FusionSense: Tri-Stage Near-Sensor Learning for Runtime-Adaptive Multimodal Edge Intelligence
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910247353843712 |
|---|---|
| author | Yun, Sanggeon Masukawa, Ryozo Na, Minhyoung Oh, Hyunwoo Yamaguchi, Yoshiki Huang, Wenjun Jeong, SungHeon Imani, Mohsen |
| author_facet | Yun, Sanggeon Masukawa, Ryozo Na, Minhyoung Oh, Hyunwoo Yamaguchi, Yoshiki Huang, Wenjun Jeong, SungHeon Imani, Mohsen |
| contents | Autonomous systems and smart-industry deployments increasingly split computation across near-sensor, edge, and cloud resources, where tight energy, latency, and reliability budgets demand run-time adaptivity. In practice, deciding what to compute and transmit at each point is pivotal; yet as multimodal sensor suites (cameras, LiDAR/depth, etc.) proliferate at the edge, most prior approaches either (i) fuse modalities on powerful servers or (ii) apply uni-modal near-sensor filters that ignore cross-modal dependencies, leading to redundant transmissions or missed events. We present FusionSense, a fusion-aware intelligent sensing framework for energy-constrained autonomous edge systems. Lightweight near-sensor classifiers are trained via a three-step procedure: (i) a server-side fusion model learns the downstream task, (ii) filter-out-safe (FoS) labels quantify each modality's necessity relative to the fused decision, and (iii) an edge-side fusion model is compacted by injecting near-sensor predictions as auxiliary signals. The result is a run-time decision layer that jointly reduces compute and communication while scaling linearly with sensor count. On a dual-modality (RGB+Depth/LiDAR) setup with SynDrone, FusionSense sustains task quality at substantially higher data-reduction rates than uni-modal filters and delivers large end-to-end gains: up to 33x lower energy at 1% FoI prevalence, 11x at 10%, a 92.3% reduction in quality loss at a fixed 30% data reduction, and roughly 1.5x higher energy savings than the best prior filtering baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_22868 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FusionSense: Tri-Stage Near-Sensor Learning for Runtime-Adaptive Multimodal Edge Intelligence Yun, Sanggeon Masukawa, Ryozo Na, Minhyoung Oh, Hyunwoo Yamaguchi, Yoshiki Huang, Wenjun Jeong, SungHeon Imani, Mohsen Machine Learning Autonomous systems and smart-industry deployments increasingly split computation across near-sensor, edge, and cloud resources, where tight energy, latency, and reliability budgets demand run-time adaptivity. In practice, deciding what to compute and transmit at each point is pivotal; yet as multimodal sensor suites (cameras, LiDAR/depth, etc.) proliferate at the edge, most prior approaches either (i) fuse modalities on powerful servers or (ii) apply uni-modal near-sensor filters that ignore cross-modal dependencies, leading to redundant transmissions or missed events. We present FusionSense, a fusion-aware intelligent sensing framework for energy-constrained autonomous edge systems. Lightweight near-sensor classifiers are trained via a three-step procedure: (i) a server-side fusion model learns the downstream task, (ii) filter-out-safe (FoS) labels quantify each modality's necessity relative to the fused decision, and (iii) an edge-side fusion model is compacted by injecting near-sensor predictions as auxiliary signals. The result is a run-time decision layer that jointly reduces compute and communication while scaling linearly with sensor count. On a dual-modality (RGB+Depth/LiDAR) setup with SynDrone, FusionSense sustains task quality at substantially higher data-reduction rates than uni-modal filters and delivers large end-to-end gains: up to 33x lower energy at 1% FoI prevalence, 11x at 10%, a 92.3% reduction in quality loss at a fixed 30% data reduction, and roughly 1.5x higher energy savings than the best prior filtering baseline. |
| title | FusionSense: Tri-Stage Near-Sensor Learning for Runtime-Adaptive Multimodal Edge Intelligence |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.22868 |