# Quantized Densely Connected U-Nets for Efficient Landmark Localization

arXiv: https://arxiv.org/abs/1808.02194 · HTML: https://mlsanity.com/paper/1808.02194/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2018.

## Built on by (most cited first, 20 of 20)

- [Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective](https://mlsanity.com/paper/2104.11536/) (2021)
- [STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection](https://mlsanity.com/paper/2306.02763/) (2023)
- [Boundary-Aware Segmentation Network for Mobile and Web Applications](https://mlsanity.com/paper/2101.04704/) (2021)
- [SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos](https://mlsanity.com/paper/2104.11452/) (2021)
- [ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment](https://mlsanity.com/paper/2109.05721/) (2021)
- [Towards Accurate Facial Landmark Detection via Cascaded Transformers](https://mlsanity.com/paper/2208.10808/) (2022)
- [Precise Facial Landmark Detection by Reference Heatmap Transformer](https://mlsanity.com/paper/2303.07840/) (2023)
- [Subpixel Heatmap Regression for Facial Landmark Localization](https://mlsanity.com/paper/2111.02360/) (2021)
- [Robust and Precise Facial Landmark Detection by Self-Calibrated Pose Attention Network](https://mlsanity.com/paper/2112.12328/) (2021)
- [Uncertainty Estimation for Heatmap-based Landmark Localization](https://mlsanity.com/paper/2203.02351/) (2022)
- [When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model](https://mlsanity.com/paper/2105.13150/) (2021)
- [KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration](https://mlsanity.com/paper/2305.16437/) (2023)
- [POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position Search](https://mlsanity.com/paper/2410.09583/) (2024)
- [Location-free Human Pose Estimation](https://mlsanity.com/paper/2205.12619/) (2022)
- [Supervision-by-Hallucination-and-Transfer: A Weakly-Supervised Approach for Robust and Precise Facial Landmark Detection](https://mlsanity.com/paper/2601.12919/) (2026)
- [FineNet: Frame Interpolation and Enhancement for Face Video Deblurring](https://mlsanity.com/paper/2103.00871/) (2021)
- [PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation](https://mlsanity.com/paper/2109.10083/) (2021)
- [Improving Pose Estimation through Contextual Activity Fusion](https://mlsanity.com/paper/2111.02500/) (2021)
- [Iterative Saliency Enhancement using Superpixel Similarity](https://mlsanity.com/paper/2112.00665/) (2021)
- [LocalEyenet: Deep Attention framework for Localization of Eyes](https://mlsanity.com/paper/2303.12728/) (2023)

## Abstract (arXiv)

In this paper, we propose quantized densely connected U-Nets for efficient visual landmark localization. The idea is that features of the same semantic meanings are globally reused across the stacked U-Nets. This dense connectivity largely improves the information flow, yielding improved localization accuracy. However, a vanilla dense design would suffer from critical efficiency issue in both training and testing. To solve this problem, we first propose order-K dense connectivity to trim off long-distance shortcuts; then, we use a memory-efficient implementation to significantly boost the training efficiency and investigate an iterative refinement that may slice the model size in half. Finally, to reduce the memory consumption and high precision operations both in training and testing, we further quantize weights, inputs, and gradients of our localization network to low bit-width numbers. We validate our approach in two tasks: human pose estimation and face alignment. The results show that our approach achieves state-of-the-art localization accuracy, but using ~70% fewer parameters, ~98% less model size and saving ~75% training memory compared with other benchmark localizers. The code is available at https://github.com/zhiqiangdon/CU-Net.