Paper Group ANR 90
Pre-Training Graph Neural Networks for Generic Structural Feature Extraction. Remote Photoplethysmograph Signal Measurement from Facial Videos Using Spatio-Temporal Networks. Sketchforme: Composing Sketched Scenes from Text Descriptions for Interactive Applications. Steady-State Control and Machine Learning of Large-Scale Deformable Mirror Models. …
Pre-Training Graph Neural Networks for Generic Structural Feature Extraction
| Title | Pre-Training Graph Neural Networks for Generic Structural Feature Extraction |
| Authors | Ziniu Hu, Changjun Fan, Ting Chen, Kai-Wei Chang, Yizhou Sun |
| Abstract | Graph neural networks (GNNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GNN model requires a large collection of labeled data and expressive features, which might be inaccessible for some applications. To tackle this problem, we propose a pre-training framework that captures generic graph structural information that is transferable across tasks. Our framework can leverage the following three tasks: 1) denoising link reconstruction, 2) centrality score ranking, and 3) cluster preserving. The pre-training procedure can be conducted purely on the synthetic graphs, and the pre-trained GNN is then adapted for downstream applications. With the proposed pre-training procedure, the generic structural information is learned and preserved, thus the pre-trained GNN requires less amount of labeled data and fewer domain-specific features to achieve high performance on different downstream tasks. Comprehensive experiments demonstrate that our proposed framework can significantly enhance the performance of various tasks at the level of node, link, and graph. |
| Tasks | Denoising |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13728v1 |
| https://arxiv.org/pdf/1905.13728v1.pdf | |
| PWC | https://paperswithcode.com/paper/pre-training-graph-neural-networks-for |
| Repo | |
| Framework | |
Remote Photoplethysmograph Signal Measurement from Facial Videos Using Spatio-Temporal Networks
| Title | Remote Photoplethysmograph Signal Measurement from Facial Videos Using Spatio-Temporal Networks |
| Authors | Zitong Yu, Xiaobai Li, Guoying Zhao |
| Abstract | Recent studies demonstrated that the average heart rate (HR) can be measured from facial videos based on non-contact remote photoplethysmography (rPPG). However for many medical applications (e.g., atrial fibrillation (AF) detection) knowing only the average HR is not sufficient, and measuring precise rPPG signals from face for heart rate variability (HRV) analysis is needed. Here we propose an rPPG measurement method, which is the first work to use deep spatio-temporal networks for reconstructing precise rPPG signals from raw facial videos. With the constraint of trend-consistency with ground truth pulse curves, our method is able to recover rPPG signals with accurate pulse peaks. Comprehensive experiments are conducted on two benchmark datasets, and results demonstrate that our method can achieve superior performance on both HR and HRV levels comparing to the state-of-the-art methods. We also achieve promising results of using reconstructed rPPG signals for AF detection and emotion recognition. |
| Tasks | Emotion Recognition, Heart Rate Variability |
| Published | 2019-05-07 |
| URL | https://arxiv.org/abs/1905.02419v2 |
| https://arxiv.org/pdf/1905.02419v2.pdf | |
| PWC | https://paperswithcode.com/paper/recovering-remote-photoplethysmograph-signal |
| Repo | |
| Framework | |
Sketchforme: Composing Sketched Scenes from Text Descriptions for Interactive Applications
| Title | Sketchforme: Composing Sketched Scenes from Text Descriptions for Interactive Applications |
| Authors | Forrest Huang, John F. Canny |
| Abstract | Sketching and natural languages are effective communication media for interactive applications. We introduce Sketchforme, the first neural-network-based system that can generate sketches based on text descriptions specified by users. Sketchforme is capable of gaining high-level and low-level understanding of multi-object sketched scenes without being trained on sketched scene datasets annotated with text descriptions. The sketches composed by Sketchforme are expressive and realistic: we show in our user study that these sketches convey descriptions better than human-generated sketches in multiple cases, and 36.5% of those sketches are considered to be human-generated. We develop multiple interactive applications using these generated sketches, and show that Sketchforme can significantly improve language learning applications and support intelligent language-based sketching assistants. |
| Tasks | |
| Published | 2019-04-08 |
| URL | http://arxiv.org/abs/1904.04399v1 |
