# Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization

arXiv: https://arxiv.org/abs/1611.05603 · HTML: https://mlsanity.com/paper/1611.05603/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2016.

## Built on by (most cited first, 9 of 9)

- [Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition](https://mlsanity.com/paper/2109.05686/) (2021)
- [Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting](https://mlsanity.com/paper/2107.03576/) (2021)
- [A Comparative Review of Recent Few-Shot Object Detection Algorithms](https://mlsanity.com/paper/2111.00201/) (2021)
- [UPAR: Unified Pedestrian Attribute Recognition and Person Retrieval](https://mlsanity.com/paper/2209.02522/) (2022)
- [SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition](https://mlsanity.com/paper/2312.06049/) (2023)
- [Attention-Based Acoustic Feature Fusion Network for Depression Detection](https://mlsanity.com/paper/2308.12478/) (2023)
- [Fine-Grained AutoAugmentation for Multi-Label Classification](https://mlsanity.com/paper/2107.05384/) (2021)
- [Learning Disentangled Label Representations for Multi-label Classification](https://mlsanity.com/paper/2212.01461/) (2022)
- [Reinforced Pedestrian Attribute Recognition with Group Optimization Reward](https://mlsanity.com/paper/2205.14042/) (2022)

## Abstract (arXiv)

State-of-the-art methods treat pedestrian attribute recognition as a multi-label image classification problem. The location information of person attributes is usually eliminated or simply encoded in the rigid splitting of whole body in previous work. In this paper, we formulate the task in a weakly-supervised attribute localization framework. Based on GoogLeNet, firstly, a set of mid-level attribute features are discovered by novelly designed detection layers, where a max-pooling based weakly-supervised object detection technique is used to train these layers with only image-level labels without the need of bounding box annotations of pedestrian attributes. Secondly, attribute labels are predicted by regression of the detection response magnitudes. Finally, the locations and rough shapes of pedestrian attributes can be inferred by performing clustering on a fusion of activation maps of the detection layers, where the fusion weights are estimated as the correlation strengths between each attribute and its relevant mid-level features. Extensive experiments are performed on the two currently largest pedestrian attribute datasets, i.e. the PETA dataset and the RAP dataset. Results show that the proposed method has achieved competitive performance on attribute recognition, compared to other state-of-the-art methods. Moreover, the results of attribute localization are visualized to understand the characteristics of the proposed method.