The paper discusses adversarial training’s robustness-accuracy trade-off problem and proposes a solution. The authors focus on invariance regularization to create adversarially invariant representations without losing discriminative power. They identify two…
Continue readingThe article presents a novel approach to Low-Light Image Enhancement (LLIE) using a new trainable color space, HVI, and a decoupling network, CIDNet. Existing methods using sRGB and HSV color…
Continue readingThe article presents an efficient network for Low-Light Image Enhancement (LLIE) named Horizontal/Vertical-Intensity (HVI) and Color and Intensity Decoupling Network (CIDNet). Traditional methods use Deep Neural Networks (DNNs) in sRGB…
Continue readingThis paper presents a new privacy-preserving synthetic continual semantic segmentation framework for robotic surgery. The researchers address the problem of ‘catastrophic forgetting’ in Deep Neural Networks (DNNs), which refers to…
Continue readingThe study explores backdoor attacks on deep neural networks-based image classification. The attacker aims to insert a backdoor into the model by manipulating training data. Current data poisoning-based attacks struggle…
Continue readingThe study focuses on the development of an attack-resilient Generative Adversarial Network (AR-GAN) for traffic sign classification in autonomous vehicles (AVs). AVs rely on Deep Neural Network (DNN)-based systems to…
Continue readingThe paper ‘Bayesian Semi-structured Subspace Inference’ presents a new method to address the problem of epistemic uncertainty in semi-structured regression models. The researchers propose a Bayesian approximation using subspace inference…
Continue readingThe paper investigates the utility of conformal prediction sets in AI-advised decision-making. Through an experiment, it compares conformal prediction sets to displays of Top-1 and Top-k predictions for AI-advised image…
Continue readingThe paper presents a model for predicting corn yield using deep neural networks (DNNR). The model considers the interaction between weather and soil variables, challenging the assumption that there is…
Continue readingThis research paper discusses a type of output error called hallucinations, produced by deep neural networks in Automatic Speech Recognition (ASR). Hallucinations in ASR are transcriptions generated by a model…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
