Are Straight-Through gradients and Soft-Thresholding all you need for Sparse Training?
Antoine VanderschuerenChristophe De VleeschouwerPublished in: WACV (2023)
Keyphrases
- soft thresholding
- wavelet domain
- denoising
- noise reduction
- image denoising
- total variation
- training process
- training samples
- test set
- image restoration
- avoid overfitting
- straight line
- training examples
- data sets
- online learning
- high quality
- neural network
- sparse representation
- wavelet transform
- training set
- multiscale
- e learning
- machine learning