| http://arxiv.org/pdf/1904.04399v1.pdf | |
| PWC | https://paperswithcode.com/paper/sketchforme-composing-sketched-scenes-from |
| Repo | |
| Framework | |
Steady-State Control and Machine Learning of Large-Scale Deformable Mirror Models
| Title | Steady-State Control and Machine Learning of Large-Scale Deformable Mirror Models |
| Authors | Aleksandar Haber |
| Abstract | We use Machine Learning (ML) and system identification validation approaches to estimate neural network models of large-scale Deformable Mirrors (DMs) used in Adaptive Optics (AO) systems. To obtain the training, validation, and test data sets, we simulate a realistic large-scale Finite Element (FE) model of a faceplate DM. The estimated models reproduce the input-output behavior of Vector AutoRegressive with eXogenous (VARX) input models and can be used for the design of high-performance AO systems. We address the model order selection and overfitting problems. We also provide an FE based approach for computing steady-state control signals that produce the desired wavefront shape. This approach can be used to predict the steady-state DM correction performance for different actuator spacings and configurations. The presented methods are tested on models with thousands of state variables and hundreds of actuators. The numerical simulations are performed on low-cost high-performance graphic processing units and implemented using the TensorFlow machine learning framework. The used codes are available online. The approaches presented in this paper are useful for the design and optimization of high-performance DMs and AO systems. |
| Tasks | |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07456v1 |
| https://arxiv.org/pdf/1911.07456v1.pdf | |
| PWC | https://paperswithcode.com/paper/steady-state-control-and-machine-learning-of |
| Repo | |
| Framework | |
Reward Potentials for Planning with Learned Neural Network Transition Models
| Title | Reward Potentials for Planning with Learned Neural Network Transition Models |
| Authors | Buser Say, Scott Sanner, Sylvie Thiébaux |
| Abstract | Optimal planning with respect to learned neural network (NN) models in continuous action and state spaces using mixed-integer linear programming (MILP) is a challenging task for branch-and-bound solvers due to the poor linear relaxation of the underlying MILP model. For a given set of features, potential heuristics provide an efficient framework for computing bounds on cost (reward) functions. In this paper, we model the problem of finding optimal potential bounds for learned NN models as a bilevel program, and solve it using a novel finite-time constraint generation algorithm. We then strengthen the linear relaxation of the underlying MILP model by introducing constraints to bound the reward function based on the precomputed reward potentials. Experimentally, we show that our algorithm efficiently computes reward potentials for learned NN models, and that the overhead of computing reward potentials is justified by the overall strengthening of the underlying MILP model for the task of planning over long horizons. |
| Tasks | |
| Published | 2019-04-19 |
| URL | https://arxiv.org/abs/1904.09366v4 |
| https://arxiv.org/pdf/1904.09366v4.pdf | |
| PWC | https://paperswithcode.com/paper/190409366 |
| Repo | |
| Framework | |
Advances in Computer-Aided Diagnosis of Diabetic Retinopathy
| Title | Advances in Computer-Aided Diagnosis of Diabetic Retinopathy |
| Authors | Saket S. Chaturvedi, Kajol Gupta, Vaishali Ninawe, Prakash S. Prasad |
| Abstract | Diabetic Retinopathy is a critical health problem influences 100 million individuals worldwide, and these figures are expected to rise, particularly in Asia. Diabetic Retinopathy is a chronic eye disease which can lead to irreversible vision loss. Considering the visual complexity of retinal images, the early-stage diagnosis of Diabetic Retinopathy can be challenging for human experts. However, Early detection of Diabetic Retinopathy can significantly help to avoid permanent vision loss. The capability of computer-aided detection systems to accurately and efficiently detect the diabetic retinopathy had popularized them among researchers. In this review paper, the literature search was conducted on PubMed, Google Scholar, IEEE Explorer with a focus on the computer-aided detection of Diabetic Retinopathy using either of Machine Learning or Deep Learning algorithms. Moreover, this study also explores the typical methodology utilized for the computer-aided diagnosis of Diabetic Retinopathy. This review paper is aimed to direct the researchers about the limitations of current methods and identify the specific areas in the field to boost future research. |
| Tasks | |
| Published | 2019-09-21 |
