Paper Group ANR 1767
Breast Anatomy Enriched Tumor Saliency Estimation. A dual mode adaptive basal-bolus advisor based on reinforcement learning. Efficient Projection-Free Online Methods with Stochastic Recursive Gradient. Meaning to Form: Measuring Systematicity as Information. Adversarial Feature Alignment: Avoid Catastrophic Forgetting in Incremental Task Lifelong L …
Breast Anatomy Enriched Tumor Saliency Estimation
| Title | Breast Anatomy Enriched Tumor Saliency Estimation |
| Authors | Fei Xu, Yingtao Zhang, Min Xian, H. D. Cheng, Boyu Zhang, Jianrui Ding, Chunping Ning, Ying Wang |
| Abstract | Breast cancer investigation is of great significance, and developing tumor detection methodologies is a critical need. However, it is a challenging task for breast ultrasound due to the complicated breast structure and poor quality of the images. In this paper, we propose a novel tumor saliency estimation model guided by enriched breast anatomy knowledge to localize the tumor. Firstly, the breast anatomy layers are generated by a deep neural network. Then we refine the layers by integrating a non-semantic breast anatomy model to solve the problems of incomplete mammary layers. Meanwhile, a new background map generation method weighted by the semantic probability and spatial distance is proposed to improve the performance. The experiment demonstrates that the proposed method with the new background map outperforms four state-of-the-art TSE models with increasing 10% of F_meansure on the BUS public dataset. |
| Tasks | Saliency Prediction |
| Published | 2019-10-23 |
| URL | https://arxiv.org/abs/1910.10652v1 |
| https://arxiv.org/pdf/1910.10652v1.pdf | |
| PWC | https://paperswithcode.com/paper/breast-anatomy-enriched-tumor-saliency |
| Repo | |
| Framework | |
A dual mode adaptive basal-bolus advisor based on reinforcement learning
| Title | A dual mode adaptive basal-bolus advisor based on reinforcement learning |
| Authors | Qingnan Sun, Marko V. Jankovic, João Budzinski, Brett Moore, Peter Diem, Christoph Stettler, Stavroula G. Mougiakakou |
| Abstract | Self-monitoring of blood glucose (SMBG) and continuous glucose monitoring (CGM) are commonly used by type 1 diabetes (T1D) patients to measure glucose concentrations. The proposed adaptive basal-bolus algorithm (ABBA) supports inputs from either SMBG or CGM devices to provide personalised suggestions for the daily basal rate and prandial insulin doses on the basis of the patients’ glucose level on the previous day. The ABBA is based on reinforcement learning (RL), a type of artificial intelligence, and was validated in silico with an FDA-accepted population of 100 adults under different realistic scenarios lasting three simulated months. The scenarios involve three main meals and one bedtime snack per day, along with different variabilities and uncertainties for insulin sensitivity, mealtime, carbohydrate amount, and glucose measurement time. The results indicate that the proposed approach achieves comparable performance with CGM or SMBG as input signals, without influencing the total daily insulin dose. The results are a promising indication that AI algorithmic approaches can provide personalised adaptive insulin optimisation and achieve glucose control - independently of the type of glucose monitoring technology. |
| Tasks | |
| Published | 2019-01-07 |
| URL | http://arxiv.org/abs/1901.01816v1 |
| http://arxiv.org/pdf/1901.01816v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-dual-mode-adaptive-basal-bolus-advisor |
| Repo | |
| Framework | |
Efficient Projection-Free Online Methods with Stochastic Recursive Gradient
| Title | Efficient Projection-Free Online Methods with Stochastic Recursive Gradient |
| Authors | Jiahao Xie, Zebang Shen, Chao Zhang, Boyu Wang, Hui Qian |
| Abstract | This paper focuses on projection-free methods for solving smooth Online Convex Optimization (OCO) problems. Existing projection-free methods either achieve suboptimal regret bounds or have high per-iteration computational costs. To fill this gap, two efficient projection-free online methods called ORGFW and MORGFW are proposed for solving stochastic and adversarial OCO problems, respectively. By employing a recursive gradient estimator, our methods achieve optimal regret bounds (up to a logarithmic factor) while possessing low per-iteration computational costs. Experimental results demonstrate the efficiency of the proposed methods compared to state-of-the-arts. |
| Tasks | |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09396v2 |
| https://arxiv.org/pdf/1910.09396v2.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-recursive-gradient-based-methods |
| Repo | |
| Framework | |
Meaning to Form: Measuring Systematicity as Information
| Title | Meaning to Form: Measuring Systematicity as Information |
