Liquid State Machines are brain inspired spiking neural networks (SNNs) with random reservoir connectivity and bio-mimetic neuronal and synaptic models. Reservoir computing networks are proposed as an alternative to deep neural networks to solve temporal classification problems. Previous studies suggest 2nd order (double exponential) synaptic waveform to be crucial for achieving high accuracy for TI-46 spoken digits recognition. The proposal of long-time range (ms) bio-mimetic synaptic waveforms is a challenge to compact and power efficient neuromorphic hardware. In this work, we analyze the role of synaptic orders namely: {\delta} (high output for single time step), 0th (rectangular with a finite pulse width), 1st (exponential fall) and 2nd order (exponential rise and fall) and synaptic timescales on the reservoir output response and on the TI-46 spoken digits classification accuracy under a more comprehensive parameter sweep. We find the optimal operating point to be correlated to an optimal range of spiking activity in the reservoir. Further, the proposed 0th order synapses perform at par with the biologically plausible 2nd order synapses. This is substantial relaxation for circuit designers as synapses are the most abundant components in an in-memory implementation for SNNs. The circuit benefits for both analog and mixed-signal realizations of 0th order synapse are highlighted demonstrating 2-3 orders of savings in area and power consumptions by eliminating Op-Amps and Digital to Analog Converter circuits. This has major implications on a complete neural network implementation with focus on peripheral limitations and algorithmic simplifications to overcome them.
Few-shot classification aims to recognize unseen classes with few labeled samples from each class. Many meta-learning models for few-shot classification elaborately design various task-shared inductive bias (meta-knowledge) to solve such tasks, and achieve impressive performance. However, when there exists the domain shift between the training tasks and the test tasks, the obtained inductive bias fails to generalize across domains, which degrades the performance of the meta-learning models. In this work, we aim to improve the robustness of the inductive bias through task augmentation. Concretely, we consider the worst-case problem around the source task distribution, and propose the adversarial task augmentation method which can generate the inductive bias-adaptive 'challenging' tasks. Our method can be used as a simple plug-and-play module for various meta-learning models, and improve their cross-domain generalization capability. We conduct extensive experiments under the cross-domain setting, using nine few-shot classification datasets: mini-ImageNet, CUB, Cars, Places, Plantae, CropDiseases, EuroSAT, ISIC and ChestX. Experimental results show that our method can effectively improve the few-shot classification performance of the meta-learning models under domain shift, and outperforms the existing works. Our code is available at https://github.com/Haoqing-Wang/CDFSL-ATA.
Many fundamental machine learning tasks can be formulated as a problem of learning with vector-valued functions, where we learn multiple scalar-valued functions together. Although there is some generalization analysis on different specific algorithms under the empirical risk minimization principle, a unifying analysis of vector-valued learning under a regularization framework is still lacking. In this paper, we initiate the generalization analysis of regularized vector-valued learning algorithms by presenting bounds with a mild dependency on the output dimension and a fast rate on the sample size. Our discussions relax the existing assumptions on the restrictive constraint of hypothesis spaces, smoothness of loss functions and low-noise condition. To understand the interaction between optimization and learning, we further use our results to derive the first generalization bounds for stochastic gradient descent with vector-valued functions. We apply our general results to multi-class classification and multi-label classification, which yield the first bounds with a logarithmic dependency on the output dimension for extreme multi-label classification with the Frobenius regularization. As a byproduct, we derive a Rademacher complexity bound for loss function classes defined in terms of a general strongly convex function.
Autonomous driving is rapidly advancing, and Level 2 functions are becoming a standard feature. One of the foremost outstanding hurdles is to obtain robust visual perception in harsh weather and low light conditions where accuracy degradation is severe. It is critical to have a weather classification model to decrease visual perception confidence during these scenarios. Thus, we have built a new dataset for weather (fog, rain, and snow) classification and light level (bright, moderate, and low) classification. Furthermore, we provide street type (asphalt, grass, and cobblestone) classification, leading to 9 labels. Each image has three labels corresponding to weather, light level, and street type. We recorded the data utilizing an industrial front camera of RCCC (red/clear) format with a resolution of $1024\times1084$. We collected 15k video sequences and sampled 60k images. We implement an active learning framework to reduce the dataset's redundancy and find the optimal set of frames for training a model. We distilled the 60k images further to 1.1k images, which will be shared publicly after privacy anonymization. There is no public dataset for weather and light level classification focused on autonomous driving to the best of our knowledge. The baseline ResNet18 network used for weather classification achieves state-of-the-art results in two non-automotive weather classification public datasets but significantly lower accuracy on our proposed dataset, demonstrating it is not saturated and needs further research.
