Feature-level reverse propagation can reconstruct intermediate features from labels via linear least squares and yield post-training accuracy comparable to backpropagation fine-tuning.
Vatld: A visual analytics system to assess, understand and im- prove traffic light detection.IEEE Transactions on Visu- alization and Computer Graphics, 27(2):261–271, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Hierarchical Feature-level Reverse Propagation for Post-Training Neural Networks
Feature-level reverse propagation can reconstruct intermediate features from labels via linear least squares and yield post-training accuracy comparable to backpropagation fine-tuning.