisms of timing. We characterize the strategies developed by recurrent and feedforward agents, which both succeed at temporal reproduction using distinct mechanisms, some of which bear specific and intriguing similarities to biological systems. These findings advance our understanding of how agents come to represent time, and they highlight the value of experimentally inspired approaches to characterizing agent abilities. |
| Tasks | |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13469v2 |
| https://arxiv.org/pdf/1905.13469v2.pdf | |
| PWC | https://paperswithcode.com/paper/interval-timing-in-deep-reinforcement |
| Repo | |
| Framework | |
Graph Convolutional Gaussian Processes
| Title | Graph Convolutional Gaussian Processes |
| Authors | Ian Walker, Ben Glocker |
| Abstract | We propose a novel Bayesian nonparametric method to learn translation-invariant relationships on non-Euclidean domains. The resulting graph convolutional Gaussian processes can be applied to problems in machine learning for which the input observations are functions with domains on general graphs. The structure of these models allows for high dimensional inputs while retaining expressibility, as is the case with convolutional neural networks. We present applications of graph convolutional Gaussian processes to images and triangular meshes, demonstrating their versatility and effectiveness, comparing favorably to existing methods, despite being relatively simple models. |
| Tasks | Gaussian Processes |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05739v1 |
| https://arxiv.org/pdf/1905.05739v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-convolutional-gaussian-processes |
| Repo | |
| Framework | |
Suppressing Model Overfitting for Image Super-Resolution Networks
| Title | Suppressing Model Overfitting for Image Super-Resolution Networks |
| Authors | Ruicheng Feng, Jinjin Gu, Yu Qiao, Chao Dong |
| Abstract | Large deep networks have demonstrated competitive performance in single image super-resolution (SISR), with a huge volume of data involved. However, in real-world scenarios, due to the limited accessible training pairs, large models exhibit undesirable behaviors such as overfitting and memorization. To suppress model overfitting and further enjoy the merits of large model capacity, we thoroughly investigate generic approaches for supplying additional training data pairs. In particular, we introduce a simple learning principle MixUp to train networks on interpolations of sample pairs, which encourages networks to support linear behavior in-between training samples. In addition, we propose a data synthesis method with learned degradation, enabling models to use extra high-quality images with higher content diversity. This strategy proves to be successful in reducing biases of data. By combining these components – MixUp and synthetic training data, large models can be trained without overfitting under very limited data samples and achieve satisfactory generalization performance. Our method won the second place in NTIRE2019 Real SR Challenge. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04809v1 |
| https://arxiv.org/pdf/1906.04809v1.pdf | |
| PWC | https://paperswithcode.com/paper/190604809 |
| Repo | |
| Framework | |
Fine-Grained Neural Architecture Search
| Title | Fine-Grained Neural Architecture Search |
| Authors | Heewon Kim, Seokil Hong, Bohyung Han, Heesoo Myeong, Kyoung Mu Lee |
| Abstract | We present an elegant framework of fine-grained neural architecture search (FGNAS), which allows to employ multiple heterogeneous operations within a single layer and can even generate compositional feature maps using several different base operations. FGNAS runs efficiently in spite of significantly large search space compared to other methods because it trains networks end-to-end by a stochastic gradient descent method. Moreover, the proposed framework allows to optimize the network under predefined resource constraints in terms of number of parameters, FLOPs and latency. FGNAS has been applied to two crucial applications in resource demanding computer vision tasks—large-scale image classification and image super-resolution—and demonstrates the state-of-the-art performance through flexible operation search and channel pruning. |
| Tasks | Image Classification, Image Super-Resolution, Neural Architecture Search, Super-Resolution |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07478v1 |
| https://arxiv.org/pdf/1911.07478v1.pdf | |
| PWC | https://paperswithcode.com/paper/fine-grained-neural-architecture-search |
| Repo | |
| Framework | |
A Comprehensive Analysis of Twitter Trending Topics
| Title | A Comprehensive Analysis of Twitter Trending Topics |
| Authors | Issa Annamoradnejad, Jafar Habibi |