Neural network designers have reached progressive accuracy by increasing models depth, introducing new layer types and discovering new combinations of layers. A common element in many architectures is the distribution of the number of filters in each layer. Neural network models keep a pattern design of increasing filters in deeper layers such as those in LeNet, VGG, ResNet, MobileNet and even in automatic discovered architectures such as NASNet. It remains unknown if this pyramidal distribution of filters is the best for different tasks and constrains. In this work we present a series of modifications in the distribution of filters in four popular neural network models and their effects in accuracy and resource consumption. Results show that by applying this approach, some models improve up to 8.9% in accuracy showing reductions in parameters up to 54%.
There has been a surge in remote sensing machine learning applications that operate on data from active or passive sensors as well as multi-sensor combinations (Ma et al. (2019)). Despite this surge, however, there has been relatively little study on the comparative value of 3D surface information for machine learning classification tasks. Adding 3D surface information to RGB imagery can provide crucial geometric information for semantic classes such as buildings, and can thus improve out-of-sample predictive performance. In this paper, we examine in-sample and out-of-sample classification performance of Fully Convolutional Neural Networks (FCNNs) and Support Vector Machines (SVMs) trained with and without 3D normalized digital surface model (nDSM) information. We assess classification performance using multispectral imagery from the International Society for Photogrammetry and Remote Sensing (ISPRS) 2D Semantic Labeling contest and the United States Special Operations Command (USSOCOM) Urban 3D Challenge. We find that providing RGB classifiers with additional 3D nDSM information results in little increase in in-sample classification performance, suggesting that spectral information alone may be sufficient for the given classification tasks. However, we observe that providing these RGB classifiers with additional nDSM information leads to significant gains in out-of-sample predictive performance. Specifically, we observe an average improvement in out-of-sample all-class accuracy of 14.4% on the ISPRS dataset and an average improvement in out-of-sample F1 score of 8.6% on the USSOCOM dataset. In addition, the experiments establish that nDSM information is critical in machine learning and classification settings that face training sample scarcity.
Astronomers require efficient automated detection and classification pipelines when conducting large-scale surveys of the (optical) sky for variable and transient sources. Such pipelines are fundamentally important, as they permit rapid follow-up and analysis of those detections most likely to be of scientific value. We therefore present a deep learning pipeline based on the convolutional neural network architecture called $\texttt{MeerCRAB}$. It is designed to filter out the so called 'bogus' detections from true astrophysical sources in the transient detection pipeline of the MeerLICHT telescope. Optical candidates are described using a variety of 2D images and numerical features extracted from those images. The relationship between the input images and the target classes is unclear, since the ground truth is poorly defined and often the subject of debate. This makes it difficult to determine which source of information should be used to train a classification algorithm. We therefore used two methods for labelling our data (i) thresholding and (ii) latent class model approaches. We deployed variants of $\texttt{MeerCRAB}$ that employed different network architectures trained using different combinations of input images and training set choices, based on classification labels provided by volunteers. The deepest network worked best with an accuracy of 99.5$\%$ and Matthews correlation coefficient (MCC) value of 0.989. The best model was integrated to the MeerLICHT transient vetting pipeline, enabling the accurate and efficient classification of detected transients that allows researchers to select the most promising candidates for their research goals.
In this paper, a multi-scale visual transformer model, referred as GasHis-Transformer, is proposed for Gastric Histopathological Image Detection (GHID), which enables the automatic global detection of gastric cancer images. GasHis-Transformer model consists of two key modules designed to extract global and local information using a position-encoded transformer model and a convolutional neural network with local convolution, respectively. A publicly available hematoxylin and eosin (H&E) stained gastric histopathological image dataset is used in the experiment. Furthermore, a Dropconnect based lightweight network is proposed to reduce the model size and training time of GasHis-Transformer for clinical applications with improved confidence. Moreover, a series of contrast and extended experiments verify the robustness, extensibility and stability of GasHis-Transformer. In conclusion, GasHis-Transformer demonstrates high global detection performance and shows its significant potential in GHID task.
Recent years, analysis dictionary learning (ADL) and its applications for classification have been well developed, due to its flexible projective ability and low classification complexity. With the learned analysis dictionary, test samples can be transformed into a sparse subspace for classification efficiently. However, the underling locality of sample data has rarely been explored in analysis dictionary to enhance the discriminative capability of the classifier. In this paper, we propose a novel locality constrained analysis dictionary learning model with a synthesis K-SVD algorithm (SK-LADL). It considers the intrinsic geometric properties by imposing graph regularization to uncover the geometric structure for the image data. Through the learned analysis dictionary, we transform the image to a new and compact space where the manifold assumption can be further guaranteed. thus, the local geometrical structure of images can be preserved in sparse representation coefficients. Moreover, the SK-LADL model is iteratively solved by the synthesis K-SVD and gradient technique. Experimental results on image classification validate the performance superiority of our SK-LADL model.
