# Weave Mamba Fusion: Global Cross-Scale Interaction for Lightweight Face Detection

arXiv: https://arxiv.org/abs/2610.05865 · HTML: https://mlsanity.com/paper/2610.05865/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 33 of its 37 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Point clouds, detection and remote sensing](https://mlsanity.com/ssm/point-clouds-detection-and-remote-sensing/)

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [MambaVision: A Hybrid Mamba-Transformer Vision Backbone](https://mlsanity.com/paper/2407.08083/) (2024)
- [Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks](https://mlsanity.com/paper/2303.03667/) (2023)
- [DSFD: Dual Shot Face Detector](https://mlsanity.com/paper/1810.10220/) (2018)
- [Feature Pyramid Transformer](https://mlsanity.com/paper/2007.09451/) (2020)
- [Sample and Computation Redistribution for Efficient Face Detection](https://mlsanity.com/paper/2105.04714/) (2021)
- [PyramidBox: A Context-assisted Single Shot Face Detector](https://mlsanity.com/paper/1803.07737/) (2018)
- [FaceBoxes: A CPU Real-time Face Detector with High Accuracy](https://mlsanity.com/paper/1708.05234/) (2017)
- [TinaFace: Strong but Simple Baseline for Face Detection](https://mlsanity.com/paper/2011.13183/) (2020)
- [Face Attention Network: An Effective Face Detector for the Occluded Faces](https://mlsanity.com/paper/1711.07246/) (2017)
- [Mamba YOLO: A Simple Baseline for Object Detection with State Space Model](https://mlsanity.com/paper/2406.05835/) (2024)
- [AFPN: Asymptotic Feature Pyramid Network for Object Detection](https://mlsanity.com/paper/2306.15988/) (2023)
- [MogFace: Towards a Deeper Appreciation on Face Detection](https://mlsanity.com/paper/2103.11139/) (2021)
- [EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection](https://mlsanity.com/paper/2204.01209/) (2022)
- [FDLite: A Single Stage Lightweight Face Detector Network](https://mlsanity.com/paper/2406.19107/) (2024)

## Abstract (arXiv)

Feature pyramid methods, from FPN to BiFPN, have achieved strong performance in face detection by fusing multi-scale features. However, detecting faces under unconstrained conditions, such as small scale, occlusion, and extreme pose, remains difficult, as it requires global cross-scale dependencies that local fusion cannot model. State space models such as Mamba provide global context with linear complexity by scanning features as a sequence, and therefore offer a promising direction for this problem. Nevertheless, such a scan needs the two pyramid scales combined into a single feature map, and the way they are combined determines whether cross-scale structure is preserved. Summation collapses the two scales before the scan, so the scan has no cross-scale structure to exploit, while concatenation keeps both scales but at far higher cost. To address this, we propose Weave Mamba Fusion (WMF), which interleaves two adjacent pyramid scales column by column so that each step of a horizontal bidirectional SS2D scan moves from one scale to the other. With partial-channel processing and parameter-free de-weaving, WMF enables efficient cross-scale interaction while preserving feature structure. Integrating WMF into every fusion node yields WeaveBiFPN, the neck of our WeaveFace detector. On WIDER FACE, WeaveFace achieves 91.41% mean AP with only 0.34M parameters and 1.16 GFLOPs, outperforming prior detectors under 0.5M parameters. Its largest gains are on the Hard subset, where it reaches 87.14% AP. The code is publicly available at urlhttps://github.com/dohun-mat/WeaveMambaFusion.