Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification

Bai, Haili; Song, Wen; Chan, S.-H. Gary

doi:10.48550/arxiv.2105.09684

Cited by 1 publication

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to its superior interpretability, feature decoupled learning has been well explored in tasks of fewshot learning (Ridgeway and Mozer 2018; Scott, Ridgeway, As for cross-domain crowd counting, on the one hand, we should effectively align domaininvariant features, on the other hand, we should be aware of the significance of task-related domain-specific features in CDCC. For example, the specific colorization information can assist the model to distinguish crowd and background in crowd counting (Bai, Wen, and Chan 2021). Therefore, the task of applying decoupling learning to CDCC is nontrivial.…”

Section: Feature Decoupling Learning In Cdccmentioning

confidence: 99%

Explicit Invariant Feature Induced Cross-Domain Crowd Counting

Cai

Chen

Guan

et al. 2023

AAAI

View full text Add to dashboard Cite

Cross-domain crowd counting has shown progressively improved performance. However, most methods fail to explicitly consider the transferability of different features between source and target domains. In this paper, we propose an innovative explicit Invariant Feature induced Cross-domain Knowledge Transformation framework to address the inconsistent domain-invariant features of different domains. The main idea is to explicitly extract domain-invariant features from both source and target domains, which builds a bridge to transfer more rich knowledge between two domains. The framework consists of three parts, global feature decoupling (GFD), relation exploration and alignment (REA), and graph-guided knowledge enhancement (GKE). In the GFD module, domain-invariant features are efficiently decoupled from domain-specific ones in two domains, which allows the model to distinguish crowds features from backgrounds in the complex scenes. In the REA module both inter-domain relation graph (Inter-RG) and intra-domain relation graph (Intra-RG) are built. Specifically, Inter-RG aggregates multi-scale domain-invariant features between two domains and further aligns local-level invariant features. Intra-RG preserves taskrelated specific information to assist the domain alignment. Furthermore, GKE strategy models the confidence of pseudolabels to further enhance the adaptability of the target domain. Various experiments show our method achieves state-of-theart performance on the standard benchmarks. Code is available at https://github.com/caiyiqing/IF-CKT.

show abstract

Section: Feature Decoupling Learning In Cdccmentioning

confidence: 99%