| Abstract | Twitter is among the most used microblogging and online social networking services. In Twitter, a name, phrase, or topic that is mentioned at a greater rate than others is called a “trending topic” or simply “trend”. Twitter trends has shown their powerful ability in many public events, elections and market changes. Nevertheless, there has been very few works focusing on understanding the dynamics of these trending topics. In this article, we thoroughly examined the Twitter’s trending topics of 2018. To this end, we accessed Twitter’s trends API for the full year of 2018 and devised six criteria to analyze our dataset. These six criteria are: lexical analysis, time to reach, trend reoccurrence, trending time, tweets count, and language analysis. In addition to providing general statistics and top trending topics regarding each criterion, we computed several distributions that explain this bulk of data. |
| Tasks | Lexical Analysis |
| Published | 2019-07-21 |
| URL | https://arxiv.org/abs/1907.09007v1 |
| https://arxiv.org/pdf/1907.09007v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comprehensive-analysis-of-twitter-trending |
| Repo | |
| Framework | |
Learning Causality: Synthesis of Large-Scale Causal Networks from High-Dimensional Time Series Data
| Title | Learning Causality: Synthesis of Large-Scale Causal Networks from High-Dimensional Time Series Data |
| Authors | Mark-Oliver Stehr, Peter Avar, Andrew R. Korte, Lida Parvin, Ziad J. Sahab, Deborah I. Bunin, Merrill Knapp, Denise Nishita, Andrew Poggio, Carolyn L. Talcott, Brian M. Davis, Christine A. Morton, Christopher J. Sevinsky, Maria I. Zavodszky, Akos Vertes |
| Abstract | There is an abundance of complex dynamic systems that are critical to our daily lives and our society but that are hardly understood, and even with today’s possibilities to sense and collect large amounts of experimental data, they are so complex and continuously evolving that it is unlikely that their dynamics will ever be understood in full detail. Nevertheless, through computational tools we can try to make the best possible use of the current technologies and available data. We believe that the most useful models will have to take into account the imbalance between system complexity and available data in the context of limited knowledge or multiple hypotheses. The complex system of biological cells is a prime example of such a system that is studied in systems biology and has motivated the methods presented in this paper. They were developed as part of the DARPA Rapid Threat Assessment (RTA) program, which is concerned with understanding of the mechanism of action (MoA) of toxins or drugs affecting human cells. Using a combination of Gaussian processes and abstract network modeling, we present three fundamentally different machine-learning-based approaches to learn causal relations and synthesize causal networks from high-dimensional time series data. While other types of data are available and have been analyzed and integrated in our RTA work, we focus on transcriptomics (that is gene expression) data obtained from high-throughput microarray experiments in this paper to illustrate capabilities and limitations of our algorithms. Our algorithms make different but overall relatively few biological assumptions, so that they are applicable to other types of biological data and potentially even to other complex systems that exhibit high dimensionality but are not of biological nature. |
| Tasks | Gaussian Processes, Time Series |
| Published | 2019-05-06 |
| URL | https://arxiv.org/abs/1905.02291v1 |
| https://arxiv.org/pdf/1905.02291v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-causality-synthesis-of-large-scale |
| Repo | |
| Framework | |
Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration
| Title | Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration |
| Authors | Shuhan Tan, Jiening Jiao, Wei-Shi Zheng |
| Abstract | In conventional domain adaptation, a critical assumption is that there exists a fully labeled domain (source) that contains the same label space as another unlabeled or scarcely labeled domain (target). However, in the real world, there often exist application scenarios in which both domains are partially labeled and not all classes are shared between these two domains. Thus, it is meaningful to let partially labeled domains learn from each other to classify all the unlabeled samples in each domain under an open-set setting. We consider this problem as weakly supervised open-set domain adaptation. To address this practical setting, we propose the Collaborative Distribution Alignment (CDA) method, which performs knowledge transfer bilaterally and works collaboratively to classify unlabeled data and identify outlier samples. Extensive experiments on the Office benchmark and an application on person reidentification show that our method achieves state-of-the-art performance. |
| Tasks | Domain Adaptation, Transfer Learning |
