arXiv subjects

Alexandros Iosifidis

Publications and source records attributed to Alexandros Iosifidis.

At least 55 records · Page 3Linked to original sources

arXiv2023

On Feature Diversity in Energy-based Models

Energy-based learning is a powerful learning paradigm that encapsulates various discriminative and generative approaches. An energy-based model (EBM) is typically formed of inner-model(s) that learn a combination of the different features to generate an energy mapping for each input configuration. In this paper, we focus on the diversity of the produced feature set. We extend the probably approximately correct (PAC) theory of EBMs and analyze the effect of redundancy reduction on the performance of EBMs. We derive generalization bounds for various learning contexts, i.e., regression, classification, and implicit regression, with different energy functions and we show that indeed reducing redundancy of the feature set can consistently decrease the gap between the true and empirical expectation of the energy and boosts the performance of the model.

cs.LG↗

arXiv2023

Adaptive Parameterization of Deep Learning Models for Federated Learning

Federated Learning offers a way to train deep neural networks in a distributed fashion. While this addresses limitations related to distributed data, it incurs a communication overhead as the model parameters or gradients need to be exchanged regularly during training. This can be an issue with large scale distribution of learning tasks and negate the benefit of the respective resource distribution. In this paper, we we propose to utilise parallel Adapters for Federated Learning. Using various datasets, we show that Adapters can be incorporated to different Federated Learning techniques. We highlight that our approach can achieve similar inference performance compared to training the full model while reducing the communication overhead by roughly 90%. We further explore the applicability of Adapters in cross-silo and cross-device settings, as well as different non-IID data distributions.

cs.LG↗

arXiv2023

Audio-Visual Dataset and Method for Anomaly Detection in Traffic Videos

We introduce the first audio-visual dataset for traffic anomaly detection taken from real-world scenes, called MAVAD, with a diverse range of weather and illumination conditions. In addition, we propose a novel method named AVACA that combines visual and audio features extracted from video sequences by means of cross-attention to detect anomalies. We demonstrate that the addition of audio improves the performance of AVACA by up to 5.2%. We also evaluate the impact of image anonymization, showing only a minor decrease in performance averaging at 1.7%.

cs.CV↗

arXiv2023

Spatiotemporal Attention-based Semantic Compression for Real-time Video Recognition

This paper studies the computational offloading of video action recognition in edge computing. To achieve effective semantic information extraction and compression, following semantic communication we propose a novel spatiotemporal attention-based autoencoder (STAE) architecture, including a frame attention module and a spatial attention module, to evaluate the importance of frames and pixels in each frame. Additionally, we use entropy encoding to remove statistical redundancy in the compressed data to further reduce communication overhead. At the receiver, we develop a lightweight decoder that leverages a 3D-2D CNN combined architecture to reconstruct missing information by simultaneously learning temporal and spatial information from the received data to improve accuracy. To fasten convergence, we use a step-by-step approach to train the resulting STAE-based vision transformer (ViT_STAE) models. Experimental results show that ViT_STAE can compress the video dataset HMDB51 by 104x with only 5% accuracy loss, outperforming the state-of-the-art baseline DeepISC. The proposed ViT_STAE achieves faster inference and higher accuracy than the DeepISC-based ViT model under time-varying wireless channel, which highlights the effectiveness of STAE in guaranteeing higher accuracy under time constraints.

cs.CV↗

arXiv2023

Accurate Gigapixel Crowd Counting by Iterative Zooming and Refinement

The increasing prevalence of gigapixel resolutions has presented new challenges for crowd counting. Such resolutions are far beyond the memory and computation limits of current GPUs, and available deep neural network architectures and training procedures are not designed for such massive inputs. Although several methods have been proposed to address these challenges, they are either limited to downsampling the input image to a small size, or borrowing from other gigapixel tasks, which are not tailored for crowd counting. In this paper, we propose a novel method called GigaZoom, which iteratively zooms into the densest areas of the image and refines coarser density maps with finer details. Through experiments, we show that GigaZoom obtains the state-of-the-art for gigapixel crowd counting and improves the accuracy of the next best method by 42%.

