arXiv subjects

Alexandros Iosifidis

Publications and source records attributed to Alexandros Iosifidis.

At least 109 records · Page 6Linked to original sources

arXiv2021

On Quantitative Evaluations of Counterfactuals

As counterfactual examples become increasingly popular for explaining decisions of deep learning models, it is essential to understand what properties quantitative evaluation metrics do capture and equally important what they do not capture. Currently, such understanding is lacking, potentially slowing down scientific progress. In this paper, we consolidate the work on evaluating visual counterfactual examples through an analysis and experiments. We find that while most metrics behave as intended for sufficiently simple datasets, some fail to tell the difference between good and bad counterfactuals when the complexity increases. We observe experimentally that metrics give good scores to tiny adversarial-like changes, wrongly identifying such changes as superior counterfactual examples. To mitigate this issue, we propose two new metrics, the Label Variation Score and the Oracle score, which are both less vulnerable to such tiny changes. We conclude that a proper quantitative evaluation of visual counterfactual examples should combine metrics to ensure that all aspects of good counterfactuals are quantified.

cs.LG↗

arXiv2021

Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocol

Domain Adaptation is the process of alleviating distribution gaps between data from different domains. In this paper, we show that Domain Adaptation methods using pair-wise relationships between source and target domain data can be formulated as a Graph Embedding in which the domain labels are incorporated into the structure of the intrinsic and penalty graphs. Specifically, we analyse the loss functions of three existing state-of-the-art Supervised Domain Adaptation methods and demonstrate that they perform Graph Embedding. Moreover, we highlight some generalisation and reproducibility issues related to the experimental setup commonly used to demonstrate the few-shot learning capabilities of these methods. To assess and compare Supervised Domain Adaptation methods accurately, we propose a rectified evaluation protocol, and report updated benchmarks on the standard datasets Office31 (Amazon, DSLR, and Webcam), Digits (MNIST, USPS, SVHN, and MNIST-M) and VisDA (Synthetic, Real).

cs.LG↗

arXiv2021

Multi-Exit Vision Transformer for Dynamic Inference

Deep neural networks can be converted to multi-exit architectures by inserting early exit branches after some of their intermediate layers. This allows their inference process to become dynamic, which is useful for time critical IoT applications with stringent latency requirements, but with time-variant communication and computation resources. In particular, in edge computing systems and IoT networks where the exact computation time budget is variable and not known beforehand. Vision Transformer is a recently proposed architecture which has since found many applications across various domains of computer vision. In this work, we propose seven different architectures for early exit branches that can be used for dynamic inference in Vision Transformer backbones. Through extensive experiments involving both classification and regression problems, we show that each one of our proposed architectures could prove useful in the trade-off between accuracy and speed.

cs.CV↗

arXiv2021

DeepTimeAnomalyViz: A Tool for Visualizing and Post-processing Deep Learning Anomaly Detection Results for Industrial Time-Series

Industrial processes are monitored by a large number of various sensors that produce time-series data. Deep Learning offers a possibility to create anomaly detection methods that can aid in preventing malfunctions and increasing efficiency. But creating such a solution can be a complicated task, with factors such as inference speed, amount of available data, number of sensors, and many more, influencing the feasibility of such implementation. We introduce the DeTAVIZ interface, which is a web browser based visualization tool for quick exploration and assessment of feasibility of DL based anomaly detection in a given problem. Provided with a pool of pretrained models and simulation results, DeTAVIZ allows the user to easily and quickly iterate through multiple post processing options and compare different models, and allows for manual optimisation towards a chosen metric.

cs.LG↗

arXiv2021

Remote Multilinear Compressive Learning with Adaptive Compression

Multilinear Compressive Learning (MCL) is an efficient signal acquisition and learning paradigm for multidimensional signals. The level of signal compression affects the detection or classification performance of a MCL model, with higher compression rates often associated with lower inference accuracy. However, higher compression rates are more amenable to a wider range of applications, especially those that require low operating bandwidth and minimal energy consumption such as Internet-of-Things (IoT) applications. Many communication protocols provide support for adaptive data transmission to maximize the throughput and minimize energy consumption. By developing compressive sensing and learning models that can operate with an adaptive compression rate, we can maximize the informational content throughput of the whole application. In this paper, we propose a novel optimization scheme that enables such a feature for MCL models. Our proposal enables practical implementation of adaptive compressive signal acquisition and inference systems. Experimental results demonstrated that the proposed approach can significantly reduce the amount of computations required during the training phase of remote learning systems but also improve the informational content throughput via adaptive-rate sensing.