The Intelligent Transportation Systems (ITS) are the subject of a world economic competition. They are the application of new information and communication technologies in the transport sector, to make the infrastructures more efficient, more reliable and more ecological. License Plates Recognition (LPR) is the key module of these systems, in which the License Plate Localization (LPL) is the most important stage, because it determines the speed and robustness of this module. Thus, during this step the algorithm must process the image and overcome several constraints as climatic and lighting conditions, sensors and angles variety, LPs no-standardization, and the real time processing. This paper presents a classification and comparison of License Plates Localization (LPL) algorithms and describes the advantages, disadvantages and improvements made by each of them
Standardized body region labelling of individual images provides data that can improve human and computer use of medical images. A CNN-based classifier was developed to identify body regions in CT and MRI. 17 CT (18 MRI) body regions covering the entire human body were defined for the classification task. Three retrospective databases were built for the AI model training, validation, and testing, with a balanced distribution of studies per body region. The test databases originated from a different healthcare network. Accuracy, recall and precision of the classifier was evaluated for patient age, patient gender, institution, scanner manufacturer, contrast, slice thickness, MRI sequence, and CT kernel. The data included a retrospective cohort of 2,934 anonymized CT cases (training: 1,804 studies, validation: 602 studies, test: 528 studies) and 3,185 anonymized MRI cases (training: 1,911 studies, validation: 636 studies, test: 638 studies). 27 institutions from primary care hospitals, community hospitals and imaging centers contributed to the test datasets. The data included cases of all genders in equal proportions and subjects aged from a few months old to +90 years old. An image-level prediction accuracy of 91.9% (90.2 - 92.1) for CT, and 94.2% (92.0 - 95.6) for MRI was achieved. The classification results were robust across all body regions and confounding factors. Due to limited data, performance results for subjects under 10 years-old could not be reliably evaluated. We show that deep learning models can classify CT and MRI images by body region including lower and upper extremities with high accuracy.
Visibility Graph (VG) transforms time series into graphs, facilitating signal processing by advanced graph data mining algorithms. In this paper, based on the classic Limited Penetrable Visibility Graph (LPVG) method, we propose a novel nonlinear mapping method named Circular Limited Penetrable Visibility Graph (CLPVG). The testing on degree distribution and clustering coefficient on the generated graphs of typical time series validates that our CLPVG is able to effectively capture the important features of time series and has better anti-noise ability than traditional LPVG. The experiments on real-world time-series datasets of radio signal and electroencephalogram (EEG) also suggest that the structural features provided by CLPVG, rather than LPVG, are more useful for time-series classification, leading to higher accuracy. And this classification performance can be further enhanced through structural feature expansion by adopting Subgraph Networks (SGN). All of these results validate the effectiveness of our CLPVG model.
Modern machine learning systems such as deep neural networks are often highly over-parameterized so that they can fit the noisy training data exactly, yet they can still achieve small test errors in practice. In this paper, we study this "benign overfitting" phenomenon of the maximum margin classifier for linear classification problems. Specifically, we consider data generated from sub-Gaussian mixtures, and provide a tight risk bound for the maximum margin linear classifier in the over-parameterized setting. Our results precisely characterize the condition under which benign overfitting can occur in linear classification problems, and improve on previous work. They also have direct implications for over-parameterized logistic regression.
Classification models are very sensitive to data uncertainty, and finding robust classifiers that are less sensitive to data uncertainty has raised great interest in the machine learning literature. This paper aims to construct robust \emph{Support Vector Machine} classifiers under feature data uncertainty via two probabilistic arguments. The first classifier, \emph{Single Perturbation}, reduces the local effect of data uncertainty with respect to one given feature and acts as a local test that could confirm or refute the presence of significant data uncertainty for that particular feature. The second classifier, \emph{Extreme Empirical Loss}, aims to reduce the aggregate effect of data uncertainty with respect to all features, which is possible via a trade-off between the number of prediction model violations and the size of these violations. Both methodologies are computationally efficient and our extensive numerical investigation highlights the advantages and possible limitations of the two robust classifiers on synthetic and real-life data.
This paper is the first to explore the question of whether images that are classified incorrectly by a face analytics algorithm (e.g., gender classification) are any more or less likely to participate in an image pair that results in a face recognition error. We analyze results from three different gender classification algorithms (one open-source and two commercial), and two face recognition algorithms (one open-source and one commercial), on image sets representing four demographic groups (African-American female and male, Caucasian female and male). For impostor image pairs, our results show that pairs in which one image has a gender classification error have a better impostor distribution than pairs in which both images have correct gender classification, and so are less likely to generate a false match error. For genuine image pairs, our results show that individuals whose images have a mix of correct and incorrect gender classification have a worse genuine distribution (increased false non-match rate) compared to individuals whose images all have correct gender classification. Thus, compared to images that generate correct gender classification, images that generate gender classification errors do generate a different pattern of recognition errors, both better (false match) and worse (false non-match).
