January 28, 2020

3029 words 15 mins read

Paper Group ANR 917

Consistent Scale Normalization for Object Recognition. Estimation of Orientation and Camera Parameters from Cryo-Electron Microscopy Images with Variational Autoencoders and Generative Adversarial Networks. Outlier Robust Extreme Learning Machine for Multi-Target Regression. PAC learning with stable and private predictions. Physics-based Neural Net …

Consistent Scale Normalization for Object Recognition


Title	Consistent Scale Normalization for Object Recognition
Authors	Zewen He, He Huang, Yudong Wu, Guan Huang, Wensheng Zhang
Abstract	Scale variation remains a challenge problem for object detection. Common paradigms usually adopt multi-scale training & testing (image pyramid) or FPN (feature pyramid network) to process objects in wide scale range. However, multi-scale methods aggravate more variation of scale that even deep convolution neural networks with FPN cannot handle well. In this work, we propose an innovative paradigm called Consistent Scale Normalization (CSN) to resolve above problem. CSN compresses the scale space of objects into a consistent range (CSN range), in both training and testing phase. This reassures problem of scale variation fundamentally, and reduces the difficulty for network learning. Experiments show that CSN surpasses multi-scale counterpart significantly for object detection, instance segmentation and multi-task human pose estimation, on several architectures. On COCO test-dev, our single model based on CSN achieves 46.5 mAP with a ResNet-101 backbone, which is among the state-of-the-art (SOTA) candidates for object detection.
Tasks	Instance Segmentation, Object Detection, Object Recognition, Pose Estimation, Semantic Segmentation
Published	2019-08-20
URL	https://arxiv.org/abs/1908.07323v1
PDF	https://arxiv.org/pdf/1908.07323v1.pdf
PWC	https://paperswithcode.com/paper/consistent-scale-normalization-for-object
Repo
Framework

Estimation of Orientation and Camera Parameters from Cryo-Electron Microscopy Images with Variational Autoencoders and Generative Adversarial Networks


Title	Estimation of Orientation and Camera Parameters from Cryo-Electron Microscopy Images with Variational Autoencoders and Generative Adversarial Networks
Authors	Nina Miolane, Frédéric Poitevin, Yee-Ting Li, Susan Holmes
Abstract	Cryo-electron microscopy (cryo-EM) is capable of producing reconstructed 3D images of biomolecules at near-atomic resolution. As such, it represents one of the most promising imaging techniques in structural biology. However, raw cryo-EM images are only highly corrupted - noisy and band-pass filtered - 2D projections of the target 3D biomolecules. Reconstructing the 3D molecular shape starts with the removal of image outliers, the estimation of the orientation of the biomolecule that has produced the given 2D image, and the estimation of camera parameters to correct for intensity defects. Current techniques performing these tasks are often computationally expensive, while the dataset sizes keep growing. There is a need for next-generation algorithms that preserve accuracy while improving speed and scalability. In this paper, we combine variational autoencoders (VAEs) and generative adversarial networks (GANs) to learn a low-dimensional latent representation of cryo-EM images. We perform an exploratory analysis of the obtained latent space, that is shown to have a structure of “orbits”, in the sense of Lie group theory, consistent with the acquisition procedure of cryo-EM images. This analysis leads us to design an estimation method for orientation and camera parameters of single-particle cryo-EM images, together with an outliers detection procedure. As such, it opens the door to geometric approaches for unsupervised estimations of orientations and camera parameters, making possible fast cryo-EM biomolecule reconstruction.
Tasks
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08121v1
PDF	https://arxiv.org/pdf/1911.08121v1.pdf
PWC	https://paperswithcode.com/paper/estimation-of-orientation-and-camera
Repo
Framework

