ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification

arXiv:2211.13189v2 Announce Type: replace-cross
Abstract: Transformers, which were originally developed for natural language processing, have recently generated significant interest in the computer vision and audio communities due to their flexibility in learning long-range relationships. Constrained by the data hungry nature of transformers and the limited amount of labelled data, most transformer-based models for audio tasks are finetuned from ImageNet pretrained models, despite the huge gap between the domain of natural images and audio. This has motivated the research in self-supervised …

abstract arxiv audio classification communities computer computer vision cs.cv cs.sd data eess.as event flexibility generated global language language processing natural natural language natural language processing nature processing relationships spectrogram transformer transformers type vision