# DMFormer: Closing the Gap Between CNN and Vision Transformers Source: [DMFormer: Closing the Gap Between CNN and Vision Transformers]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:48:10.793Z Authors: Zimian Wei, Hengyue Pan, Lujun Li, Menglong Lu, Xin Niu, Peijie Dong, Dongsheng Li Published: 2022-09-16T06:45:01.000Z ## Abstract Vision transformers have shown excellent performance in computer vision tasks. As the computation cost of their self-attention mechanism is expensive, recent works tried to replace the self-attention mechanism in vision transformers with convolutional operations, which is more efficient with built-in inductive bias. However, these efforts either ignore multi-level features or lack dynamic prosperity, leading to sub-optimal performance. In this paper, we propose a Dynamic Multi-level Attention mechanism (DMA), which captures different patterns of input images by multiple kernel sizes and enables input-adaptive weights with a gating mechanism. Based on DMA, we present an efficient backbone network named DMFormer. DMFormer adopts the overall architecture of vision transformers, while replacing the self-attention mechanism with our proposed DMA. Extensive experimental results on ImageNet-1K and ADE20K datasets demonstrated that DMFormer achieves state-of-the-art performance, which outperforms similar-sized vision transformers(ViTs) and convolutional neural networks (CNNs). ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()