| URL | https://arxiv.org/abs/1909.09853v1 |
| https://arxiv.org/pdf/1909.09853v1.pdf | |
| PWC | https://paperswithcode.com/paper/190909853 |
| Repo | |
| Framework | |
Learning discriminative features in sequence training without requiring framewise labelled data
| Title | Learning discriminative features in sequence training without requiring framewise labelled data |
| Authors | Jun Wang, Dan Su, Jie Chen, Shulin Feng, Dongpeng Ma, Na Li, Dong Yu |
| Abstract | In this work, we try to answer two questions: Can deeply learned features with discriminative power benefit an ASR system’s robustness to acoustic variability? And how to learn them without requiring framewise labelled sequence training data? As existing methods usually require knowing where the labels occur in the input sequence, they have so far been limited to many real-world sequence learning tasks. We propose a novel method which simultaneously models both the sequence discriminative training and the feature discriminative learning within a single network architecture, so that it can learn discriminative deep features in sequence training that obviates the need for presegmented training data. Our experiment in a realistic industrial ASR task shows that, without requiring any specific fine-tuning or additional complexity, our proposed models have consistently outperformed state-of-the-art models and significantly reduced Word Error Rate (WER) under all test conditions, and especially with highest improvements under unseen noise conditions, by relative 12.94%, 8.66% and 5.80%, showing our proposed models can generalize better to acoustic variability. |
| Tasks | |
| Published | 2019-05-16 |
| URL | https://arxiv.org/abs/1905.06907v1 |
| https://arxiv.org/pdf/1905.06907v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-discriminative-features-in-sequence |
| Repo | |
| Framework | |
A hierarchical approach to deep learning and its application to tomographic reconstruction
| Title | A hierarchical approach to deep learning and its application to tomographic reconstruction |
| Authors | Lin Fu, Bruno De Man |
| Abstract | Deep learning (DL) has shown unprecedented performance for many image analysis and image enhancement tasks. Yet, solving large-scale inverse problems like tomographic reconstruction remains challenging for DL. These problems involve non-local and space-variant integral transforms between the input and output domains, for which no efficient neural network models have been found. A prior attempt to solve such problems with supervised learning relied on a brute-force fully connected network and applied it to reconstruction for a $128^4$ system matrix size. This cannot practically scale to realistic data sizes such as $512^4$ and $512^6$ for three-dimensional data sets. Here we present a novel framework to solve such problems with deep learning by casting the original problem as a continuum of intermediate representations between the input and output data. The original problem is broken down into a sequence of simpler transformations that can be well mapped onto an efficient hierarchical network architecture, with exponentially fewer parameters than a generic network would need. We applied the approach to computed tomography (CT) image reconstruction for a $512^4$ system matrix size. To our knowledge, this enabled the first data-driven DL solver for full-size CT reconstruction without relying on the structure of direct (analytical) or iterative (numerical) inversion techniques. The proposed approach is applicable to other imaging problems such as emission and magnetic resonance reconstruction. More broadly, hierarchical DL opens the door to a new class of solvers for general inverse problems, which could potentially lead to improved signal-to-noise ratio, spatial resolution and computational efficiency in various areas. |
| Tasks | Computed Tomography (CT), Image Enhancement, Image Reconstruction |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07743v1 |
| https://arxiv.org/pdf/1912.07743v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-hierarchical-approach-to-deep-learning-and |
| Repo | |
| Framework | |
Hyperspectral holography and spectroscopy: computational features of inverse discrete cosine transform
| Title | Hyperspectral holography and spectroscopy: computational features of inverse discrete cosine transform |
| Authors | Vladimir Katkovnik, Igor Shevkunov, Karen Egiazarian |
| Abstract | Broadband hyperspectral digital holography and Fourier transform spectroscopy are important instruments in various science and application fields. In the digital hyperspectral holography and spectroscopy the variable of interest are obtained as inverse discrete cosine transforms of observed diffractive intensity patterns. In these notes, we provide a variety of algorithms for the inverse cosine transform with the proofs of perfect spectrum reconstruction, as well as we discuss and illustrate some nontrivial features of these algorithms. |
