# Tiny Collaborative Inference for Occlusion-Robust Object Detection

arXiv: https://arxiv.org/abs/2606.02894 · HTML: https://mlsanity.com/paper/2606.02894/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Builds on (most cited first, 18 of 18)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [Decentralized Federated Learning: A Survey and Perspective](https://mlsanity.com/paper/2306.01603/) (2023)
- [Robust Object Detection under Occlusion with Context-Aware CompositionalNets](https://mlsanity.com/paper/2005.11643/) (2020)
- [Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion](https://mlsanity.com/paper/2003.04490/) (2020)
- [Lightweight Deep Learning for Resource-Constrained Environments: A Survey](https://mlsanity.com/paper/2404.07236/) (2024)
- [A Survey of Methods for Low-Power Deep Learning and Computer Vision](https://mlsanity.com/paper/2003.11066/) (2020)
- [Occlusion Handling in Generic Object Detection: A Review](https://mlsanity.com/paper/2101.08845/) (2021)
- [Federated Learning for Computer Vision](https://mlsanity.com/paper/2308.13558/) (2023)
- [Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models](https://mlsanity.com/paper/1905.04598/) (2019)
- [Cross-domain Federated Object Detection](https://mlsanity.com/paper/2206.14996/) (2022)
- [A Multicore and Edge TPU-Accelerated Multimodal TinyML System for Livestock Behavior Recognition](https://mlsanity.com/paper/2504.11467/) (2025)
- [Deep Models for Multi-View 3D Object Recognition: A Review](https://mlsanity.com/paper/2404.15224/) (2024)
- [Edge-device Collaborative Computing for Multi-view Classification](https://mlsanity.com/paper/2409.15973/) (2024)

## Abstract (arXiv)

Edge AI nodes for search and rescue are increasingly expected to run computer vision locally, yet ultra-low-end hardware imposes hard constraints on memory, compute, and inter-device communication. This work addresses occlusion-robust object detection on devices with less than 1 MB SRAM by combining an MCUNet backbone, a YOLOv2 detection head, and Lite quantisation. Two collaborative inference strategies are evaluated: feature-level fusion, concatenating intermediate feature maps, and decision-level fusion via Weighted Boxes Fusion (WBF). WBF outperforms feature-level fusion under all tested occlusion conditions, yielding gains of up to +0.2736 mAP in asymmetric scenarios. Extending fusion to three views improves accuracy further (up to +0.3827 mAP) at modest communication overhead (~1.3 KB per exchange). Hardware experiments progress from a host-assisted USB-relay baseline to a Wi-Fi peer-to-peer deployment on two Coral Dev Board Micro units, where WBF executes on-device with negligible communication energy relative to inference. In a 301.9 s autonomous session of 108 frames, fused output is produced on 61 frames versus 47 for a single board - a coverage gain of +29.8%. A decentralised federated learning feasibility note is included but not treated as a primary result, as performance remains limited under non-iid data. The results support decision-level fusion as a viable option for improving occlusion robustness in small-scale edge object detection, including host-free multi-board operation on ultra-low-end hardware.