Outlier Robust Extreme Learning Machine for Multi-Target Regression


Title	Outlier Robust Extreme Learning Machine for Multi-Target Regression
Authors	Bruno Légora Souza da Silva, Fernando Kentaro Inaba, Evandro Ottoni Teatini Salles, Patrick Marques Ciarelli
Abstract	The popularity of algorithms based on Extreme Learning Machine (ELM), which can be used to train Single Layer Feedforward Neural Networks (SLFN), has increased in the past years. They have been successfully applied to a wide range of classification and regression tasks. The most commonly used methods are the ones based on minimizing the $\ell_2$ norm of the error, which is not suitable to deal with outliers, essentially in regression tasks. The use of $\ell_1$ norm was proposed in Outlier Robust ELM (OR-ELM), which is defined to one-dimensional outputs. In this paper, we generalize OR-ELM to deal with multi-target regression problems, using the error $\ell_{2,1}$ norm and the Elastic Net theory, which can result in a more sparse network, resulting in our method, Generalized Outlier Robust ELM (GOR-ELM). We use Alternating Direction Method of Multipliers (ADMM) to solve the resulting optimization problem. An incremental version of GOR-ELM is also proposed. We chose 15 public real-world multi-target regression datasets to test our methods. Our conducted experiments show that they are statistically better than other ELM-based techniques, when considering data contaminated with outliers, and equivalent to them, otherwise.
Tasks
Published	2019-05-22
URL	https://arxiv.org/abs/1905.09368v2
PDF	https://arxiv.org/pdf/1905.09368v2.pdf
PWC	https://paperswithcode.com/paper/outlier-robust-extreme-learning-machine-for
Repo
Framework

PAC learning with stable and private predictions


Title	PAC learning with stable and private predictions
Authors	Yuval Dagan, Vitaly Feldman
Abstract	We study binary classification algorithms for which the prediction on any point is not too sensitive to individual examples in the dataset. Specifically, we consider the notions of uniform stability (Bousquet and Elisseeff, 2001) and prediction privacy (Dwork and Feldman, 2018). Previous work on these notions shows how they can be achieved in the standard PAC model via simple aggregation of models trained on disjoint subsets of data. Unfortunately, this approach leads to a significant overhead in terms of sample complexity. Here we demonstrate several general approaches to stable and private prediction that either eliminate or significantly reduce the overhead. Specifically, we demonstrate that for any class $C$ of VC dimension $d$ there exists a $\gamma$-uniformly stable algorithm for learning $C$ with excess error $\alpha$ using $\tilde O(d/(\alpha\gamma) + d/\alpha^2)$ samples. We also show that this bound is nearly tight. For $\epsilon$-differentially private prediction we give two new algorithms: one using $\tilde O(d/(\alpha^2\epsilon))$ samples and another one using $\tilde O(d^2/(\alpha\epsilon) + d/\alpha^2)$ samples. The best previously known bounds for these problems are $O(d/(\alpha^2\gamma))$ and $O(d/(\alpha^3\epsilon))$, respectively.
Tasks
Published	2019-11-24
URL	https://arxiv.org/abs/1911.10541v1
PDF	https://arxiv.org/pdf/1911.10541v1.pdf
PWC	https://paperswithcode.com/paper/pac-learning-with-stable-and-private
Repo
Framework

Physics-based Neural Networks for Shape from Polarization


Title	Physics-based Neural Networks for Shape from Polarization
Authors	Yunhao Ba, Rui Chen, Yiqin Wang, Lei Yan, Boxin Shi, Achuta Kadambi
Abstract	How should prior knowledge from physics inform a neural network solution? We study the blending of physics and deep learning in the context of Shape from Polarization (SfP). The classic SfP problem recovers an object’s shape from polarized photographs of the scene. The SfP problem is special because the physical models are only approximate. Previous attempts to solve SfP have been purely model-based, and are susceptible to errors when real-world conditions deviate from the idealized physics. In our solution, there is a subtlety to combining physics and neural networks. Our final solution blends deep learning with synthetic renderings (derived from physics) in the framework of a two-stage encoder. The lessons learned from this exemplary problem foreshadow the future impact of physics-based learning.
Tasks
Published	2019-03-25
URL	http://arxiv.org/abs/1903.10210v1
PDF	http://arxiv.org/pdf/1903.10210v1.pdf
PWC	https://paperswithcode.com/paper/physics-based-neural-networks-for-shape-from
Repo
Framework

