Robust and Explainable Fine-Grained Visual Classification with Transfer Learning: A Dual-Carriageway Framework

arXiv:2405.05853v1 Announce Type: new
Abstract: In the realm of practical fine-grained visual classification applications rooted in deep learning, a common scenario involves training a model using a pre-existing dataset. Subsequently, a new dataset becomes available, prompting the desire to make a pivotal decision for achieving enhanced and leveraged inference performance on both sides: Should one opt to train datasets from scratch or fine-tune the model trained on the initial dataset using the newly released dataset? The existing literature reveals a …

abstract applications arxiv classification cs.cv dataset decision deep learning fine-grained framework pivotal practical prompting realm robust training transfer transfer learning type visual