A modular, component-wise feature inversion technique applied to DETR and ViT shows that DETR progressively abstracts images into prototypical objects while ViT retains detailed local information.
On Interpretability of Artificial Neural Networks: A Survey
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Deep learning as represented by the artificial deep neural networks (DNNs) has achieved great success in many important areas that deal with text, images, videos, graphs, and so on. However, the black-box nature of DNNs has become one of the primary obstacles for their wide acceptance in mission-critical applications such as medical diagnosis and therapy. Due to the huge potential of deep learning, interpreting neural networks has recently attracted much research attention. In this paper, based on our comprehensive taxonomy, we systematically review recent studies in understanding the mechanism of neural networks, describe applications of interpretability especially in medicine, and discuss future directions of interpretability research, such as in relation to fuzzy logic and brain science.
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Understanding Transformer-based Vision Models through Inversion
A modular, component-wise feature inversion technique applied to DETR and ViT shows that DETR progressively abstracts images into prototypical objects while ViT retains detailed local information.