cs.CV↗

arXiv2023

Class-Specific Variational Auto-Encoder for Content-Based Image Retrieval

Using a discriminative representation obtained by supervised deep learning methods showed promising results on diverse Content-Based Image Retrieval (CBIR) problems. However, existing methods exploiting labels during training try to discriminate all available classes, which is not ideal in cases where the retrieval problem focuses on a class of interest. In this paper, we propose a regularized loss for Variational Auto-Encoders (VAEs) forcing the model to focus on a given class of interest. As a result, the model learns to discriminate the data belonging to the class of interest from any other possibility, making the learnt latent space of the VAE suitable for class-specific retrieval tasks. The proposed Class-Specific Variational Auto-Encoder (CS-VAE) is evaluated on three public and one custom datasets, and its performance is compared with that of three related VAE-based methods. Experimental results show that the proposed method outperforms its competition in both in-domain and out-of-domain retrieval problems.

cs.CV↗

arXiv2023

Online Non-Destructive Moisture Content Estimation of Filter Media During Drying Using Artificial Neural Networks

Moisture content (MC) estimation is important in the manufacturing process of drying bulky filter media products as it is the prerequisite for drying optimization. In this study, a dataset collected by performing 161 drying industrial experiments is described and a methodology for MC estimation in an non-destructive and online manner during industrial drying is presented. An artificial neural network (ANN) based method is compared to state-of-the-art MC estimation methods reported in the literature. Results of model fitting and training show that a three-layer Perceptron achieves the lowest error. Experimental results show that ANNs combined with oven settings data, drying time and product temperature can be used to reliably estimate the MC of bulky filter media products.

cs.LG↗

arXiv2023

Continual Spatio-Temporal Graph Convolutional Networks

Graph-based reasoning over skeleton data has emerged as a promising approach for human action recognition. However, the application of prior graph-based methods, which predominantly employ whole temporal sequences as their input, to the setting of online inference entails considerable computational redundancy. In this paper, we tackle this issue by reformulating the Spatio-Temporal Graph Convolutional Neural Network as a Continual Inference Network, which can perform step-by-step predictions in time without repeat frame processing. To evaluate our method, we create a continual version of ST-GCN, CoST-GCN, alongside two derived methods with different self-attention mechanisms, CoAGCN and CoS-TR. We investigate weight transfer strategies and architectural modifications for inference acceleration, and perform experiments on the NTU RGB+D 60, NTU RGB+D 120, and Kinetics Skeleton 400 datasets. Retaining similar predictive accuracy, we observe up to 109x reduction in time complexity, on-hardware accelerations of 26x, and reductions in maximum allocated memory of 52% during online inference.

cs.CV↗

arXiv2023

Fighting Money Laundering with Statistics and Machine Learning

Money laundering is a profound global problem. Nonetheless, there is little scientific literature on statistical and machine learning methods for anti-money laundering. In this paper, we focus on anti-money laundering in banks and provide an introduction and review of the literature. We propose a unifying terminology with two central elements: (i) client risk profiling and (ii) suspicious behavior flagging. We find that client risk profiling is characterized by diagnostics, i.e., efforts to find and explain risk factors. On the other hand, suspicious behavior flagging is characterized by non-disclosed features and hand-crafted risk indices. Finally, we discuss directions for future research. One major challenge is the need for more public data sets. This may potentially be addressed by synthetic data generation. Other possible research directions include semi-supervised and deep learning, interpretability, and fairness of the results.

stat.ML↗

arXiv2023

Physics-guided machine learning for wind-farm power prediction: Toward interpretability and generalizability

With the increasing amount of available data from simulations and experiments, research for the development of data-driven models for wind-farm power prediction has increased significantly. While the data-driven models can successfully predict the power of a wind farm with similar characteristics as those in the training ensemble, they generally do not have a high degree of flexibility for extrapolation to unseen cases in contrast to the physics-based models. In this paper, we focus on data-driven models with improved interpretability and generalizability levels that can predict the performance of turbines in wind farms. To prepare the datasets, several cases are defined based on the layouts of operational wind farms, and massive computational fluid dynamics simulations are performed. The extreme gradient boosting algorithm is used afterward to build models, which have turbine-level geometric inputs in combination with the efficiency from physics-based models as the features. After training, to analyze the models' capability in generalization, their predictions for the unseen cases with different operating conditions, inflow turbulence levels, and wind-farm layouts are compared to the Park model and an empirical-analytical Gaussian wake model. Results show that the physics-guided machine-learning models outperform both physics-based models showing a high degree of generalizability, and the machine is not sensitive to the choice of the physics-based guide model.

