通过类别可分性聚类实现互补性剪枝，提升模型压缩效率与精度。
CoSeP: Complementary Separability Pruning via Class-Separability Clustering
- 基于类别可分性距离构建特征空间，聚类筛选互补组件。
- 自动确定每层剪枝比例，避免手动调参，最高提速20%。
- 适用于ResNet/VGG等主流架构，剪枝后精度不降反升。
神经网络剪枝旨在压缩模型以实现高效部署，但面临两大挑战：其一，多数方法依赖组件重要性评分，独立选择滤波器或神经元，忽略冗余性——保留的组件可能重复捕获相似判别模式，而遗漏其他关键信息；其二，各层剪枝比例通常需人工调参，缺乏理论停顿标准。本文提出CoSeP（互补可分性剪枝），不再孤立评估组件，而是通过杰弗里斯-马图西塔距离计算每个组件在所有类别对上的类别可分性轮廓，构建可分性空间。在该空间中，相近组件可能存在冗余，相远组件则蕴含互补信息。CoSeP采用k-medoids聚类，以简化轮廓均值评估候选子集质量，并通过拐点检测自动确定应保留的组件数量。在CIFAR-10、CIFAR-100和ImageNet-1K上，针对ResNet、VGG、MobileNet和DenseNet架构，CoSeP在保持或提升准确率的同时降低计算量，推理时间最高减少20%。例如，在ResNet-50/ImageNet-1K上实现+0.66%准确率提升与2.30倍FLOPs压缩；在VGG-16/CIFAR-10上实现+0.37%提升与2.59倍压缩。结果表明，建模可分性空间中的互补性为剪枝提供了有效且原理清晰的新路径。
原文摘要 · Abstract (English)
Neural network pruning aims to compress models for efficient deployment, yet two fundamental challenges remain. First, many methods rely on per-component importance scores, selecting filters or neurons independently and ignoring redundancy: the retained set may include multiple components capturing similar discriminative patterns while missing others entirely. Second, determining per-layer pruning ratios typically requires manual, architecture-specific tuning with no principled stopping criterion. We propose CoSeP (Complementary Separability Pruning) to address both issues. Rather than scoring components in isolation, CoSeP represents each component by its class-separability profile across all class pairs, computed via Jeffries--Matusita distances. This defines a separability space in which nearby components are potentially redundant and distant components capture complementary information. CoSeP selects a compact set of representatives in this space: components are grouped via k-medoids clustering, candidate subset sizes are evaluated using the Mean Simplified Silhouette, and a knee-detection criterion automatically determines how many components to retain. Across CIFAR-10, CIFAR-100, and ImageNet-1K, on ResNet, VGG, MobileNet, and DenseNet architectures, CoSeP matches or improves accuracy while reducing FLOPs, with measured wall-clock inference-time reductions of up to 20%. For example, it achieves a +0.66% top-1 accuracy gain with 2.30x FLOPs reduction on ResNet-50/ImageNet-1K, and a 0.37% gain with 2.59x FLOPs reduction on VGG-16/CIFAR-10. These results demonstrate that modeling complementarity in class-separability space provides an effective and principled approach to pruning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。