LScDC-new large scientific dictionary


Title	LScDC-new large scientific dictionary
Authors	Neslihan Suzen, Evgeny M. Mirkes, Alexander N. Gorban
Abstract	In this paper, we present a scientific corpus of abstracts of academic papers in English – Leicester Scientific Corpus (LSC). The LSC contains 1,673,824 abstracts of research articles and proceeding papers indexed by Web of Science (WoS) in which publication year is 2014. Each abstract is assigned to at least one of 252 subject categories. Paper metadata include these categories and the number of citations. We then develop scientific dictionaries named Leicester Scientific Dictionary (LScD) and Leicester Scientific Dictionary-Core (LScDC), where words are extracted from the LSC. The LScD is a list of 974,238 unique words (lemmas). The LScDC is a core list (sub-list) of the LScD with 104,223 lemmas. It was created by removing LScD words appearing in not greater than 10 texts in the LSC. LScD and LScDC are available online. Both the corpus and dictionaries are developed to be later used for quantification of meaning in academic texts. Finally, the core list LScDC was analysed by comparing its words and word frequencies with a classic academic word list ‘New Academic Word List (NAWL)’ containing 963 word families, which is also sampled from an academic corpus. The major sources of the corpus where NAWL is extracted are Cambridge English Corpus (CEC), oral sources and textbooks. We investigate whether two dictionaries are similar in terms of common words and ranking of words. Our comparison leads us to main conclusion: most of words of NAWL (99.6%) are present in the LScDC but two lists differ in word ranking. This difference is measured.
Tasks
Published	2019-12-14
URL	https://arxiv.org/abs/1912.06858v1
PDF	https://arxiv.org/pdf/1912.06858v1.pdf
PWC	https://paperswithcode.com/paper/lscdc-new-large-scientific-dictionary
Repo
Framework

Human-Guided Learning of Column Networks: Augmenting Deep Learning with Advice


Title	Human-Guided Learning of Column Networks: Augmenting Deep Learning with Advice
Authors	Mayukh Das, Yang Yu, Devendra Singh Dhami, Gautam Kunapuli, Sriraam Natarajan
Abstract	Recently, deep models have been successfully applied in several applications, especially with low-level representations. However, sparse, noisy samples and structured domains (with multiple objects and interactions) are some of the open challenges in most deep models. Column Networks, a deep architecture, can succinctly capture such domain structure and interactions, but may still be prone to sub-optimal learning from sparse and noisy samples. Inspired by the success of human-advice guided learning in AI, especially in data-scarce domains, we propose Knowledge-augmented Column Networks that leverage human advice/knowledge for better learning with noisy/sparse samples. Our experiments demonstrate that our approach leads to either superior overall performance or faster convergence (i.e., both effective and efficient).
Tasks
Published	2019-04-15
URL	http://arxiv.org/abs/1904.06950v1
PDF	http://arxiv.org/pdf/1904.06950v1.pdf
PWC	https://paperswithcode.com/paper/human-guided-learning-of-column-networks
Repo
Framework

The Profiling Potential of Computer Vision and the Challenge of Computational Empiricism


Title	The Profiling Potential of Computer Vision and the Challenge of Computational Empiricism
Authors	Jake Goldenfein
Abstract	Computer vision and other biometrics data science applications have commenced a new project of profiling people. Rather than using ‘transaction generated information’, these systems measure the ‘real world’ and produce an assessment of the ‘world state’ - in this case an assessment of some individual trait. Instead of using proxies or scores to evaluate people, they increasingly deploy a logic of revealing the truth about reality and the people within it. While these profiling knowledge claims are sometimes tentative, they increasingly suggest that only through computation can these excesses of reality be captured and understood. This article explores the bases of those claims in the systems of measurement, representation, and classification deployed in computer vision. It asks if there is something new in this type of knowledge claim, sketches an account of a new form of computational empiricism being operationalised, and questions what kind of human subject is being constructed by these technological systems and practices. Finally, the article explores legal mechanisms for contesting the emergence of computational empiricism as the dominant knowledge platform for understanding the world and the people within it.
Tasks
Published	2019-04-22
URL	http://arxiv.org/abs/1904.10016v1
PDF	http://arxiv.org/pdf/1904.10016v1.pdf
PWC	https://paperswithcode.com/paper/the-profiling-potential-of-computer-vision
Repo
Framework

