FaceOcc: A Diverse, High-quality Face Occlusion Dataset for Human Face Extraction

Yin, Xiangnan; Chen, Liming

doi:10.48550/arxiv.2201.08425

Cited by 2 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FaceOcc's COFW_test [21] and NatOcc's RealOcc datasets [10] are used to evaluate the performance of the occlusionaware model. This dataset consists of actual occluded photos, not synthetic ones, and only has labels for the skin class.…”

Section: ) Datasets For Occlusion Performance Testmentioning

confidence: 99%

Advancing Face Parsing in Real-World: Synergizing Self-Attention and Self-Distillation

Han,

Yoon

2024

IEEE Access

View full text Add to dashboard Cite

Face parsing, the segmentation of facial components at the pixel level, is pivotal for comprehensive facial analysis. However, previous studies encountered challenges, showing reduced performance in areas with small or thin classes like necklaces and earrings, and struggling to adapt to occlusion scenarios such as masks, glasses, caps or hands. To address these issues, this study proposes a robust face parsing technique through the strategic integration of self-attention and self-distillation methods. The self-attention module enhances contextual information, enabling precise feature identification for each facial element. Multi-task learning for edge detection, coupled with a specialized loss function focusing on edge regions, elevates the understanding of fine structures and contours. Additionally, the application of self-distillation for fine-tuning proves highly efficient, producing refined parsing results while maintaining high performance in scenarios with limited labels and ensuring robust generalization. The integration of self-attention and self-distillation techniques addresses challenges of previous studies, particularly in handling small or thin classes. This strategic fusion enhances overall performance, achieving computational efficiency, and aligns with the latest trends in this research area. The proposed approach attains a Mean F1 score of 88.18% on the CelebAMask-HQ dataset, marking a significant advancement in face parsing with state-of-the-art performance. Even in challenging occlusion areas like hands and masks, it demonstrates a remarkable F1 score of over 99%, showcasing robust face parsing capabilities in real-world environments.

show abstract

Section: ) Datasets For Occlusion Performance Testmentioning

confidence: 99%

Advancing Face Parsing in Real-World: Synergizing Self-Attention and Self-Distillation

Han,

Yoon

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Face occlusion segmentation tasks [14,51,52,53] employ the above semantic segmentation approaches. Particularly, Voo et al [14] opened their face occlusion dataset, based on CelebAMask-HQ [54].…”

Section: Occlusion Segmentationmentioning

confidence: 99%

“…Consequently, they synthesized face images with hands, COCO [55] objects, or random shapes. Yin et al [53] also synthesized a face occlusion dataset based on CelebAMask-HQ, but it is currently unavailable.…”

Section: Occlusion Segmentationmentioning

confidence: 99%

Facial Landmark, Head Pose, and Occlusion Analysis Using Multitask Stacked Hourglass

2023

View full text Add to dashboard Cite

In this study, we proposed a multitask network architecture for three attributes, landmark, head pose, and occlusion, from a face image. A 2-stacked hourglass with three task-specific heads is the proposed network architecture. We also designed three auxiliary components for the network. First is the feature pyramid fusion module, which plays a crucial role in facilitating contextual information from various receptive fields. Second is the interlevel occlusion-aware fusion module, which explicitly fuses intermediate occlusion prediction between subnetworks. The third is the gimbal-lock-free head pose head, which outputs a rotation matrix from a 6D rotation representation. We conducted an ablative study of these auxiliary components to determine their impacts on the network. Additionally, we introduced the landmark heatmap scaling approach to avoid falling local minima. We trained the proposed network with a 300W-LP dataset for landmark and head pose and a C-CM dataset for occlusion. Then, we fine-tuned the network using the 300W or WFLW dataset, instead of the 300W-LP dataset for the landmark task. This 2-stage training method contributes to enhancing the landmark detection accuracy and that of other tasks. In the experiments, we assessed the proposed network using eight test datasets and task-specific metrics.

show abstract

FaceOcc: A Diverse, High-quality Face Occlusion Dataset for Human Face Extraction

Cited by 2 publications

References 22 publications

Advancing Face Parsing in Real-World: Synergizing Self-Attention and Self-Distillation

Advancing Face Parsing in Real-World: Synergizing Self-Attention and Self-Distillation

Facial Landmark, Head Pose, and Occlusion Analysis Using Multitask Stacked Hourglass

Contact Info

Product

Resources

About