cs.CV↗

arXiv2021

Bilinear Input Normalization for Neural Networks in Financial Forecasting

Data normalization is one of the most important preprocessing steps when building a machine learning model, especially when the model of interest is a deep neural network. This is because deep neural network optimized with stochastic gradient descent is sensitive to the input variable range and prone to numerical issues. Different than other types of signals, financial time-series often exhibit unique characteristics such as high volatility, non-stationarity and multi-modality that make them challenging to work with, often requiring expert domain knowledge for devising a suitable processing pipeline. In this paper, we propose a novel data-driven normalization method for deep neural networks that handle high-frequency financial time-series. The proposed normalization scheme, which takes into account the bimodal characteristic of financial multivariate time-series, requires no expert knowledge to preprocess a financial time-series since this step is formulated as part of the end-to-end optimization process. Our experiments, conducted with state-of-the-arts neural networks and high-frequency data from two large-scale limit order books coming from the Nordic and US markets, show significant improvements over other normalization techniques in forecasting future stock price dynamics.

q-fin.ST↗

arXiv2021

Detecting Faults during Automatic Screwdriving: A Dataset and Use Case of Anomaly Detection for Automatic Screwdriving

Detecting faults in manufacturing applications can be difficult, especially if each fault model is to be engineered by hand. Data-driven approaches, using Machine Learning (ML) for detecting faults have recently gained increasing interest, where a ML model can be trained on a set of data from a manufacturing process. In this paper, we present a use case of using ML models for detecting faults during automated screwdriving operations, and introduce a new dataset containing fully monitored and registered data from a Universal Robot and OnRobot screwdriver during both normal and anomalous operations. We illustrate, with the use of two time-series ML models, how to detect faults in an automated screwdriving application.

cs.LG↗

arXiv2021

Low-Rank Temporal Attention-Augmented Bilinear Network for financial time-series forecasting

Financial market analysis, especially the prediction of movements of stock prices, is a challenging problem. The nature of financial time-series data, being non-stationary and nonlinear, is the main cause of these challenges. Deep learning models have led to significant performance improvements in many problems coming from different domains, including prediction problems of financial time-series data. Although the prediction performance is the main goal of such models, dealing with ultra high-frequency data sets restrictions in terms of the number of model parameters and its inference speed. The Temporal Attention-Augmented Bilinear network was recently proposed as an efficient and high-performing model for Limit Order Book time-series forecasting. In this paper, we propose a low-rank tensor approximation of the model to further reduce the number of trainable parameters and increase its speed.

cs.LG↗

arXiv2021

Automatic Social Distance Estimation From Images: Performance Evaluation, Test Benchmark, and Algorithm

The COVID-19 virus has caused a global pandemic since March 2020. The World Health Organization (WHO) has provided guidelines on how to reduce the spread of the virus and one of the most important measures is social distancing. Maintaining a minimum of one meter distance from other people is strongly suggested to reduce the risk of infection. This has created a strong interest in monitoring the social distances either as a safety measure or to study how the measures have affected human behavior and country-wise differences in this. The need for automatic social distance estimation algorithms is evident, but there is no suitable test benchmark for such algorithms. Collecting images with measured ground-truth pair-wise distances between all the people using different camera settings is cumbersome. Furthermore, performance evaluation for social distance estimation algorithms is not straightforward and there is no widely accepted evaluation protocol. In this paper, we provide a dataset of varying images with measured pair-wise social distances under different camera positionings and focal length values. We suggest a performance evaluation protocol and provide a benchmark to easily evaluate social distance estimation algorithms. We also propose a method for automatic social distance estimation. Our method takes advantage of object detection and human pose estimation. It can be applied on any single image as long as focal length and sensor size information are known. The results on our benchmark are encouraging with 92% human detection rate and only 28.9% average error in distance estimation among the detected people.

