HASTE enables training-free dynamic compression of pre-trained CNNs by patch-wise LSH-based merging of redundant channels, reporting 46.2% FLOPs reduction on ResNet34 CIFAR-10 with 1.25% accuracy drop.
In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Two heuristic algorithms (fixed-point from penalized KKT and staged ADAM) are proposed for symmetric multi-type orthogonal NMF tri-factorization and evaluated on synthetic noisy data and citation networks for recovery and downstream tasks.
citing papers explorer
-
HASTE: A Framework for Training-Free, Dynamic, and Steerable Compression of Pre-Trained Convolutional Neural Networks
HASTE enables training-free dynamic compression of pre-trained CNNs by patch-wise LSH-based merging of redundant channels, reporting 46.2% FLOPs reduction on ResNet34 CIFAR-10 with 1.25% accuracy drop.
-
On solving symmetric multi-type orthogonal non-negative matrix tri-factorization problem
Two heuristic algorithms (fixed-point from penalized KKT and staged ADAM) are proposed for symmetric multi-type orthogonal NMF tri-factorization and evaluated on synthetic noisy data and citation networks for recovery and downstream tasks.