The paper tackles the challenge of generalization in neural networks to new domains not seen during training. The authors introduce a simple framework for generalizing semantic segmentation networks by using…
Continue readingThis research paper addresses the challenge of recognizing faces masked due to the post-pandemic scenario. The researchers created a new dataset by selecting images from the Labelled Faces in the…
Continue readingThe paper discusses the creation of an acoustic-based COVID-19 diagnosis system named ‘Cough to COVID-19’ (C2C). The system was submitted to the BHI 2023 Data Competition and won first place….
Continue readingThis paper presents EMIT-Diff, a new method for synthesizing medical image data to enhance medical image segmentation tasks. Leveraging diffusion probabilistic models, the proposed method generates realistic and diverse synthetic…
Continue readingThe article discusses the challenge of detecting replay attacks, which are simple but effective voice spoofing attacks. A method is proposed that uses audio compression to assist feature extraction, which…
Continue readingThe paper addresses the challenge of achieving robustness to spatial transformations in computer vision. Traditional methods involve data augmentation or hard-coding invariances, but these can have limitations. The authors propose…
Continue readingThe paper discusses the use of deepfake audio as a data augmentation technique to train robust speech-to-text transcription models. The authors argue that finding a diverse and large labeled dataset…
Continue readingThis paper presents AMPLIFY, a new Mixup method for data augmentation that minimizes the impact of noise and aberrant features in original samples on prediction results. Unlike common Mixup methods,…
Continue readingThe article discusses a study aimed at improving the generalization of imitation learning agents in game AI through the use of data augmentation. The authors note that while imitation learning…
Continue readingThe paper presents MosaicFusion, a data augmentation approach that uses diffusion models for large vocabulary instance segmentation. This method is training-free and does not rely on label supervision. It uses…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