cs.CV↗

arXiv2021

Visualising Deep Network's Time-Series Representations

Despite the popularisation of machine learning models, more often than not, they still operate as black boxes with no insight into what is happening inside the model. There exist a few methods that allow to visualise and explain why a model has made a certain prediction. Those methods, however, allow visualisation of the link between the input and output of the model without presenting how the model learns to represent the data used to train the model as whole. In this paper, a method that addresses that issue is proposed, with a focus on visualising multi-dimensional time-series data. Experiments on a high-frequency stock market dataset show that the method provides fast and discernible visualisations. Large datasets can be visualised quickly and on one plot, which makes it easy for a user to compare the learned representations of the data. The developed method successfully combines known techniques to provide an insight into the inner workings of time-series classification models.

cs.LG↗

arXiv2021

Automatic Main Character Recognition for Photographic Studies

Main characters in images are the most important humans that catch the viewer's attention upon first look, and they are emphasized by properties such as size, position, color saturation, and sharpness of focus. Identifying the main character in images plays an important role in traditional photographic studies and media analysis, but the task is performed manually and can be slow and laborious. Furthermore, selection of main characters can be sometimes subjective. In this paper, we analyze the feasibility of solving the main character recognition needed for photographic studies automatically and propose a method for identifying the main characters. The proposed method uses machine learning based human pose estimation along with traditional computer vision approaches for this task. We approach the task as a binary classification problem where each detected human is classified either as a main character or not. To evaluate both the subjectivity of the task and the performance of our method, we collected a dataset of 300 varying images from multiple sources and asked five people, a photographic researcher and four other persons, to annotate the main characters. Our analysis showed a relatively high agreement between different annotators. The proposed method achieved a promising F1 score of 0.83 on the full image set and 0.96 on a subset evaluated as most clear and important cases by the photographic researcher.

cs.CV↗

arXiv2021

Progressive Spatio-Temporal Bilinear Network with Monte Carlo Dropout for Landmark-based Facial Expression Recognition with Uncertainty Estimation

Deep neural networks have been widely used for feature learning in facial expression recognition systems. However, small datasets and large intra-class variability can lead to overfitting. In this paper, we propose a method which learns an optimized compact network topology for real-time facial expression recognition utilizing localized facial landmark features. Our method employs a spatio-temporal bilinear layer as backbone to capture the motion of facial landmarks during the execution of a facial expression effectively. Besides, it takes advantage of Monte Carlo Dropout to capture the model's uncertainty which is of great importance to analyze and treat uncertain cases. The performance of our method is evaluated on three widely used datasets and it is comparable to that of video-based state-of-the-art methods while it has much less complexity.

cs.CV↗

arXiv2021

Analysis of voxel-based 3D object detection methods efficiency for real-time embedded systems

Real-time detection of objects in the 3D scene is one of the tasks an autonomous agent needs to perform for understanding its surroundings. While recent Deep Learning-based solutions achieve satisfactory performance, their high computational cost renders their application in real-life settings in which computations need to be performed on embedded platforms intractable. In this paper, we analyze the efficiency of two popular voxel-based 3D object detection methods providing a good compromise between high performance and speed based on two aspects, their ability to detect objects located at large distances from the agent and their ability to operate in real time on embedded platforms equipped with high-performance GPUs. Our experiments show that these methods mostly fail to detect distant small objects due to the sparsity of the input point clouds at large distances. Moreover, models trained on near objects achieve similar or better performance compared to those trained on all objects in the scene. This means that the models learn object appearance representations mostly from near objects. Our findings suggest that a considerable part of the computations of existing methods is focused on locations of the scene that do not contribute with successful detection. This means that the methods can achieve a speed-up of $40$-$60\%$ by restricting operation to near objects while not sacrificing much in performance.

cs.CV↗

arXiv2021

Progressive Spatio-Temporal Graph Convolutional Network for Skeleton-Based Human Action Recognition