Graph neural networks (GNN) have been ubiquitous in graph node classification tasks. Most of GNN methods update the node embedding iteratively by aggregating its neighbors' information. However, they often suffer from negative disturbance, due to edges connecting nodes with different labels. One approach to alleviate this negative disturbance is to use attention to learn the weights of aggregation, but current attention-based GNNs only consider feature similarity and also suffer from the lack of supervision. In this paper, we consider the label dependency of graph nodes and propose a decoupling attention mechanism to learn both hard and soft attention. The hard attention is learned on labels for a refined graph structure with fewer inter-class edges, so that the aggregation's negative disturbance can be reduced. The soft attention aims to learn the aggregation weights based on features over the refined graph structure to enhance information gains during message passing. Particularly, we formulate our model under the EM framework, and the learned attention is used to guide the label propagation in the M-step and the feature propagation in the E-step, respectively. Extensive experiments are performed on six well-known benchmark graph datasets to verify the effectiveness of the proposed method.
In many urban areas, traffic load and noise pollution are constantly increasing. Automated systems for traffic monitoring are promising countermeasures, which allow to systematically quantify and predict local traffic flow in order to to support municipal traffic planning decisions. In this paper, we present a novel open benchmark dataset, containing 2.5 hours of stereo audio recordings of 4718 vehicle passing events captured with both high-quality sE8 and medium-quality MEMS microphones. This dataset is well suited to evaluate the use-case of deploying audio classification algorithms to embedded sensor devices with restricted microphone quality and hardware processing power. In addition, this paper provides a detailed review of recent acoustic traffic monitoring (ATM) algorithms as well as the results of two benchmark experiments on vehicle type classification and direction of movement estimation using four state-of-the-art convolutional neural network architectures.
Graph pooling is an essential ingredient of Graph Neural Networks (GNNs) in graph classification and regression tasks. For these tasks, different pooling strategies have been proposed to generate a graph-level representation by downsampling and summarizing nodes' features in a graph. However, most existing pooling methods are unable to capture distinguishable structural information effectively. Besides, they are prone to adversarial attacks. In this work, we propose a novel pooling method named as {HIBPool} where we leverage the Information Bottleneck (IB) principle that optimally balances the expressiveness and robustness of a model to learn representations of input data. Furthermore, we introduce a novel structure-aware Discriminative Pooling Readout ({DiP-Readout}) function to capture the informative local subgraph structures in the graph. Finally, our experimental results show that our model significantly outperforms other state-of-art methods on several graph classification benchmarks and more resilient to feature-perturbation attack than existing pooling methods.
Can the analysis of the semantics of words used in the text of a scientific paper predict its future impact measured by citations? This study details examples of automated text classification that achieved 80% success rate in distinguishing between highly-cited and little-cited articles. Automated intelligent systems allow the identification of promising works that could become influential in the scientific community. The problems of quantifying the meaning of texts and representation of human language have been clear since the inception of Natural Language Processing. This paper presents a novel method for vector representation of text meaning based on information theory and show how this informational semantics is used for text classification on the basis of the Leicester Scientific Corpus. We describe the experimental framework used to evaluate the impact of scientific articles through their informational semantics. Our interest is in citation classification to discover how important semantics of texts are in predicting the citation count. We propose the semantics of texts as an important factor for citation prediction. For each article, our system extracts the abstract of paper, represents the words of the abstract as vectors in Meaning Space, automatically analyses the distribution of scientific categories (Web of Science categories) within the text of abstract, and then classifies papers according to citation counts (highly-cited, little-cited). We show that an informational approach to representing the meaning of a text has offered a way to effectively predict the scientific impact of research papers.
The recent studies of knowledge distillation have discovered that ensembling the "dark knowledge" from multiple teachers or students contributes to creating better soft targets for training, but at the cost of significantly more computations and/or parameters. In this work, we present BAtch Knowledge Ensembling (BAKE) to produce refined soft targets for anchor images by propagating and ensembling the knowledge of the other samples in the same mini-batch. Specifically, for each sample of interest, the propagation of knowledge is weighted in accordance with the inter-sample affinities, which are estimated on-the-fly with the current network. The propagated knowledge can then be ensembled to form a better soft target for distillation. In this way, our BAKE framework achieves online knowledge ensembling across multiple samples with only a single network. It requires minimal computational and memory overhead compared to existing knowledge ensembling methods. Extensive experiments demonstrate that the lightweight yet effective BAKE consistently boosts the classification performance of various architectures on multiple datasets, e.g., a significant +0.7% gain of Swin-T on ImageNet with only +1.5% computational overhead and zero additional parameters. BAKE does not only improve the vanilla baselines, but also surpasses the single-network state-of-the-arts on all the benchmarks.