Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones
Vision backbone networks play a central role in modern computer vision. Enhancing their efficiency directly benefits a wide range of downstream applications. To measure efficiency, many publications rely on MACs (Multiply Accumulate operations) as a predictor of execution time. In this paper, we experimentally demonstrate the shortcomings of such a metric, especially in the context of edge devices. By contrasting the MAC count and execution time of common architectural design elements, we identify key factors for efficient execution and provide insights to optimize backbone design. Based on these insights, we present LowFormer, a novel vision backbone family. LowFormer features a streamli...
| Authors | Moritz Nottebaum, Matteo Dunnhofer, Christian Micheloni |
|---|---|
| Primary category | cs.CV |
| Published | 27 March 2026 |
| Last updated at source | 16 June 2026 |
Connected in the knowledge graph
- timm/lowformer_e1.in1kModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.