| Authors | Tiago Pimentel, Arya D. McCarthy, Damián E. Blasi, Brian Roark, Ryan Cotterell |
| Abstract | A longstanding debate in semiotics centers on the relationship between linguistic signs and their corresponding semantics: is there an arbitrary relationship between a word form and its meaning, or does some systematic phenomenon pervade? For instance, does the character bigram \textit{gl} have any systematic relationship to the meaning of words like \textit{glisten}, \textit{gleam} and \textit{glow}? In this work, we offer a holistic quantification of the systematicity of the sign using mutual information and recurrent neural networks. We employ these in a data-driven and massively multilingual approach to the question, examining 106 languages. We find a statistically significant reduction in entropy when modeling a word form conditioned on its semantic representation. Encouragingly, we also recover well-attested English examples of systematic affixes. We conclude with the meta-point: Our approximate effect size (measured in bits) is quite small—despite some amount of systematicity between form and meaning, an arbitrary relationship and its resulting benefits dominate human language. |
| Tasks | |
| Published | 2019-06-13 |
| URL | https://arxiv.org/abs/1906.05906v2 |
| https://arxiv.org/pdf/1906.05906v2.pdf | |
| PWC | https://paperswithcode.com/paper/meaning-to-form-measuring-systematicity-as |
| Repo | |
| Framework | |
Adversarial Feature Alignment: Avoid Catastrophic Forgetting in Incremental Task Lifelong Learning
| Title | Adversarial Feature Alignment: Avoid Catastrophic Forgetting in Incremental Task Lifelong Learning |
| Authors | Xin Yao, Tianchi Huang, Chenglei Wu, Rui-Xiao Zhang, Lifeng Sun |
| Abstract | Human beings are able to master a variety of knowledge and skills with ongoing learning. By contrast, dramatic performance degradation is observed when new tasks are added to an existing neural network model. This phenomenon, termed as \emph{Catastrophic Forgetting}, is one of the major roadblocks that prevent deep neural networks from achieving human-level artificial intelligence. Several research efforts, e.g. \emph{Lifelong} or \emph{Continual} learning algorithms, have been proposed to tackle this problem. However, they either suffer from an accumulating drop in performance as the task sequence grows longer, or require to store an excessive amount of model parameters for historical memory, or cannot obtain competitive performance on the new tasks. In this paper, we focus on the incremental multi-task image classification scenario. Inspired by the learning process of human students, where they usually decompose complex tasks into easier goals, we propose an adversarial feature alignment method to avoid catastrophic forgetting. In our design, both the low-level visual features and high-level semantic features serve as soft targets and guide the training process in multiple stages, which provide sufficient supervised information of the old tasks and help to reduce forgetting. Due to the knowledge distillation and regularization phenomenons, the proposed method gains even better performance than finetuning on the new tasks, which makes it stand out from other methods. Extensive experiments in several typical lifelong learning scenarios demonstrate that our method outperforms the state-of-the-art methods in both accuracies on new tasks and performance preservation on old tasks. |
| Tasks | Continual Learning, Image Classification |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.10986v1 |
| https://arxiv.org/pdf/1910.10986v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-feature-alignment-avoid |
| Repo | |
| Framework | |
Cross-view Relation Networks for Mammogram Mass Detection
| Title | Cross-view Relation Networks for Mammogram Mass Detection |
| Authors | Jiechao Ma, Sen Liang, Xiang Li, Hongwei Li, Bjoern H Menze, Rongguo Zhang, Wei-Shi Zheng |
| Abstract | Mammogram is the most effective imaging modality for the mass lesion detection of breast cancer at the early stage. The information from the two paired views (i.e., medio-lateral oblique and cranio-caudal) are highly relational and complementary, and this is crucial for doctors’ decisions in clinical practice. However, existing mass detection methods do not consider jointly learning effective features from the two relational views. To address this issue, this paper proposes a novel mammogram mass detection framework, termed Cross-View Relation Region-based Convolutional Neural Networks (CVR-RCNN). The proposed CVR-RCNN is expected to capture the latent relation information between the corresponding mass region of interests (ROIs) from the two paired views. Evaluations on a new large-scale private dataset and a public mammogram dataset show that the proposed CVR-RCNN outperforms existing state-of-the-art mass detection methods. Meanwhile, our experimental results suggest that incorporating the relation information across two views helps to train a superior detection model, which is a promising avenue for mammogram mass detection. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://arxiv.org/abs/1907.00528v1 |
