Multi-Task Learning with Deep Dual-Path Network for Facial Attribute Recognition

Lai, Xinyu; Chen, Si; Wang, Da‐Han; Zhu, Shengqi

doi:10.1145/3436369.3437403

Cited by 4 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to KT-MTL [12] and DMM-CNN [13], our approach exploits the correlations among attribute labels more deeply and reduces human intervention. Compared to Nian et al [37] and DPN [18], our method mitigates the effect of imbalanced data. It is important to note that only accuracy is -363 used when comparing the proposed solution with state-of-theart methods.…”

Section: Results and Analysis Of Our Methodsmentioning

confidence: 97%

“…Compared to Nian et al. [37] and DPN [18], our method mitigates the effect of imbalanced data. It is important to note that only accuracy is used when comparing the proposed solution with state‐of‐the‐art methods.…”

Section: Methodsmentioning

confidence: 99%

“…PS-MCNN divides 40 attributes into four groups (upper, middle, lower, and whole) according to their location in the image. Similarly, Lai et al [18] propose a dual-path network that takes two groups (local and global attributes) as inputs. These methods only simply group the attributes according to their positions in the face.…”

Section: Attribute Grouping In Facmentioning

confidence: 99%

“…Similarly, Lai et al. [18] propose a dual‐path network that takes two groups (local and global attributes) as inputs. These methods only simply group the attributes according to their positions in the face.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Facial attribute classification by deep mining inter‐attribute correlations

Liu

Zhang

Chang

et al. 2023

IET Computer Vision

View full text Add to dashboard Cite

Face attribute classification (FAC) has received considerable attention due to its excellent application value in bio‐metric verification and face retrieval. Current FAC methods suffer two typical challenges: complex inter‐attribute correlations and imbalanced learning. Aims at the challenges, presents an end‐to‐end FAC framework with integrated use of multiple strategies, which consists of a convolutional neural network (CNN) and a graph convolutional network (GCN). The GCN is used to model the semantic correlations among attributes and capture inter‐dependency among them. The correlation information learnt via the GCN is used to guide the learning of the inter‐dependent classification features of the FAC network. An adaptive thresholding strategy and a boosting scheme are adopted to alleviate the effect of the class‐imbalance. To deal with the task imbalance problem, a new dynamic weighting scheme is proposed to update the weight of each attribute classification task in the training process. We apply four evaluation metrics to evaluate the proposed method. Experimental results show all the proposed strategies are effective, and our approach outperforms state‐of‐the‐art FAC methods on two challenging datasets CelebA and LFWA.

show abstract