PulseAugur
LIVE 02:07:25
research · [2 sources] ·

New method repairs sparse vision networks after pruning

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

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Improves accuracy of pruned vision models, potentially enabling more efficient deployment on resource-constrained devices.

RANK_REASON The cluster contains an academic paper detailing a new method for repairing sparse vision networks.

Read on arXiv cs.LG →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 · Minxuan Hu ·

    Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks

    One-shot magnitude pruning can cause severe accuracy collapse in the high-sparsity regime, even when the pruning mask preserves the largest weights. We argue that this failure reflects a granularity mismatch in post-pruning repair. Under global magnitude pruning, nearly collapsed…

  2. Hugging Face Daily Papers TIER_1 ·

    Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks

    One-shot magnitude pruning can cause severe accuracy collapse in the high-sparsity regime, even when the pruning mask preserves the largest weights. We argue that this failure reflects a granularity mismatch in post-pruning repair. Under global magnitude pruning, nearly collapsed…