physics.flu-dyn↗

arXiv2023

Learning Diversified Feature Representations for Facial Expression Recognition in the Wild

Diversity of the features extracted by deep neural networks is important for enhancing the model generalization ability and accordingly its performance in different learning tasks. Facial expression recognition in the wild has attracted interest in recent years due to the challenges existing in this area for extracting discriminative and informative features from occluded images in real-world scenarios. In this paper, we propose a mechanism to diversify the features extracted by CNN layers of state-of-the-art facial expression recognition architectures for enhancing the model capacity in learning discriminative features. To evaluate the effectiveness of the proposed approach, we incorporate this mechanism in two state-of-the-art models to (i) diversify local/global features in an attention-based model and (ii) diversify features extracted by different learners in an ensemble-based model. Experimental results on three well-known facial expression recognition in-the-wild datasets, AffectNet, FER+, and RAF-DB, show the effectiveness of our method, achieving the state-of-the-art performance of 89.99% on RAF-DB, 89.34% on FER+ and the competitive accuracy of 60.02% on AffectNet dataset.

cs.CV↗

arXiv2023

Variational Voxel Pseudo Image Tracking

Uncertainty estimation is an important task for critical problems, such as robotics and autonomous driving, because it allows creating statistically better perception models and signaling the model's certainty in its predictions to the decision method or a human supervisor. In this paper, we propose a Variational Neural Network-based version of a Voxel Pseudo Image Tracking (VPIT) method for 3D Single Object Tracking. The Variational Feature Generation Network of the proposed Variational VPIT computes features for target and search regions and the corresponding uncertainties, which are later combined using an uncertainty-aware cross-correlation module in one of two ways: by computing similarity between the corresponding uncertainties and adding it to the regular cross-correlation values, or by penalizing the uncertain feature channels to increase influence of the certain features. In experiments, we show that both methods improve tracking performance, while penalization of uncertain features provides the best uncertainty quality.

cs.CV↗

arXiv2023

Attention-based Feature Compression for CNN Inference Offloading in Edge Computing

This paper studies the computational offloading of CNN inference in device-edge co-inference systems. Inspired by the emerging paradigm semantic communication, we propose a novel autoencoder-based CNN architecture (AECNN), for effective feature extraction at end-device. We design a feature compression module based on the channel attention method in CNN, to compress the intermediate data by selecting the most important features. To further reduce communication overhead, we can use entropy encoding to remove the statistical redundancy in the compressed data. At the receiver, we design a lightweight decoder to reconstruct the intermediate data through learning from the received compressed data to improve accuracy. To fasten the convergence, we use a step-by-step approach to train the neural networks obtained based on ResNet-50 architecture. Experimental results show that AECNN can compress the intermediate data by more than 256x with only about 4% accuracy loss, which outperforms the state-of-the-art work, BottleNet++. Compared to offloading inference task directly to edge server, AECNN can complete inference task earlier, in particular, under poor wireless channel condition, which highlights the effectiveness of AECNN in guaranteeing higher accuracy within time constraint.

cs.CV↗

arXiv2023

Structured Pruning Adapters

Adapters are a parameter-efficient alternative to fine-tuning, which augment a frozen base network to learn new tasks. Yet, the inference of the adapted model is often slower than the corresponding fine-tuned model. To improve on this, we propose Structured Pruning Adapters (SPAs), a family of compressing, task-switching network adapters, that accelerate and specialize networks using tiny parameter sets and structured pruning. Specifically, we propose a channel-based SPA and evaluate it with a suite of pruning methods on multiple computer vision benchmarks. Compared to regular structured pruning with fine-tuning, our channel-SPAs improve accuracy by 6.9% on average while using half the parameters at 90% pruned weights. Alternatively, they can learn adaptations with 17x fewer parameters at 70% pruning with 1.6% lower accuracy. Similarly, our block-SPA requires far fewer parameters than pruning with fine-tuning. Our experimental code and Python library of adapters are available at github.com/lukashedegaard/structured-pruning-adapters.