Graph convolutional networks (GCNs) have been very successful in skeleton-based human action recognition where the sequence of skeletons is modeled as a graph. However, most of the GCN-based methods in this area train a deep feed-forward network with a fixed topology that leads to high computational complexity and restricts their application in low computation scenarios. In this paper, we propose a method to automatically find a compact and problem-specific topology for spatio-temporal graph convolutional networks in a progressive manner. Experimental results on two widely used datasets for skeleton-based human action recognition indicate that the proposed method has competitive or even better classification performance compared to the state-of-the-art methods with much lower computational complexity.

cs.CV↗

arXiv2021

Temporal Attention-Augmented Graph Convolutional Network for Efficient Skeleton-Based Human Action Recognition

Graph convolutional networks (GCNs) have been very successful in modeling non-Euclidean data structures, like sequences of body skeletons forming actions modeled as spatio-temporal graphs. Most GCN-based action recognition methods use deep feed-forward networks with high computational complexity to process all skeletons in an action. This leads to a high number of floating point operations (ranging from 16G to 100G FLOPs) to process a single sample, making their adoption in restricted computation application scenarios infeasible. In this paper, we propose a temporal attention module (TAM) for increasing the efficiency in skeleton-based action recognition by selecting the most informative skeletons of an action at the early layers of the network. We incorporate the TAM in a light-weight GCN topology to further reduce the overall number of computations. Experimental results on two benchmark datasets show that the proposed method outperforms with a large margin the baseline GCN-based method while having 2.9 times less number of computations. Moreover, it performs on par with the state-of-the-art with up to 9.6 times less number of computations.

cs.CV↗

arXiv2021

On the spatial attention in Spatio-Temporal Graph Convolutional Networks for skeleton-based human action recognition

Graph convolutional networks (GCNs) achieved promising performance in skeleton-based human action recognition by modeling a sequence of skeletons as a spatio-temporal graph. Most of the recently proposed GCN-based methods improve the performance by learning the graph structure at each layer of the network using a spatial attention applied on a predefined graph Adjacency matrix that is optimized jointly with model's parameters in an end-to-end manner. In this paper, we analyze the spatial attention used in spatio-temporal GCN layers and propose a symmetric spatial attention for better reflecting the symmetric property of the relative positions of the human body joints when executing actions. We also highlight the connection of spatio-temporal GCN layers employing additive spatial attention to bilinear layers, and we propose the spatio-temporal bilinear network (ST-BLN) which does not require the use of predefined Adjacency matrices and allows for more flexible design of the model. Experimental results show that the three models lead to effectively the same performance. Moreover, by exploiting the flexibility provided by the proposed ST-BLN, one can increase the efficiency of the model.

cs.CV↗

arXiv2021

Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning

Deploying deep learning services for time-sensitive and resource-constrained settings such as IoT using edge computing systems is a challenging task that requires dynamic adjustment of inference time. Multi-exit architectures allow deep neural networks to terminate their execution early in order to adhere to tight deadlines at the cost of accuracy. To mitigate this cost, in this paper we introduce a novel method called Multi-Exit Curriculum Learning that utilizes curriculum learning, a training strategy for neural networks that imitates human learning by sorting the training samples based on their difficulty and gradually introducing them to the network. Experiments on CIFAR-10 and CIFAR-100 datasets and various configurations of multi-exit architectures show that our method consistently improves the accuracy of early exits compared to the standard training approach.

cs.LG↗

arXiv2021

ECINN: Efficient Counterfactuals from Invertible Neural Networks

Counterfactual examples identify how inputs can be altered to change the predicted class of a classifier, thus opening up the black-box nature of, e.g., deep neural networks. We propose a method, ECINN, that utilizes the generative capacities of invertible neural networks for image classification to generate counterfactual examples efficiently. In contrast to competing methods that sometimes need a thousand evaluations or more of the classifier, ECINN has a closed-form expression and generates a counterfactual in the time of only two evaluations. Arguably, the main challenge of generating counterfactual examples is to alter only input features that affect the predicted outcome, i.e., class-dependent features. Our experiments demonstrate how ECINN alters class-dependent image regions to change the perceptual and predicted class of the counterfactuals. Additionally, we extend ECINN to also produce heatmaps (ECINNh) for easy inspection of, e.g., pairwise class-dependent changes in the generated counterfactual examples. Experimentally, we find that ECINNh outperforms established methods that generate heatmap-based explanations.

cs.LG↗