| https://arxiv.org/pdf/1907.00528v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-view-relation-networks-for-mammogram |
| Repo | |
| Framework | |
Context-Sensitive Malicious Spelling Error Correction
| Title | Context-Sensitive Malicious Spelling Error Correction |
| Authors | Hongyu Gong, Yuchen Li, Suma Bhat, Pramod Viswanath |
| Abstract | Misspelled words of the malicious kind work by changing specific keywords and are intended to thwart existing automated applications for cyber-environment control such as harassing content detection on the Internet and email spam detection. In this paper, we focus on malicious spelling correction, which requires an approach that relies on the context and the surface forms of targeted keywords. In the context of two applications–profanity detection and email spam detection–we show that malicious misspellings seriously degrade their performance. We then propose a context-sensitive approach for malicious spelling correction using word embeddings and demonstrate its superior performance compared to state-of-the-art spell checkers. |
| Tasks | Spelling Correction, Word Embeddings |
| Published | 2019-01-23 |
| URL | http://arxiv.org/abs/1901.07688v1 |
| http://arxiv.org/pdf/1901.07688v1.pdf | |
| PWC | https://paperswithcode.com/paper/context-sensitive-malicious-spelling-error |
| Repo | |
| Framework | |
Optimal In-place Algorithms for Basic Graph Problems
| Title | Optimal In-place Algorithms for Basic Graph Problems |
| Authors | Sankardeep Chakraborty, Kunihiko Sadakane, Srinivasa Rao Satti |
| Abstract | We present linear time {\it in-place} algorithms for several basic and fundamental graph problems including the well-known graph search methods (like depth-first search, breadth-first search, maximum cardinality search), connectivity problems (like biconnectivity, $2$-edge connectivity), decomposition problem (like chain decomposition) among various others, improving the running time (by polynomial multiplicative factor) of the recent results of Chakraborty et al. [ESA, 2018] who designed $O(n^3 \lg n)$ time in-place algorithms for a strict subset of the above mentioned problems. The running times of all our algorithms are essentially optimal as they run in linear time. One of the main ideas behind obtaining these algorithms is the detection and careful exploitation of sortedness present in the input representation for any graph without loss of generality. This observation alone is powerful enough to design some basic linear time in-place algorithms, but more non-trivial graph problems require extra techniques which, we believe, may find other applications while designing in-place algorithms for different graph problems in the future. |
| Tasks | |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09280v1 |
| https://arxiv.org/pdf/1907.09280v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-in-place-algorithms-for-basic-graph |
| Repo | |
| Framework | |
Truncated nuclear norm regularization for low-rank tensor completion
| Title | Truncated nuclear norm regularization for low-rank tensor completion |
| Authors | Shengke Xue, Wenyuan Qiu, Fan Liu, Xinyu Jin |
| Abstract | Recently, low-rank tensor completion has become increasingly attractive in recovering incomplete visual data. Considering a color image or video as a three-dimensional (3D) tensor, existing studies have put forward several definitions of tensor nuclear norm. However, they are limited and may not accurately approximate the real rank of a tensor, and they do not explicitly use the low-rank property in optimization. It is proved that the recently proposed truncated nuclear norm (TNN) can replace the traditional nuclear norm, as an improved approximation to the rank of a matrix. In this paper, we propose a new method called the tensor truncated nuclear norm (T-TNN), which suggests a new definition of tensor nuclear norm. The truncated nuclear norm is generalized from the matrix case to the tensor case. With the help of the low rankness of TNN, our approach improves the efficacy of tensor completion. We adopt the definition of the previously proposed tensor singular value decomposition, the alternating direction method of multipliers, and the accelerated proximal gradient line search method in our algorithm. Substantial experiments on real-world videos and images illustrate that the performance of our approach is better than those of previous methods. |
| Tasks | |
| Published | 2019-01-07 |