| Tasks | |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.03013v1 |
| https://arxiv.org/pdf/1910.03013v1.pdf | |
| PWC | https://paperswithcode.com/paper/hyperspectral-holography-and-spectroscopy |
| Repo | |
| Framework | |
Why Couldn’t You do that? Explaining Unsolvability of Classical Planning Problems in the Presence of Plan Advice
| Title | Why Couldn’t You do that? Explaining Unsolvability of Classical Planning Problems in the Presence of Plan Advice |
| Authors | Sarath Sreedharan, Siddharth Srivastava, David Smith, Subbarao Kambhampati |
| Abstract | Explainable planning is widely accepted as a prerequisite for autonomous agents to successfully work with humans. While there has been a lot of research on generating explanations of solutions to planning problems, explaining the absence of solutions remains an open and under-studied problem, even though such situations can be the hardest to understand or debug. In this paper, we show that hierarchical abstractions can be used to efficiently generate reasons for unsolvability of planning problems. In contrast to related work on computing certificates of unsolvability, we show that these methods can generate compact, human-understandable reasons for unsolvability. Empirical analysis and user studies show the validity of our methods as well as their computational efficacy on a number of benchmark planning domains. |
| Tasks | |
| Published | 2019-03-19 |
| URL | http://arxiv.org/abs/1903.08218v1 |
| http://arxiv.org/pdf/1903.08218v1.pdf | |
| PWC | https://paperswithcode.com/paper/why-couldnt-you-do-that-explaining |
| Repo | |
| Framework | |
Preimplantation Blastomere Boundary Identification in HMC Microscopic Images of Early Stage Human Embryos
| Title | Preimplantation Blastomere Boundary Identification in HMC Microscopic Images of Early Stage Human Embryos |
| Authors | Shakiba Kheradmand, Parvaneh Saeedi, Jason Au, John Havelock |
| Abstract | We present a novel method for identification of the boundary of embryonic cells (blastomeres) in Hoffman Modulation Contrast (HMC) microscopic images that are taken between day one to day three. Identification of boundaries of blastomeres is a challenging task, especially in the cases containing four or more cells. This is because these cells are bundled up tightly inside an embryo’s membrane and any 2D image projection of such 3D embryo includes cell overlaps, occlusions, and projection ambiguities. Moreover, human embryos include fragmentation, which does not conform to any specific patterns or shape. Here we developed a model-based iterative approach, in which blastomeres are modeled as ellipses that conform to the local image features, such as edges and normals. In an iterative process, each image feature contributes only to one candidate and is removed upon being associated to a model candidate. We have tested the proposed algorithm on an image dataset comprising of 468 human embryos obtained from different sources. An overall Precision, Sensitivity and Overall Quality (OQ) of 92%, 88% and 83% are achieved. |
| Tasks | |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.05972v1 |
| https://arxiv.org/pdf/1910.05972v1.pdf | |
| PWC | https://paperswithcode.com/paper/preimplantation-blastomere-boundary |
| Repo | |
| Framework | |
Semantics Preserving Adversarial Learning
| Title | Semantics Preserving Adversarial Learning |
| Authors | Ousmane Amadou Dia, Elnaz Barshan, Reza Babanezhad |
| Abstract | While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains a challenge. In this paper, we propose a framework to generate semantics preserving adversarial examples. First, we present a manifold learning method to capture the semantics of the inputs. The motivating principle is to learn the low-dimensional geometric summaries of the inputs via statistical inference. Then, we perturb the elements of the learned manifold using the Gram-Schmidt process to induce the perturbed elements to remain in the manifold. To produce adversarial examples, we propose an efficient algorithm whereby we leverage the semantics of the inputs as a source of knowledge upon which we impose adversarial constraints. We apply our approach on toy data, images and text, and show its effectiveness in producing semantics preserving adversarial examples which evade existing defenses against adversarial attacks. |
| Tasks | Text Classification |
| Published | 2019-03-10 |
| URL | https://arxiv.org/abs/1903.03905v5 |