| Published | 2019-04-30 |
| URL | http://arxiv.org/abs/1904.13179v1 |
| http://arxiv.org/pdf/1904.13179v1.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-open-set-domain-adaptation |
| Repo | |
| Framework | |
Multitask Text-to-Visual Embedding with Titles and Clickthrough Data
| Title | Multitask Text-to-Visual Embedding with Titles and Clickthrough Data |
| Authors | Pranav Aggarwal, Zhe Lin, Baldo Faieta, Saeid Motiian |
| Abstract | Text-visual (or called semantic-visual) embedding is a central problem in vision-language research. It typically involves mapping of an image and a text description to a common feature space through a CNN image encoder and a RNN language encoder. In this paper, we propose a new method for learning text-visual embedding using both image titles and click-through data from an image search engine. We also propose a new triplet loss function by modeling positive awareness of the embedding, and introduce a novel mini-batch-based hard negative sampling approach for better data efficiency in the learning process. Experimental results show that our proposed method outperforms existing methods, and is also effective for real-world text-to-visual retrieval. |
| Tasks | Image Retrieval |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.13339v1 |
| https://arxiv.org/pdf/1905.13339v1.pdf | |
| PWC | https://paperswithcode.com/paper/multitask-text-to-visual-embedding-with |
| Repo | |
| Framework | |
Making the Last Iterate of SGD Information Theoretically Optimal
| Title | Making the Last Iterate of SGD Information Theoretically Optimal |
| Authors | Prateek Jain, Dheeraj Nagaraj, Praneeth Netrapalli |
| Abstract | Stochastic gradient descent (SGD) is one of the most widely used algorithms for large scale optimization problems. While classical theoretical analysis of SGD for convex problems studies (suffix) \emph{averages} of iterates and obtains information theoretically optimal bounds on suboptimality, the \emph{last point} of SGD is, by far, the most preferred choice in practice. The best known results for last point of SGD \cite{shamir2013stochastic} however, are suboptimal compared to information theoretic lower bounds by a $\log T$ factor, where $T$ is the number of iterations. \cite{harvey2018tight} shows that in fact, this additional $\log T$ factor is tight for standard step size sequences of $\OTheta{\frac{1}{\sqrt{t}}}$ and $\OTheta{\frac{1}{t}}$ for non-strongly convex and strongly convex settings, respectively. Similarly, even for subgradient descent (GD) when applied to non-smooth, convex functions, the best known step-size sequences still lead to $O(\log T)$-suboptimal convergence rates (on the final iterate). The main contribution of this work is to design new step size sequences that enjoy information theoretically optimal bounds on the suboptimality of \emph{last point} of SGD as well as GD. We achieve this by designing a modification scheme, that converts one sequence of step sizes to another so that the last point of SGD/GD with modified sequence has the same suboptimality guarantees as the average of SGD/GD with original sequence. We also show that our result holds with high-probability. We validate our results through simulations which demonstrate that the new step size sequence indeed improves the final iterate significantly compared to the standard step size sequences. |
| Tasks | |
| Published | 2019-04-29 |
| URL | https://arxiv.org/abs/1904.12443v2 |
| https://arxiv.org/pdf/1904.12443v2.pdf | |
| PWC | https://paperswithcode.com/paper/making-the-last-iterate-of-sgd-information |
| Repo | |
| Framework | |
Multispectral snapshot demosaicing via non-convex matrix completion
| Title | Multispectral snapshot demosaicing via non-convex matrix completion |
| Authors | Giancarlo A. Antonucci, Simon Vary, David Humphreys, Robert A. Lamb, Jonathan Piper, Jared Tanner |
| Abstract | Snapshot mosaic multispectral imagery acquires an undersampled data cube by acquiring a single spectral measurement per spatial pixel. Sensors which acquire $p$ frequencies, therefore, suffer from severe $1/p$ undersampling of the full data cube. We show that the missing entries can be accurately imputed using non-convex techniques from sparse approximation and matrix completion initialised with traditional demosaicing algorithms. In particular, we observe the peak signal-to-noise ratio can typically be improved by 2 to 5 dB over current state-of-the-art methods when simulating a $p=16$ mosaic sensor measuring both high and low altitude urban and rural scenes as well as ground-based scenes. |
| Tasks | Demosaicking, Matrix Completion |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.11032v2 |
| http://arxiv.org/pdf/1902.11032v2.pdf | |
| PWC | https://paperswithcode.com/paper/multilspectral-snapshot-demosaicing-via-non |
| Repo | |
| Framework | |
