Paper Detail

CLANE: Continual Learning of Actions on Neuromorphic Hardware from Event Cameras

Elvin Hajizada, Michael Neumeier, Edward Paxon Frady, Yulia Sandamirskaya, Axel von Arnim, Bing Li, Eyke Hüllermeier

arxiv Score 16.0

Published 2026-05-27 · First seen 2026-05-31

Research Track A · General AI

Abstract

Recognizing and continuously learning novel human actions without forgetting prior classes is a requirement for emerging AR/VR and robotics applications. For these applications, both on-device processing and learning are essential for privacy and low-latency adaptation. Event cameras address the efficiency of visual sensing with sparse, asynchronous output that is naturally compatible with neuromorphic processing. Yet no prior system has deployed a continual on-device learning pipeline for event-based action recognition using neuromorphic hardware. We present CLANE, Continual Learning of Actions on Neuromorphic Hardware from Event Cameras, deployed end-to-end on Intel Loihi 2. CLANE combines a spiking 2D CNN for spatiotemporal feature extraction with CLP-SNN as its on-chip learning head, extended to action clips via a Temporal Aggregation Layer and a fixed-point Normalization Layer, both novel Loihi 2 modules. On THU E-ACT-50, a 50-class dataset captured under real-world conditions, CLANE achieves 70.4% accuracy in a continual learning task while delivering more than 100x energy reduction and 16x lower latency over a sequential CNN+GRU+CLP edge GPU baseline, validated through iso-algorithm cross-platform benchmarking across three evaluation levels.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{hajizada2026clane,
  title = {CLANE: Continual Learning of Actions on Neuromorphic Hardware from Event Cameras},
  author = {Elvin Hajizada and Michael Neumeier and Edward Paxon Frady and Yulia Sandamirskaya and Axel von Arnim and Bing Li and Eyke Hüllermeier},
  year = {2026},
  abstract = {Recognizing and continuously learning novel human actions without forgetting prior classes is a requirement for emerging AR/VR and robotics applications. For these applications, both on-device processing and learning are essential for privacy and low-latency adaptation. Event cameras address the efficiency of visual sensing with sparse, asynchronous output that is naturally compatible with neuromorphic processing. Yet no prior system has deployed a continual on-device learning pipeline for event},
  url = {https://arxiv.org/abs/2605.28387},
  keywords = {cs.LG, cs.AI, cs.NE},
  eprint = {2605.28387},
  archiveprefix = {arXiv},
}

Metadata

{}