# Dynamic loss balancing and sequential enhancement for road-safety assessment and traffic scene classification

arXiv: https://arxiv.org/abs/2211.04165 · HTML: https://mlsanity.com/paper/2211.04165/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 76 references that are in the map.
- First posted on arXiv 8 Nov 2022.

## Builds on (most cited first, 21 of 21)

- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [Beyond Short Snippets: Deep Networks for Video Classification](https://mlsanity.com/paper/1503.08909/) (2015)
- [Rethinking the Faster R-CNN Architecture for Temporal Action Localization](https://mlsanity.com/paper/1804.07667/) (2018)
- [R-C3D: Region Convolutional 3D Network for Temporal Activity Detection](https://mlsanity.com/paper/1703.07814/) (2017)
- [In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images](https://mlsanity.com/paper/1903.08469/) (2019)
- [In-Place Activated BatchNorm for Memory-Optimized Training of DNNs](https://mlsanity.com/paper/1712.02616/) (2017)
- [Macro F1 and Macro F1](https://mlsanity.com/paper/1911.03347/) (2019)
- [Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networks](https://mlsanity.com/paper/1903.02193/) (2019)
- [Deep Learning for Large-Scale Traffic-Sign Detection and Recognition](https://mlsanity.com/paper/1904.00649/) (2019)
- [Striking the Right Balance: Recall Loss for Semantic Segmentation](https://mlsanity.com/paper/2106.14917/) (2021)
- [Efficient Ladder-style DenseNets for Semantic Segmentation of Large Images](https://mlsanity.com/paper/1905.05661/) (2019)
- [Dense outlier detection and open-set recognition based on training with noisy negative images](https://mlsanity.com/paper/2101.09193/) (2021)
- [Dynamic Traffic Scene Classification with Space-Time Coherence](https://mlsanity.com/paper/1905.12708/) (2019)
- [Context-Aware Multi-Task Learning for Traffic Scene Recognition in Autonomous Vehicles](https://mlsanity.com/paper/2004.01351/) (2020)

## Built on by (most cited first, 2 of 2)

- [V-RoAst: Visual Road Assessment. Can VLM be a Road Safety Assessor Using the iRAP Standard?](https://mlsanity.com/paper/2408.10872/) (2024)
- [EG-ARSA: An Expert-Grounded Open Model for Visual Road Safety Auditing in Low-Resource Settings](https://mlsanity.com/paper/2608.23563/) (2026)

## Abstract (arXiv)

Road-safety inspection is an indispensable instrument for reducing road-accident fatalities contributed to road infrastructure. Recent work formalizes road-safety assessment in terms of carefully selected risk factors that are also known as road-safety attributes. In current practice, these attributes are manually annotated in geo-referenced monocular video for each road segment. We propose to reduce dependency on tedious human labor by automating recognition with a two-stage neural architecture. The first stage predicts more than forty road-safety attributes by observing a local spatio-temporal context. Our design leverages an efficient convolutional pipeline, which benefits from pre-training on semantic segmentation of street scenes. The second stage enhances predictions through sequential integration across a larger temporal window. Our design leverages per-attribute instances of a lightweight bidirectional LSTM architecture. Both stages alleviate extreme class imbalance by incorporating a multi-task variant of recall-based dynamic loss weighting. We perform experiments on the iRAP-BH dataset, which involves fully labeled geo-referenced video along 2,300 km of public roads in Bosnia and Herzegovina. We also validate our approach by comparing it with the related work on two road-scene classification datasets from the literature: Honda Scenes and FM3m. Experimental evaluation confirms the value of our contributions on all three datasets.