Incremental Few-Shot Learning for Pedestrian Attribute Recognition
By Liuyu Xiang, Xiaoming Jin, Guiguang Ding, Jungong Han, Leida Li. 2019
33 citations recorded by the source corpus.
Pedestrian attribute recognition has received increasing attention due to its important role in video surveillance applications. However, most existing methods are designed for a fixed set of attributes. They are unable to handle the incremental few-shot learning scenario, i.e. adapting a well-trained model to newly added attributes with scarce data, which commonly exists in the real world. In this work, we present a meta learning based method to address this issue. The core of our framework is a meta architecture capable of disentangling multiple attribute information and generalizing rapidly to new coming attributes. By conducting extensive experiments on the benchmark dataset PETA and RAP under the incremental few-shot setting, we show that our method is able to perform the task with competitive performances and low resource requirements.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Stefano Soatto
- Alessandro Achille
- Avinash Ravichandran
- Rahul Bhotika
- Qing Liu
- Orchid Majumder
- Haopeng Ren
- Yi Cai
In Computer Vision and Pattern Recognition
- Stefano Soatto
- Alessandro Achille
- Avinash Ravichandran
- Rahul Bhotika
- Qing Liu
- Dacheng Tao
- Orchid Majumder
- Guiguang Ding
Citations in the corpus
- A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification (2020, background): “Currently, several related works (Qi et al., 2018; Gidaris and Komodakis, 2018; Xiang et al., 2019; Ren et al., 2019) are proposed in computer vision field and they concentrate on image classification task.”
- Incremental Meta-Learning via Indirect Discriminant Alignment (2020, background): “[40, 34] extended this class-incremental framework to other visual recognition tasks like semantic segmentation”
- Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification (2020, background): “Few-shot learning methods [10, 15, 47] also try to generalize knowledge from a richly annotated dataset to a low-shot dataset.”
- A Survey on Few-Shot Class-Incremental Learning (2023, methodology): “Based on the idea of meta-learning, Xiang et al. (2019) uses an attribute prototype generator module and attribute relationship module to generate novel classification weights from annotated data.”