# Efficient Ladder-style DenseNets for Semantic Segmentation of Large Images

arXiv: https://arxiv.org/abs/1905.05661 · HTML: https://mlsanity.com/paper/1905.05661/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2019.

## Built on by (most cited first, 17 of 17)

- [Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation](https://mlsanity.com/paper/2211.14512/) (2022)
- [DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition](https://mlsanity.com/paper/2207.02606/) (2022)
- [Maskomaly:Zero-Shot Mask Anomaly Segmentation](https://mlsanity.com/paper/2305.16972/) (2023)
- [Dense outlier detection and open-set recognition based on training with noisy negative images](https://mlsanity.com/paper/2101.09193/) (2021)
- [Multi-domain semantic segmentation with overlapping labels](https://mlsanity.com/paper/2108.11224/) (2021)
- [Computation-efficient Deep Learning for Computer Vision: A Survey](https://mlsanity.com/paper/2308.13998/) (2023)
- [Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data](https://mlsanity.com/paper/2112.12833/) (2021)
- [Hybrid Open-set Segmentation with Synthetic Negative Data](https://mlsanity.com/paper/2301.08555/) (2023)
- [Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey](https://mlsanity.com/paper/2309.15467/) (2023)
- [On Efficient Real-Time Semantic Segmentation: A Survey](https://mlsanity.com/paper/2206.08605/) (2022)
- [Class Based Thresholding in Early Exit Semantic Segmentation Networks](https://mlsanity.com/paper/2210.15621/) (2022)
- [Weakly supervised training of universal visual concepts for multi-domain semantic segmentation](https://mlsanity.com/paper/2212.10340/) (2022)
- [Revisiting consistency for semi-supervised semantic segmentation](https://mlsanity.com/paper/2106.07075/) (2021)
- [Dense Semantic Forecasting in Video by Joint Regression of Features and Feature Motion](https://mlsanity.com/paper/2101.10777/) (2021)
- [Panoptic SwiftNet: Pyramidal Fusion for Real-time Panoptic Segmentation](https://mlsanity.com/paper/2203.07908/) (2022)
- [Dynamic loss balancing and sequential enhancement for road-safety assessment and traffic scene classification](https://mlsanity.com/paper/2211.04165/) (2022)
- [AVOID: The Adverse Visual Conditions Dataset with Obstacles for Driving Scene Understanding](https://mlsanity.com/paper/2512.23215/) (2025)

## Abstract (arXiv)

Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks. However, the transition to semantic segmentation is hampered by strict memory limitations of contemporary GPUs. The extent of feature map caching required by convolutional backprop poses significant challenges even for moderately sized Pascal images, while requiring careful architectural considerations when the source resolution is in the megapixel range. To address these concerns, we propose a novel DenseNet-based ladder-style architecture which features high modelling power and a very lean upsampling datapath. We also propose to substantially reduce the extent of feature map caching by exploiting inherent spatial efficiency of the DenseNet feature extractor. The resulting models deliver high performance with fewer parameters than competitive approaches, and allow training at megapixel resolution on commodity hardware. The presented experimental results outperform the state-of-the-art in terms of prediction accuracy and execution speed on Cityscapes, Pascal VOC 2012, CamVid and ROB 2018 datasets. Source code will be released upon publication.