| https://arxiv.org/pdf/1903.03905v5.pdf | |
| PWC | https://paperswithcode.com/paper/manifold-preserving-adversarial-learning |
| Repo | |
| Framework | |
Natural Analysts in Adaptive Data Analysis
| Title | Natural Analysts in Adaptive Data Analysis |
| Authors | Tijana Zrnic, Moritz Hardt |
| Abstract | Adaptive data analysis is frequently criticized for its pessimistic generalization guarantees. The source of these pessimistic bounds is a model that permits arbitrary, possibly adversarial analysts that optimally use information to bias results. While being a central issue in the field, still lacking are notions of natural analysts that allow for more optimistic bounds faithful to the reality that typical analysts aren’t adversarial. In this work, we propose notions of natural analysts that smoothly interpolate between the optimal non-adaptive bounds and the best-known adaptive generalization bounds. To accomplish this, we model the analyst’s knowledge as evolving according to the rules of an unknown dynamical system that takes in revealed information and outputs new statistical queries to the data. This allows us to restrict the analyst through different natural control-theoretic notions. One such notion corresponds to a recency bias, formalizing an inability to arbitrarily use distant information. Another complementary notion formalizes an anchoring bias, a tendency to weight initial information more strongly. Both notions come with quantitative parameters that smoothly interpolate between the non-adaptive case and the fully adaptive case, allowing for a rich spectrum of intermediate analysts that are neither non-adaptive nor adversarial. Natural not only from a cognitive perspective, we show that our notions also capture standard optimization methods, like gradient descent in various settings. This gives a new interpretation to the fact that gradient descent tends to overfit much less than its adaptive nature might suggest. |
| Tasks | |
| Published | 2019-01-30 |
| URL | https://arxiv.org/abs/1901.11143v2 |
| https://arxiv.org/pdf/1901.11143v2.pdf | |
| PWC | https://paperswithcode.com/paper/natural-analysts-in-adaptive-data-analysis |
| Repo | |
| Framework | |
A Comparison of Techniques for Sentiment Classification of Film Reviews
| Title | A Comparison of Techniques for Sentiment Classification of Film Reviews |
| Authors | Milan Gritta |
| Abstract | We undertake the task of comparing lexicon-based sentiment classification of film reviews with machine learning approaches. We look at existing methodologies and attempt to emulate and improve on them using a ‘given’ lexicon and a bag-of-words approach. We also utilise syntactical information such as part-of-speech and dependency relations. We will show that a simple lexicon-based classification achieves good results however machine learning techniques prove to be the superior tool. We also show that more features do not necessarily deliver better performance as well as elaborate on three further enhancements not tested in this article. |
| Tasks | Sentiment Analysis |
| Published | 2019-05-12 |
| URL | https://arxiv.org/abs/1905.04727v1 |
| https://arxiv.org/pdf/1905.04727v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comparison-of-techniques-for-sentiment |
| Repo | |
| Framework | |
Mix-review: Alleviate Forgetting in the Pretrain-Finetune Framework for Neural Language Generation Models
| Title | Mix-review: Alleviate Forgetting in the Pretrain-Finetune Framework for Neural Language Generation Models |
| Authors | Tianxing He, Jun Liu, Kyunghyun Cho, Myle Ott, Bing Liu, James Glass, Fuchun Peng |
| Abstract | In this work, we study how the large-scale pretrain-finetune framework changes the behavior of a neural language generator. We focus on the transformer encoder-decoder model for the open-domain dialogue response generation task. We find that after standard fine-tuning, the model forgets important language generation skills acquired during large-scale pre-training. We demonstrate the forgetting phenomenon through a detailed behavior analysis from the perspectives of context sensitivity and knowledge transfer. Adopting the concept of data mixing, we propose an intuitive fine-tuning strategy named “mix-review”. We find that mix-review effectively regularize the fine-tuning process, and the forgetting problem is largely alleviated. Finally, we discuss interesting behavior of the resulting dialogue model and its implications. |
| Tasks | Text Generation, Transfer Learning |
| Published | 2019-10-16 |
| URL | https://arxiv.org/abs/1910.07117v3 |
| https://arxiv.org/pdf/1910.07117v3.pdf | |
| PWC | https://paperswithcode.com/paper/mix-review-alleviate-forgetting-in-the |
| Repo | |
| Framework | |
