Incremental Few-Shot Learning for Pedestrian Attribute Recognition

Xiang, Liuyu; Jin, Xiaoming; Ding, Guiguang; Han, Jungong; Li, Leida

doi:10.24963/ijcai.2019/543

Cited by 23 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Few-shot learning methods [15,9,11,46] also try to generalize knowledge from a richly annotated dataset to a low-shot dataset. This is often achieved by training a meta-learner from the many-shot classes and then generalize to new fewshot classes.…”

Section: Related Workmentioning

confidence: 99%

Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-Tailed Classification

Xiang

Ding

Han

2020

Lecture Notes in Computer Science

Self Cite

187

109

View full text Add to dashboard Cite

In real-world scenarios, data tends to exhibit a long-tailed distribution, which increases the difficulty of training deep networks. In this paper, we propose a novel self-paced knowledge distillation framework, termed Learning From Multiple Experts (LFME). Our method is inspired by the observation that networks trained on less imbalanced subsets of the distribution often yield better performances than their jointly-trained counterparts. We refer to these models as 'Experts', and the proposed LFME framework aggregates the knowledge from multiple 'Experts' to learn a unified student model. Specifically, the proposed framework involves two levels of adaptive learning schedules: Self-paced Expert Selection and Curriculum Instance Selection, so that the knowledge is adaptively transferred to the 'Student'. We conduct extensive experiments and demonstrate that our method is able to achieve superior performances compared to state-of-the-art methods. We also show that our method can be easily plugged into state-of-the-art long-tailed classification algorithms for further improvements.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-Tailed Classification

Xiang

Ding

Han

2020

Lecture Notes in Computer Science

Self Cite

187

109

View full text Add to dashboard Cite

show abstract

“…To tackle this problem, we consider a more realistic setting where the relations learning system can not only learn the base relations from the large-scale training data, but also dynamically recognize the novel relations with only a few support examples (termed as incremental few-shot relation classification). 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. Different from images, the text is more diverse and noisy.…”

Section: Related Workmentioning

confidence: 99%

“…However, these two solutions still suffer from the lack of large-scale labeled data for novel relations. They are prone to overfitting on novel relations and may even lead to catastrophic forgetting on base ones (i.e., previous pre-defined relations) when given insufficient training data for novel relations (Xiang et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification

Ren¹,

Cai²,

Chen³

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

Relation Classification (RC) plays an important role in natural language processing (NLP). Current conventional supervised and distantly supervised RC models always make a closed-world assumption which ignores the emergence of novel relations in an open environment. To incrementally recognize the novel relations, current two solutions (i.e, re-training and lifelong learning) are designed but suffer from the lack of large-scale labeled data for novel relations. Meanwhile, prototypical network enjoys better performance on both fields of deep supervised learning and few-shot learning. However, it still suffers from the incompatible feature embedding problem when the novel relations come in. Motivated by them, we propose a two-phase prototypical network with prototype attention alignment and triplet loss to dynamically recognize the novel relations with a few support instances meanwhile without catastrophic forgetting. Extensive experiments are conducted to evaluate the effectiveness of our proposed model.

show abstract

“…Han et al [20] proposed an attention aware pooling method for pedestrian attribute recognition which can also exploit the correlations between attributes. Xiang et al [21] proposed a meta learning based method for pedestrian attribute recognition to handle the scenario for newly added attributes; semantic similarity and the spatial neighborhood of attributes are not taken into account in this method. In [22], the authors theoretically illustrated that the deeper networks generally take more information into consideration which helps improve classification accuracy.…”

Section: Related Workmentioning

confidence: 99%

Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance Scenarios

2019

View full text Add to dashboard Cite

Pedestrian attribute recognition is to predict a set of attribute labels of the pedestrian from surveillance scenarios, which is a very challenging task for computer vision due to poor image quality, continual appearance variations, as well as diverse spatial distribution of imbalanced attributes. It is desirable to model the label dependencies between different attributes to improve the recognition performance as each pedestrian normally possesses many attributes. In this paper, we treat pedestrian attribute recognition as multi-label classification and propose a novel model based on the graph convolutional network (GCN). The model is mainly divided into two parts, we first use convolutional neural network (CNN) to extract pedestrian feature, which is a normal operation processing image in deep learning, then we transfer attribute labels to word embedding and construct a correlation matrix between labels to help GCN propagate information between nodes. This paper applies the object classifiers learned by GCN to the image representation extracted by CNN to enable the model to have the ability to be end-to-end trainable. Experiments on pedestrian attribute recognition dataset show that the approach obviously outperforms other existing state-of-the-art methods.

show abstract

Incremental Few-Shot Learning for Pedestrian Attribute Recognition

Cited by 23 publications

References 7 publications

Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-Tailed Classification

Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-Tailed Classification

A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification

Pedestrian Attribute Recognition with Graph Convolutional Network in Surveillance Scenarios

Contact Info

Product

Resources

About