# Toward On-Chip Training of Spiking Neural Networks for Dense Event-Based Vision

arXiv: https://arxiv.org/abs/2609.32405 · HTML: https://mlsanity.com/paper/2609.32405/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [DSEC: A Stereo Event Camera Dataset for Driving Scenarios](https://mlsanity.com/paper/2103.06011/) (2021)
- [E-RAFT: Dense Optical Flow from Event Cameras](https://mlsanity.com/paper/2108.10552/) (2021)
- [Training Neural Networks with Local Error Signals](https://mlsanity.com/paper/1901.06656/) (2019)
- [Greedy Layerwise Learning Can Scale to ImageNet](https://mlsanity.com/paper/1812.11446/) (2018)
- [ESS: Learning Event-based Semantic Segmentation from Still Images](https://mlsanity.com/paper/2203.10016/) (2022)
- [Optical flow estimation from event-based cameras and spiking neural networks](https://mlsanity.com/paper/2302.06492/) (2023)
- [Adaptive-SpikeNet: Event-based Optical Flow Estimation using Spiking Neural Networks with Learnable Neuronal Dynamics](https://mlsanity.com/paper/2209.11741/) (2022)
- [EventFly: Event Camera Perception from Ground to the Sky](https://mlsanity.com/paper/2503.19916/) (2025)
- [Accurate and Efficient Event-based Semantic Segmentation Using Adaptive Spiking Encoder-Decoder Network](https://mlsanity.com/paper/2304.11857/) (2023)
- [EvSegSNN: Neuromorphic Semantic Segmentation for Event Data](https://mlsanity.com/paper/2406.14178/) (2024)
- [Efficient Training of Spiking Neural Networks with Temporally-Truncated Local Backpropagation through Time](https://mlsanity.com/paper/2201.07210/) (2021)

## Abstract (arXiv)

Event cameras provide low-latency, asynchronous visual sensing for resource-constrained robotics. Spiking neural networks (SNNs) process event streams naturally, but training deep SNNs with backpropagation through time (BPTT) requires substantial memory and remains difficult on neuromorphic hardware. Local learning avoids this by restricting error propagation to local blocks, but existing methods mainly target classification rather than dense prediction. We introduce DELL (Dense Event-driven Local Learning), a block wise scheme for dense event-based vision that replaces global gradient propagation with local dense supervision. Learnable, spatially structured local heads supervise each block at its appropriate resolution while preserving temporal dynamics within blocks. We evaluate DELL on optical-flow regression and semantic segmentation with a fully spiking U-shaped architecture. On DSEC optical flow, DELL reduces peak training memory by 39.6% relative to end-to-end BPTT while improving accuracy, reaching 1.670 px endpoint error on the official test benchmark versus 1.941 px for the same backbone trained end-to-end. Block detachment behaves more like a regularizer than a constraint. DECOLLE, the existing local-learning baseline, relies on fixed random local read-outs poorly suited to dense regression, resulting in a 3.9x higher endpoint error; learnable local heads recover this loss and outperform end-to-end training across all optical-flow metrics. On segmentation, they recover most of the performance gap, although DELL remains a few mIoU points behind end-to-end training. With 2.3M parameters, 24x fewer than the strongest SNN baseline, the backbone remains competitive with the SNN state of the art on DSEC. These results extend local learning to dense event-based prediction while substantially reducing training memory.