Revisiting a kNN-based Image Classification System with High-capacity Storage. (arXiv:2204.01186v2 [cs.CV] UPDATED)

In existing image classification systems that use deep neural networks, the
knowledge needed for image classification is implicitly stored in model
parameters. If users want to update this knowledge, then they need to fine-tune
the model parameters. Moreover, users cannot verify the validity of inference
results or evaluate the contribution of knowledge to the results. In this
paper, we investigate a system that stores knowledge for image classification,
such as image feature maps, labels, and original images, not in model …

arxiv capacity classification cv image knn storage