# HALSIE: Hybrid Approach to Learning Segmentation by Simultaneously Exploiting Image and Event Modalities

arXiv: https://arxiv.org/abs/2211.10754 · HTML: https://mlsanity.com/paper/2211.10754/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 79 references that are in the map.
- First posted on arXiv 19 Nov 2022.

## Builds on (most cited first, 30 of 43)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation](https://mlsanity.com/paper/1909.11065/) (2019)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [High Speed and High Dynamic Range Video with an Event Camera](https://mlsanity.com/paper/1906.07165/) (2019)
- [Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion](https://mlsanity.com/paper/1812.08156/) (2018)
- [DSEC: A Stereo Event Camera Dataset for Driving Scenarios](https://mlsanity.com/paper/2103.06011/) (2021)
- [The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception](https://mlsanity.com/paper/1801.10202/) (2018)
- [Training Deep Spiking Neural Networks using Backpropagation](https://mlsanity.com/paper/1608.08782/) (2016)
- [Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars](https://mlsanity.com/paper/1804.01310/) (2018)
- [Hierarchical Multi-Scale Attention for Semantic Segmentation](https://mlsanity.com/paper/2005.10821/) (2020)
- [Video to Events: Recycling Video Datasets for Event Cameras](https://mlsanity.com/paper/1912.03095/) (2019)
- [What Makes Multi-modal Learning Better than Single (Provably)](https://mlsanity.com/paper/2106.04538/) (2021)
- [RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network](https://mlsanity.com/paper/2003.01811/) (2020)
- [Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences](https://mlsanity.com/paper/1610.09513/) (2016)
- [Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks](https://mlsanity.com/paper/2003.06696/) (2020)
- [Event-based High Dynamic Range Image and Very High Frame Rate Video Generation using Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1811.08230/) (2018)
- [EV-SegNet: Semantic Segmentation for Event-based Cameras](https://mlsanity.com/paper/1811.12039/) (2018)

## Built on by (most cited first, 25 of 25)

- [Recent Event Camera Innovations: A Survey](https://mlsanity.com/paper/2408.13627/) (2024)
- [OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2405.05259/) (2024)
- [Direct Learning-Based Deep Spiking Neural Networks: A Review](https://mlsanity.com/paper/2305.19725/) (2023)
- [Event-guided Low-light Video Semantic Segmentation](https://mlsanity.com/paper/2411.00639/) (2024)
- [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)
- [HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation](https://mlsanity.com/paper/2403.16788/) (2024)
- [Finding Meaning in Points: Weakly Supervised Semantic Segmentation for Event Cameras](https://mlsanity.com/paper/2407.11216/) (2024)
- [Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach](https://mlsanity.com/paper/2507.03765/) (2025)
- [Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras](https://mlsanity.com/paper/2507.17664/) (2025)
- [CEIA: CLIP-Based Event-Image Alignment for Open-World Event-Based Understanding](https://mlsanity.com/paper/2407.06611/) (2024)
- [MambaSeg: Harnessing Mamba for Accurate and Efficient Image-Event Semantic Segmentation](https://mlsanity.com/paper/2512.24243/) (2025)
- [Ev-Edge: Efficient Execution of Event-based Vision Algorithms on Commodity Edge Platforms](https://mlsanity.com/paper/2403.15717/) (2024)
- [Segment Any Events with Language](https://mlsanity.com/paper/2601.23159/) (2026)
- [Scaling Dense Event-Stream Pretraining from Visual Foundation Models](https://mlsanity.com/paper/2603.03969/) (2026)
- [Low-Latency Scalable Streaming for Event-Based Vision](https://mlsanity.com/paper/2412.07889/) (2024)
- [Enhanced Neuromorphic Semantic Segmentation Latency through Stream Event](https://mlsanity.com/paper/2502.18982/) (2025)
- [Learning Flow-Guided Registration for RGB-Event Semantic Segmentation](https://mlsanity.com/paper/2505.01548/) (2025)
- [Re-coding for Uncertainties: Edge-awareness Semantic Concordance for Resilient Event-RGB Segmentation](https://mlsanity.com/paper/2511.08269/) (2025)
- [EIFNet: Leveraging Event-Image Fusion for Robust Semantic Segmentation](https://mlsanity.com/paper/2507.21971/) (2025)
- [Reliable Brain Tumor Segmentation Based on Spiking Neural Networks with Efficient Training](https://mlsanity.com/paper/2601.16652/) (2026)
- [REALM: An RGB- and Event-Aligned Latent Manifold for Cross-Modal Perception](https://mlsanity.com/paper/2605.00271/) (2026)
- [Weaving Light and Time: Unified Harmonic-Geometric Representation Learning for Dense RGB-Event Parsing](https://mlsanity.com/paper/2607.09143/) (2026)
- [Event-Frame Fusion for Inter-Frame Segmentation via Event-Guided Motion](https://mlsanity.com/paper/2609.22500/) (2026)
- [Multimodal Fusion of RGB and Complementary Modalities for Semantic Segmentation](https://mlsanity.com/paper/2610.17800/) (2026)

## Abstract (arXiv)

Event cameras detect changes in per-pixel intensity to generate asynchronous `event streams'. They offer great potential for accurate semantic map retrieval in real-time autonomous systems owing to their much higher temporal resolution and high dynamic range (HDR) compared to conventional cameras. However, existing implementations for event-based segmentation suffer from sub-optimal performance since these temporally dense events only measure the varying component of a visual signal, limiting their ability to encode dense spatial context compared to frames. To address this issue, we propose a hybrid end-to-end learning framework HALSIE, utilizing three key concepts to reduce inference cost by up to 20× versus prior art while retaining similar performance: First, a simple and efficient cross-domain learning scheme to extract complementary spatio-temporal embeddings from both frames and events. Second, a specially designed dual-encoder scheme with Spiking Neural Network (SNN) and Artificial Neural Network (ANN) branches to minimize latency while retaining cross-domain feature aggregation. Third, a multi-scale cue mixer to model rich representations of the fused embeddings. These qualities of HALSIE allow for a very lightweight architecture achieving state-of-the-art segmentation performance on DDD-17, MVSEC, and DSEC-Semantic datasets with up to 33× higher parameter efficiency and favorable inference cost (17.9mJ per cycle). Our ablation study also brings new insights into effective design choices that can prove beneficial for research across other vision tasks.