Search Results for author:
Found 3 papers, 1 papers with code
Overcoming Forgetting Catastrophe in Quantization-Aware Training
Afterward, we exploit replay data (a subset of old task data) for retraining in new tasks to alleviate the forgetting problem.
AlignQ: Alignment Quantization With ADMM-Based Correlation Preservation
Afterward, our theoretical analysis indicates that the significant changes in data correlations after the quantization induce a large quantization error.
Color-complexity enabled exhaustive color-dots identification and spatial patterns testing in images
Targeted color-dots with varying shapes and sizes in images are first exhaustively identified, and then their multiscale 2D geometric patterns are extracted for testing spatial uniformness in a progressive fashion.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
