# Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net

arXiv: https://arxiv.org/abs/1511.06881 · HTML: https://mlsanity.com/paper/1511.06881/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2015.

## Built on by (most cited first, 21 of 21)

- [SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation](https://mlsanity.com/paper/2209.08575/) (2022)
- [Sapiens: Foundation for Human Vision Models](https://mlsanity.com/paper/2408.12569/) (2024)
- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [Fine-Grained Visual Prompting](https://mlsanity.com/paper/2306.04356/) (2023)
- [Progressive Semantic Segmentation](https://mlsanity.com/paper/2104.03778/) (2021)
- [Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing](https://mlsanity.com/paper/2103.04570/) (2021)
- [Resolution learning in deep convolutional networks using scale-space theory](https://mlsanity.com/paper/2106.03412/) (2021)
- [NightLab: A Dual-level Architecture with Hardness Detection for Segmentation at Night](https://mlsanity.com/paper/2204.05538/) (2022)
- [Learning to Downsample for Segmentation of Ultra-High Resolution Images](https://mlsanity.com/paper/2109.11071/) (2021)
- [Deep Learning Technique for Human Parsing: A Survey and Outlook](https://mlsanity.com/paper/2301.00394/) (2023)
- [Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles](https://mlsanity.com/paper/2103.14098/) (2021)
- [SALISA: Saliency-based Input Sampling for Efficient Video Object Detection](https://mlsanity.com/paper/2204.02397/) (2022)
- [FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing](https://mlsanity.com/paper/2203.16168/) (2022)
- [From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction](https://mlsanity.com/paper/2602.01661/) (2026)
- [Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentation](https://mlsanity.com/paper/2309.08020/) (2023)
- [PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarization](https://mlsanity.com/paper/2211.06560/) (2022)
- [Parsing Objects at a Finer Granularity: A Survey](https://mlsanity.com/paper/2212.13693/) (2022)
- [Deep Learning for Human Parsing: A Survey](https://mlsanity.com/paper/2301.12416/) (2023)
- [Graph-Boosted Attentive Network for Semantic Body Parsing](https://mlsanity.com/paper/2407.05924/) (2024)
- [Dictionary-based Framework for Interpretable and Consistent Object Parsing](https://mlsanity.com/paper/2502.19540/) (2025)
- [Learning 3D Texture-Aware Representations for Parsing Diverse Human Clothing and Body Parts](https://mlsanity.com/paper/2508.06032/) (2025)

## Abstract (arXiv)

Parsing articulated objects, e.g. humans and animals, into semantic parts (e.g. body, head and arms, etc.) from natural images is a challenging and fundamental problem for computer vision. A big difficulty is the large variability of scale and location for objects and their corresponding parts. Even limited mistakes in estimating scale and location will degrade the parsing output and cause errors in boundary details. To tackle these difficulties, we propose a "Hierarchical Auto-Zoom Net" (HAZN) for object part parsing which adapts to the local scales of objects and parts. HAZN is a sequence of two "Auto-Zoom Net" (AZNs), each employing fully convolutional networks that perform two tasks: (1) predict the locations and scales of object instances (the first AZN) or their parts (the second AZN); (2) estimate the part scores for predicted object instance or part regions. Our model can adaptively "zoom" (resize) predicted image regions into their proper scales to refine the parsing. We conduct extensive experiments over the PASCAL part datasets on humans, horses, and cows. For humans, our approach significantly outperforms the state-of-the-arts by 5% mIOU and is especially better at segmenting small instances and small parts. We obtain similar improvements for parsing cows and horses over alternative methods. In summary, our strategy of first zooming into objects and then zooming into parts is very effective. It also enables us to process different regions of the image at different scales adaptively so that, for example, we do not need to waste computational resources scaling the entire image.