Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks
Researchers have developed Adaptive Signal Resuscitation (ASR), a novel training-free method to repair sparse vision networks after pruning. ASR addresses the accuracy collapse seen in high-sparsity models by applying corrections at a channel-wise granularity, unlike previous layer-wise approaches. This technique estimates and stabilizes variance-matching corrections for each output channel, significantly improving performance in high-sparsity scenarios. For instance, ASR recovered 55.6% top-1 accuracy on ResNet-50 at 90% sparsity on CIFAR-10, a substantial improvement over existing methods. AI
IMPACT Improves accuracy of pruned vision models, potentially enabling more efficient deployment on resource-constrained devices.