Multi-agent Hierarchical Reinforcement Learning with Dynamic Termination


Title	Multi-agent Hierarchical Reinforcement Learning with Dynamic Termination
Authors	Dongge Han, Wendelin Boehmer, Michael Wooldridge, Alex Rogers
Abstract	In a multi-agent system, an agent’s optimal policy will typically depend on the policies chosen by others. Therefore, a key issue in multi-agent systems research is that of predicting the behaviours of others, and responding promptly to changes in such behaviours. One obvious possibility is for each agent to broadcast their current intention, for example, the currently executed option in a hierarchical reinforcement learning framework. However, this approach results in inflexibility of agents if options have an extended duration and are dynamic. While adjusting the executed option at each step improves flexibility from a single-agent perspective, frequent changes in options can induce inconsistency between an agent’s actual behaviour and its broadcast intention. In order to balance flexibility and predictability, we propose a dynamic termination Bellman equation that allows the agents to flexibly terminate their options. We evaluate our model empirically on a set of multi-agent pursuit and taxi tasks, and show that our agents learn to adapt flexibly across scenarios that require different termination behaviours.
Tasks	Hierarchical Reinforcement Learning
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09508v1
PDF	https://arxiv.org/pdf/1910.09508v1.pdf
PWC	https://paperswithcode.com/paper/multi-agent-hierarchical-reinforcement
Repo
Framework

IRNet: Instance Relation Network for Overlapping Cervical Cell Segmentation


Title	IRNet: Instance Relation Network for Overlapping Cervical Cell Segmentation
Authors	Yanning Zhou, Hao Chen, Jiaqi Xu, Qi Dou, Pheng-Ann Heng
Abstract	Cell instance segmentation in Pap smear image remains challenging due to the wide existence of occlusion among translucent cytoplasm in cell clumps. Conventional methods heavily rely on accurate nuclei detection results and are easily disturbed by miscellaneous objects. In this paper, we propose a novel Instance Relation Network (IRNet) for robust overlapping cell segmentation by exploring instance relation interaction. Specifically, we propose the Instance Relation Module to construct the cell association matrix for transferring information among individual cell-instance features. With the collaboration of different instances, the augmented features gain benefits from contextual information and improve semantic consistency. Meanwhile, we proposed a sparsity constrained Duplicate Removal Module to eliminate the misalignment between classification and localization accuracy for candidates selection. The largest cervical Pap smear (CPS) dataset with more than 8000 cell annotations in Pap smear image was constructed for comprehensive evaluation. Our method outperforms other methods by a large margin, demonstrating the effectiveness of exploring instance relation.
Tasks	Cell Segmentation, Instance Segmentation, Semantic Segmentation
Published	2019-08-19
URL	https://arxiv.org/abs/1908.06623v1
PDF	https://arxiv.org/pdf/1908.06623v1.pdf
PWC	https://paperswithcode.com/paper/irnet-instance-relation-network-for
Repo
Framework

Psycholinguistics meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answering


Title	Psycholinguistics meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answering
Authors	Claudio Greco, Barbara Plank, Raquel Fernández, Raffaella Bernardi
Abstract	We study the issue of catastrophic forgetting in the context of neural multimodal approaches to Visual Question Answering (VQA). Motivated by evidence from psycholinguistics, we devise a set of linguistically-informed VQA tasks, which differ by the types of questions involved (Wh-questions and polar questions). We test what impact task difficulty has on continual learning, and whether the order in which a child acquires question types facilitates computational models. Our results show that dramatic forgetting is at play and that task difficulty and order matter. Two well-known current continual learning methods mitigate the problem only to a limiting degree.
Tasks	Continual Learning, Question Answering, Visual Question Answering
Published	2019-06-10
URL	https://arxiv.org/abs/1906.04229v1
PDF	https://arxiv.org/pdf/1906.04229v1.pdf
PWC	https://paperswithcode.com/paper/psycholinguistics-meets-continual-learning
Repo
Framework

On regularization for a convolutional kernel in neural networks


Title	On regularization for a convolutional kernel in neural networks
Authors	Peichang Guo, Qiang Ye
Abstract	Convolutional neural network is an important model in deep learning. To avoid exploding/vanishing gradient problems and to improve the generalizability of a neural network, it is desirable to have a convolution operation that nearly preserves the norm, or to have the singular values of the transformation matrix corresponding to a convolutional kernel bounded around $1$. We propose a penalty function that can be used in the optimization of a convolutional neural network to constrain the singular values of the transformation matrix around $1$. We derive an algorithm to carry out the gradient descent minimization of this penalty function in terms of convolution kernels. Numerical examples are presented to demonstrate the effectiveness of the method.
Tasks
Published	2019-06-12
URL	https://arxiv.org/abs/1906.04866v2
PDF	https://arxiv.org/pdf/1906.04866v2.pdf
PWC	https://paperswithcode.com/paper/on-regularization-for-a-convolutional-kernel
Repo
Framework