| URL | http://arxiv.org/abs/1901.01997v1 |
| http://arxiv.org/pdf/1901.01997v1.pdf | |
| PWC | https://paperswithcode.com/paper/truncated-nuclear-norm-regularization-for-low |
| Repo | |
| Framework | |
Active emulation of computer codes with Gaussian processes – Application to remote sensing
| Title | Active emulation of computer codes with Gaussian processes – Application to remote sensing |
| Authors | Daniel Heestermans Svendsen, Luca Martino, Gustau Camps-Valls |
| Abstract | Many fields of science and engineering rely on running simulations with complex and computationally expensive models to understand the involved processes in the system of interest. Nevertheless, the high cost involved hamper reliable and exhaustive simulations. Very often such codes incorporate heuristics that ironically make them less tractable and transparent. This paper introduces an active learning methodology for adaptively constructing surrogate models, i.e. emulators, of such costly computer codes in a multi-output setting. The proposed technique is sequential and adaptive, and is based on the optimization of a suitable acquisition function. It aims to achieve accurate approximations, model tractability, as well as compact and expressive simulated datasets. In order to achieve this, the proposed Active Multi-Output Gaussian Process Emulator (AMOGAPE) combines the predictive capacity of Gaussian Processes (GPs) with the design of an acquisition function that favors sampling in low density and fluctuating regions of the approximation functions. Comparing different acquisition functions, we illustrate the promising performance of the method for the construction of emulators with toy examples, as well as for a widely used remote sensing transfer code. |
| Tasks | Active Learning, Gaussian Processes |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.06552v1 |
| https://arxiv.org/pdf/1912.06552v1.pdf | |
| PWC | https://paperswithcode.com/paper/active-emulation-of-computer-codes-with |
| Repo | |
| Framework | |
Neural Cognitive Diagnosis for Intelligent Education Systems
| Title | Neural Cognitive Diagnosis for Intelligent Education Systems |
| Authors | Fei Wang, Qi Liu, Enhong Chen, Zhenya Huang, Yuying Chen, Yu Yin, Zai Huang, Shijin Wang |
| Abstract | Cognitive diagnosis is a fundamental issue in intelligent education, which aims to discover the proficiency level of students on specific knowledge concepts. Existing approaches usually mine linear interactions of student exercising process by manual-designed function (e.g., logistic function), which is not sufficient for capturing complex relations between students and exercises. In this paper, we propose a general Neural Cognitive Diagnosis (NeuralCD) framework, which incorporates neural networks to learn the complex exercising interactions, for getting both accurate and interpretable diagnosis results. Specifically, we project students and exercises to factor vectors and leverage multi neural layers for modeling their interactions, where the monotonicity assumption is applied to ensure the interpretability of both factors. Furthermore, we propose two implementations of NeuralCD by specializing the required concepts of each exercise, i.e., the NeuralCDM with traditional Q-matrix and the improved NeuralCDM+ exploring the rich text content. Extensive experimental results on real-world datasets show the effectiveness of NeuralCD framework with both accuracy and interpretability. |
| Tasks | |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.08733v3 |
| https://arxiv.org/pdf/1908.08733v3.pdf | |
| PWC | https://paperswithcode.com/paper/interpretable-cognitive-diagnosis-with-neural |
| Repo | |
| Framework | |
Range Adaptation for 3D Object Detection in LiDAR
| Title | Range Adaptation for 3D Object Detection in LiDAR |
| Authors | Ze Wang, Sihao Ding, Ying Li, Minming Zhao, Sohini Roychowdhury, Andreas Wallin, Guillermo Sapiro, Qiang Qiu |
| Abstract | LiDAR-based 3D object detection plays a crucial role in modern autonomous driving systems. LiDAR data often exhibit severe changes in properties across different observation ranges. In this paper, we explore cross-range adaptation for 3D object detection using LiDAR, i.e., far-range observations are adapted to near-range. This way, far-range detection is optimized for similar performance to near-range one. We adopt a bird-eyes view (BEV) detection framework to perform the proposed model adaptation. Our model adaptation consists of an adversarial global adaptation, and a fine-grained local adaptation. The proposed cross range adaptation framework is validated on three state-of-the-art LiDAR based object detection networks, and we consistently observe performance improvement on the far-range objects, without adding any auxiliary parameters to the model. To the best of our knowledge, this paper is the first attempt to study cross-range LiDAR adaptation for object detection in point clouds. To demonstrate the generality of the proposed adaptation framework, experiments on more challenging cross-device adaptation are further conducted, and a new LiDAR dataset with high-quality annotated point clouds is released to promote future research. |
