研究人员开发了HASTE，一个新颖的框架，旨在压缩大型预训练卷积神经网络（CNN）而无需额外的训练或数据访问。这个即插即用的模块在推理过程中利用局部敏感哈希动态合并冗余通道，从而降低计算成本。在CIFAR-10和ImageNet等数据集上的实验表明，FLOPs显著减少，例如ResNet34的FLOPs减少了46.2%，而准确率仅有微小下降。 AI
影响 使得在资源受限的设备上无需重新训练即可更有效地部署大型CNN。
排序理由 该集群描述了一篇关于CNN压缩新颖框架的最新研究论文。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2509.25136v3 Announce Type: replace Abstract: Activation-aware low-rank factorization techniques yield strong compression results but are generally confined to linear layers, while existing whitening-based theory typically makes an implicit full-rank assumption on activatio…
arXiv:2508.13836v2 Announce Type: replace-cross Abstract: Pruning is a core technique for compressing neural networks to improve computational efficiency. This process is typically approached in two ways: one-shot pruning, which involves a single pass of training and pruning, and…
arXiv:2606.30516v1 Announce Type: new Abstract: Deploying large convolutional neural networks (CNNs) on resource-constrained devices is challenging due to their high computational cost. While dynamic execution methods are promising, existing approaches for CNNs typically require …
Deploying large convolutional neural networks (CNNs) on resource-constrained devices is challenging due to their high computational cost. While dynamic execution methods are promising, existing approaches for CNNs typically require specialized training or fine-tuning, limiting th…