Utility/Privacy Trade-off through the lens of Optimal Transport


Title	Utility/Privacy Trade-off through the lens of Optimal Transport
Authors	Etienne Boursier, Vianney Perchet
Abstract	Strategic information is valuable either by remaining private (for instance if it is sensitive) or, on the other hand, by being used publicly to increase some utility. These two objectives are antagonistic and leaking this information might be more rewarding than concealing it. Unlike classical solutions that focus on the first point, we consider instead agents that optimize a natural trade-off between both objectives. We formalize this as an optimization problem where the objective mapping is regularized by the amount of information revealed to the adversary (measured as a divergence between the prior and posterior on the private knowledge). Quite surprisingly, when combined with the entropic regularization, the Sinkhorn loss naturally emerges in the optimization objective, making it efficiently solvable. We apply these techniques to preserve some privacy in online repeated auctions.
Tasks
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11148v3
PDF	https://arxiv.org/pdf/1905.11148v3.pdf
PWC	https://paperswithcode.com/paper/private-learning-and-regularized-optimal
Repo
Framework

Learning Propagation for Arbitrarily-structured Data


Title	Learning Propagation for Arbitrarily-structured Data
Authors	Sifei Liu, Xueting Li, Varun Jampani, Shalini De Mello, Jan Kautz
Abstract	Processing an input signal that contains arbitrary structures, e.g., superpixels and point clouds, remains a big challenge in computer vision. Linear diffusion, an effective model for image processing, has been recently integrated with deep learning algorithms. In this paper, we propose to learn pairwise relations among data points in a global fashion to improve semantic segmentation with arbitrarily-structured data, through spatial generalized propagation networks (SGPN). The network propagates information on a group of graphs, which represent the arbitrarily-structured data, through a learned, linear diffusion process. The module is flexible to be embedded and jointly trained with many types of networks, e.g., CNNs. We experiment with semantic segmentation networks, where we use our propagation module to jointly train on different data – images, superpixels and point clouds. We show that SGPN consistently improves the performance of both pixel and point cloud segmentation, compared to networks that do not contain this module. Our method suggests an effective way to model the global pairwise relations for arbitrarily-structured data.
Tasks	Semantic Segmentation
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11237v1
PDF	https://arxiv.org/pdf/1909.11237v1.pdf
PWC	https://paperswithcode.com/paper/learning-propagation-for-arbitrarily
Repo
Framework

An Alert-Generation Framework for Improving Resiliency in Human-Supervised, Multi-Agent Teams


Title	An Alert-Generation Framework for Improving Resiliency in Human-Supervised, Multi-Agent Teams
Authors	Sarah Al-Hussaini, Jason M. Gregory, Shaurya Shriyam, Satyandra K. Gupta
Abstract	Human-supervision in multi-agent teams is a critical requirement to ensure that the decision-maker’s risk preferences are utilized to assign tasks to robots. In stressful complex missions that pose risk to human health and life, such as humanitarian-assistance and disaster-relief missions, human mistakes or delays in tasking robots can adversely affect the mission. To assist human decision making in such missions, we present an alert-generation framework capable of detecting various modes of potential failure or performance degradation. We demonstrate that our framework, based on state machine simulation and formal methods, offers probabilistic modeling to estimate the likelihood of unfavorable events. We introduce smart simulation that offers a computationally-efficient way of detecting low-probability situations compared to standard Monte-Carlo simulations. Moreover, for certain class of problems, our inference-based method can provide guarantees on correctly detecting task failures.
Tasks	Decision Making
Published	2019-09-13
URL	https://arxiv.org/abs/1909.06480v1
PDF	https://arxiv.org/pdf/1909.06480v1.pdf
PWC	https://paperswithcode.com/paper/an-alert-generation-framework-for-improving
Repo
Framework