# BlitzNet: A Real-Time Deep Network for Scene Understanding

arXiv: https://arxiv.org/abs/1708.02813 · HTML: https://mlsanity.com/paper/1708.02813/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2017.

## Built on by (most cited first, 29 of 29)

- [InverseForm: A Loss Function for Structured Boundary-Aware Segmentation](https://mlsanity.com/paper/2104.02745/) (2021)
- [HybridNets: End-to-End Perception Network](https://mlsanity.com/paper/2203.09035/) (2022)
- [Scalable Video Object Segmentation with Simplified Framework](https://mlsanity.com/paper/2308.09903/) (2023)
- [ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery](https://mlsanity.com/paper/2112.08189/) (2021)
- [AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning](https://mlsanity.com/paper/2110.13076/) (2021)
- [Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches](https://mlsanity.com/paper/2206.08016/) (2022)
- [DiSparse: Disentangled Sparsification for Multitask Model Compression](https://mlsanity.com/paper/2206.04662/) (2022)
- [FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions](https://mlsanity.com/paper/2210.01595/) (2022)
- [Multi-Task Consistency for Active Learning](https://mlsanity.com/paper/2306.12398/) (2023)
- [Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition](https://mlsanity.com/paper/2103.00259/) (2021)
- [Deep Joint Source-Channel Coding for Multi-Task Network](https://mlsanity.com/paper/2109.05779/) (2021)
- [Instance-Level Task Parameters: A Robust Multi-task Weighting Framework](https://mlsanity.com/paper/2106.06129/) (2021)
- [Multitask Network for Joint Object Detection, Semantic Segmentation and Human Pose Estimation in Vehicle Occupancy Monitoring](https://mlsanity.com/paper/2205.01515/) (2022)
- [GraMMaR: Ground-aware Motion Model for 3D Human Motion Reconstruction](https://mlsanity.com/paper/2306.16736/) (2023)
- [Monocular visual simultaneous localization and mapping: (r)evolution from geometry to deep learning-based pipelines](https://mlsanity.com/paper/2503.02955/) (2025)
- [Disentangling Transfer and Interference in Multi-Domain Learning](https://mlsanity.com/paper/2107.05445/) (2021)
- [Panoptic SwiftNet: Pyramidal Fusion for Real-time Panoptic Segmentation](https://mlsanity.com/paper/2203.07908/) (2022)
- [Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel Pairs](https://mlsanity.com/paper/2101.12431/) (2021)
- [A Review of Mobile Mapping Systems: From Sensors to Applications](https://mlsanity.com/paper/2205.15865/) (2022)
- [FasterVideo: Efficient Online Joint Object Detection And Tracking](https://mlsanity.com/paper/2204.07394/) (2022)
- [Autonomous Robotic Drilling System for Mice Cranial Window Creation: An Evaluation with an Egg Model](https://mlsanity.com/paper/2303.12265/) (2023)
- [Attacking All Tasks at Once Using Adversarial Examples in Multi-Task Learning](https://mlsanity.com/paper/2305.12066/) (2023)
- [Robust Analysis of Multi-Task Learning Efficiency: New Benchmarks on Light-Weighed Backbones and Effective Measurement of Multi-Task Learning Challenges by Feature Disentanglement](https://mlsanity.com/paper/2402.03557/) (2024)
- [SemAug: Semantically Meaningful Image Augmentations for Object Detection Through Language Grounding](https://mlsanity.com/paper/2208.07407/) (2022)
- [An advanced YOLOv3 method for small object detection](https://mlsanity.com/paper/2212.02809/) (2022)
- [Label Budget Allocation in Multi-Task Learning](https://mlsanity.com/paper/2308.12949/) (2023)
- [YOLO-Former: YOLO Shakes Hand With ViT](https://mlsanity.com/paper/2401.06244/) (2024)
- [Autonomous Robotic Drilling System for Mice Cranial Window Creation](https://mlsanity.com/paper/2406.14135/) (2024)
- [DMTG: One-Shot Differentiable Multi-Task Grouping](https://mlsanity.com/paper/2407.05082/) (2024)

## Abstract (arXiv)

Real-time scene understanding has become crucial in many applications such as autonomous driving. In this paper, we propose a deep architecture, called BlitzNet, that jointly performs object detection and semantic segmentation in one forward pass, allowing real-time computations. Besides the computational gain of having a single network to perform several tasks, we show that object detection and semantic segmentation benefit from each other in terms of accuracy. Experimental results for VOC and COCO datasets show state-of-the-art performance for object detection and segmentation among real time systems.