cs.CV↗

arXiv2023

Bayesian Bilinear Neural Network for Predicting the Mid-price Dynamics in Limit-Order Book Markets

The prediction of financial markets is a challenging yet important task. In modern electronically-driven markets, traditional time-series econometric methods often appear incapable of capturing the true complexity of the multi-level interactions driving the price dynamics. While recent research has established the effectiveness of traditional machine learning (ML) models in financial applications, their intrinsic inability to deal with uncertainties, which is a great concern in econometrics research and real business applications, constitutes a major drawback. Bayesian methods naturally appear as a suitable remedy conveying the predictive ability of ML methods with the probabilistically-oriented practice of econometric research. By adopting a state-of-the-art second-order optimization algorithm, we train a Bayesian bilinear neural network with temporal attention, suitable for the challenging time-series task of predicting mid-price movements in ultra-high-frequency limit-order book markets. We thoroughly compare our Bayesian model with traditional ML alternatives by addressing the use of predictive distributions to analyze errors and uncertainties associated with the estimated parameters and model forecasts. Our results underline the feasibility of the Bayesian deep-learning approach and its predictive and decisional advantages in complex econometric tasks, prompting future research in this direction.

econ.EM↗

arXiv2023

Bayesian Learning for Neural Networks: an algorithmic survey

The last decade witnessed a growing interest in Bayesian learning. Yet, the technicality of the topic and the multitude of ingredients involved therein, besides the complexity of turning theory into practical implementations, limit the use of the Bayesian learning paradigm, preventing its widespread adoption across different fields and applications. This self-contained survey engages and introduces readers to the principles and algorithms of Bayesian Learning for Neural Networks. It provides an introduction to the topic from an accessible, practical-algorithmic perspective. Upon providing a general introduction to Bayesian Neural Networks, we discuss and present both standard and recent approaches for Bayesian inference, with an emphasis on solutions relying on Variational Inference and the use of Natural gradients. We also discuss the use of manifold optimization as a state-of-the-art approach to Bayesian learning. We examine the characteristic properties of all the discussed methods, and provide pseudo-codes for their implementation, paying attention to practical aspects, such as the computation of the gradients.

stat.ML↗

arXiv2023

PromptMix: Text-to-image diffusion models enhance the performance of lightweight networks

Many deep learning tasks require annotations that are too time consuming for human operators, resulting in small dataset sizes. This is especially true for dense regression problems such as crowd counting which requires the location of every person in the image to be annotated. Techniques such as data augmentation and synthetic data generation based on simulations can help in such cases. In this paper, we introduce PromptMix, a method for artificially boosting the size of existing datasets, that can be used to improve the performance of lightweight networks. First, synthetic images are generated in an end-to-end data-driven manner, where text prompts are extracted from existing datasets via an image captioning deep network, and subsequently introduced to text-to-image diffusion models. The generated images are then annotated using one or more high-performing deep networks, and mixed with the real dataset for training the lightweight network. By extensive experiments on five datasets and two tasks, we show that PromptMix can significantly increase the performance of lightweight networks by up to 26%.

cs.CV↗

arXiv2023

Variational Neural Networks

Bayesian Neural Networks (BNNs) provide a tool to estimate the uncertainty of a neural network by considering a distribution over weights and sampling different models for each input. In this paper, we propose a method for uncertainty estimation in neural networks which, instead of considering a distribution over weights, samples outputs of each layer from a corresponding Gaussian distribution, parametrized by the predictions of mean and variance sub-layers. In uncertainty quality estimation experiments, we show that the proposed method achieves better uncertainty quality than other single-bin Bayesian Model Averaging methods, such as Monte Carlo Dropout or Bayes By Backpropagation methods.

cs.LG↗