Related papers: TrustMAE: A Noise-Resilient Defect Classification …

Automated image captioning has the potential to be a useful tool for people with vision impairments. Images taken by this user group are often noisy, which leads to incorrect and even unsafe model predictions. In this paper, we propose a…

Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using…

In industrial imaging, accurately detecting and distinguishing surface defects from noise is critical and challenging, particularly in complex environments with noisy data. This paper presents a hybrid framework that integrates both…

As attention to recorded data grows in the realm of automotive testing and manual evaluation reaches its limits, there is a growing need for automatic online anomaly detection. This real-world data is complex in many ways and requires the…

Accurate fault detection in high-dimensional industrial environments remains a major challenge due to the inherent complexity, noise, and redundancy in sensor data. This paper introduces CLAIRE, i.e., a hybrid end-to-end learning framework…

Masked AutoEncoders (MAE) have emerged as a robust self-supervised framework, offering remarkable performance across a wide range of downstream tasks. To increase the difficulty of the pretext task and learn richer visual representations,…

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead…

Building a scalable machine learning system for unsupervised anomaly detection via representation learning is highly desirable. One of the prevalent methods is using a reconstruction error from variational autoencoder (VAE) via maximizing…

Existing deepfake detection methods have reported promising in-distribution results, by accessing published large-scale dataset. However, due to the non-smooth synthesis method, the fake samples in this dataset may expose obvious artifacts…

This letter introduces a new denoiser that modifies the structure of denoising autoencoder (DAE), namely noise learning based DAE (nlDAE). The proposed nlDAE learns the noise of the input data. Then, the denoising is performed by…

Due to limited computational and memory resources, current deep learning models accept only rather small images in input, calling for preliminary image resizing. This is not a problem for high-level vision problems, where discriminative…

Supervised deep learning performance is heavily tied to the availability of high-quality labels for training. Neural networks can gradually overfit corrupted labels if directly trained on noisy datasets, leading to severe performance…

Wind turbine reliability is critical to the growing renewable energy sector, where early fault detection significantly reduces downtime and maintenance costs. This paper introduces a novel ensemble-based deep learning framework for…

Anomaly detection plays a pivotal role in automated industrial inspection, aiming to identify subtle or rare defects in otherwise uniform visual patterns. As collecting representative examples of all possible anomalies is infeasible, we…

Endoscopy is a routine imaging technique used for both diagnosis and minimally invasive surgical treatment. Artifacts such as motion blur, bubbles, specular reflections, floating objects and pixel saturation impede the visual interpretation…

Current state-of-the-art deep learning systems for visual object recognition and detection use purely supervised training with regularization such as dropout to avoid overfitting. The performance depends critically on the amount of labeled…

In complex physical systems, conventional differential equations often fall short in capturing non-local and memory effects, as they are limited to local dynamics and integer-order interactions. This study introduces a stepwise data-driven…

Despite that deep learning has achieved state-of-the-art performance for medical image segmentation, its success relies on a large set of manually annotated images for training that are expensive to acquire. In this paper, we propose an…

Directed Energy Deposition (DED) offers significant potential for manufacturing complex and multi-material parts. However, internal defects such as porosity and cracks can compromise mechanical properties and overall performance. This study…

Anomaly detection (AD) plays a pivotal role in AI applications, e.g., in classification, and intrusion/threat detection in cybersecurity. However, most existing methods face challenges of heterogeneity amongst feature subsets posed by…