全局注意力与权重共享在紧凑视觉骨干网络中的适用位置研究
Where Global Context and Weight Sharing Work in Compact Vision Backbones
AI 导读
一项 arXiv 论文在 ImageNet-1k 上用受控 EfficientNet-B0 实验探究混合架构中全局自注意力与重复块权重共享的作用。
正文 · 原文
Abstract:Compact convolutional backbones such as EfficientNet achieve strong parameter efficiency through local depthwise separable convolutions, yet two structural questions remain central to hybrid design: where does global self-attention improve recognition over pure convolution, and can repeated blocks share weights without losing representational capacity? We investigate both questions on ImageNet-1k (50,000-image validation) using controlled EfficientNet-B0 experiments. First, we show that wrapping a classification backbone in multi-scale feature pyramids (BiFPN) fails to outperform a plain MBConv trunk (69.99% - 71.81% vs. 72.86% plain B0) until paired with stage attention (73.15%). In contrast, keeping the MBConv trunk intact and inserting lightweight zero-gated residual self-attention adapters at stages P3 (28x28 windowed), P4 (14x14 global), and P5 (7x7 global) reaches 74.02% standalone and outperforms a bit-for-bit matched plain-B0 control by +0.954 percentage points (73.88% vs. 72.92%) across an 88-epoch stateless replay schedule, with learned attention amplitude rising monotonically with semantic depth (27.2% at P3 -> 45.4% at P4 -> 66.3% at P5). Second, we evaluate recurrent weight sharing across repeated MBConv blocks with pass-specific BatchNorm statistics (+1,536 parameters per pass). While post-hoc kernel averaging degrades accuracy to 17.03% and single-template stage tying (-27.6% parameters) plateaus at 66.10%, alternating two shared block templates ([B1, A, B, A]) in Stage 6 cuts total model parameters by 10.9% (582K weights) and recovers by +10.82 points in a single epoch to 70.92% (-1.84 points vs. unshared control).
| Comments: | 8 pages, 5 figures |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.23446 [cs.CV] |
| (or arXiv:2611.23446v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23446 arXiv-issued DOI via DataCite |
Submission history
From: Michael Schroeder [view email]
[v1]
Tue, 17 Nov 2026 19:49:55 UTC (101 KB)
[v2]
Thu, 19 Nov 2026 14:28:24 UTC (102 KB)
来源:arXiv cs.AI · arxiv.org