| Tasks | 3D Object Detection, Autonomous Driving, Object Detection |
| Published | 2019-09-26 |
| URL | https://arxiv.org/abs/1909.12249v1 |
| https://arxiv.org/pdf/1909.12249v1.pdf | |
| PWC | https://paperswithcode.com/paper/range-adaptation-for-3d-object-detection-in |
| Repo | |
| Framework | |
Rethinking Generalisation
| Title | Rethinking Generalisation |
| Authors | Antonia Marcu, Adam Prügel-Bennett |
| Abstract | In this paper, a new approach to computing the generalisation performance is presented that assumes the distribution of risks, $\rho(r)$, for a learning scenario is known. From this, the expected error of a learning machine using empirical risk minimisation is computed for both classification and regression problems. A critical quantity in determining the generalisation performance is the power-law behaviour of $\rho(r)$ around its minimum value—a quantity we call attunement. The distribution $\rho(r)$ is computed for the case of all Boolean functions and for the perceptron used in two different problem settings. Initially a simplified analysis is presented where an independence assumption about the losses is made. A more accurate analysis is carried out taking into account chance correlations in the training set. This leads to corrections in the typical behaviour that is observed. |
| Tasks | |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04301v2 |
| https://arxiv.org/pdf/1911.04301v2.pdf | |
| PWC | https://paperswithcode.com/paper/rethinking-generalisation |
| Repo | |
| Framework | |
Physics Informed Data Driven model for Flood Prediction: Application of Deep Learning in prediction of urban flood development
| Title | Physics Informed Data Driven model for Flood Prediction: Application of Deep Learning in prediction of urban flood development |
| Authors | Kun Qian, Abduallah Mohamed, Christian Claudel |
| Abstract | Flash floods in urban areas occur with increasing frequency. Detecting these floods would greatlyhelp alleviate human and economic losses. However, current flood prediction methods are eithertoo slow or too simplified to capture the flood development in details. Using Deep Neural Networks,this work aims at boosting the computational speed of a physics-based 2-D urban flood predictionmethod, governed by the Shallow Water Equation (SWE). Convolutional Neural Networks(CNN)and conditional Generative Adversarial Neural Networks(cGANs) are applied to extract the dy-namics of flood from the data simulated by a Partial Differential Equation(PDE) solver. Theperformance of the data-driven model is evaluated in terms of Mean Squared Error(MSE) andPeak Signal to Noise Ratio(PSNR). The deep learning-based, data-driven flood prediction modelis shown to be able to provide precise real-time predictions of flood development |
| Tasks | |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.10312v1 |
| https://arxiv.org/pdf/1908.10312v1.pdf | |
| PWC | https://paperswithcode.com/paper/physics-informed-data-driven-model-for-flood |
| Repo | |
| Framework | |
Normalisation of Weights and Firing Rates in Spiking Neural Networks with Spike-Timing-Dependent Plasticity
| Title | Normalisation of Weights and Firing Rates in Spiking Neural Networks with Spike-Timing-Dependent Plasticity |
| Authors | Katarzyna Kozdon, Peter Bentley |
| Abstract | Maintaining the ability to fire sparsely is crucial for information encoding in neural networks. Additionally, spiking homeostasis is vital for spiking neural networks with changing numbers of weights and neurons. We discuss a range of network stabilisation approaches, inspired by homeostatic synaptic plasticity mechanisms reported in the brain. These include weight scaling, and weight change as a function of the network’s spiking activity. We tested normalisation of the sum of weights for all neurons, and by neuron type. We examined how this approach affects firing rate and performance on clustering of time-series data in the form of moving geometric shapes. We found that neuron type-specific normalisation is a promising approach for preventing weight drift in spiking neural networks, thus enabling longer training cycles. It can be adapted for networks with architectural plasticity. |
| Tasks | Time Series |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1910.00122v1 |
| https://arxiv.org/pdf/1910.00122v1.pdf | |
| PWC | https://paperswithcode.com/paper/normalisation-of-weights-and-firing-rates-in |
| Repo | |
| Framework | |
