Image quality assessment based on self-supervised learning and knowledge distillation

Sang, Qingbing; Shu, Ziru; Liu, Lixiong; Hu, Cong; Wu, Qingqing

doi:10.1016/j.jvcir.2022.103708

Cited by 6 publications

(1 citation statement)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the proposed method is flexible in fusing characteristics from any architectures. Some works [15], [69] have tried to utilize the complementarity to improve self-supervised learning. Specifically, these methods make the ViT and ResNet guide each other.…”

Section: Heterogeneity On Neural Networkmentioning

confidence: 99%

Research on the restoration of costumes in the paintings of ladies in the Ming Dynasty

Liu

Gao

2023

Machine Learning, Multi Agent and Cyber Physical Systems

View full text Add to dashboard Cite

Incorporating heterogeneous representations from different architectures has facilitated various vision tasks, e.g., some hybrid networks combine transformers and convolutions. However, complementarity between such heterogeneous architectures has not been well exploited in self-supervised learning. Thus, we propose Heterogeneous Self-Supervised Learning (HSSL), which enforces a base model to learn from an auxiliary head whose architecture is heterogeneous from the base model. In this process, HSSL endows the base model with new characteristics in a representation learning way without structural changes. To comprehensively understand the HSSL, we conduct experiments on various heterogeneous pairs containing a base model and an auxiliary head. We discover that the representation quality of the base model moves up as their architecture discrepancy grows. This observation motivates us to propose a search strategy that quickly determines the most suitable auxiliary head for a specific base model to learn and several simple but effective methods to enlarge the model discrepancy. The HSSL is compatible with various self-supervised methods, achieving superior performances on various downstream tasks, including image classification, semantic segmentation, instance segmentation, and object detection. Our source code will be made publicly available.

show abstract

Section: Heterogeneity On Neural Networkmentioning

confidence: 99%

Research on the restoration of costumes in the paintings of ladies in the Ming Dynasty

Liu

Gao

2023

Machine Learning, Multi Agent and Cyber Physical Systems

View full text Add to dashboard Cite

show abstract

QualityNet: A multi-stream fusion framework with spatial and channel attention for blind image quality assessment

Aslam,

Wei,

Khalid

et al. 2024

Sci Rep

View full text Add to dashboard Cite

This study introduces a novel Blind Image Quality Assessment (BIQA) approach leveraging a multi-stream spatial and channel attention model. Our method addresses challenges posed by diverse image content and distortions by integrating feature maps from two distinct backbones. Through spatial and channel attention mechanisms, our algorithm prioritizes regions of interest, enhancing its ability to capture crucial image details. Extensive evaluations on four benchmark datasets demonstrate superior performance compared to existing methods, closely aligning with human perceptual assessment. Our approach exhibits exceptional generalization capabilities on both authentic and synthetic distortion databases. Moreover, it demonstrates a distinctive focus on perceptual foreground information, enhancing its practical applicability. Thorough quantitative analyses underscore the algorithm’s superior performance, establishing its dominance over existing methods.

show abstract

Review of Quality Assessment Algorithms on the Realistic Blurred Image Database (BID2011)

Yu,

Gu,

Wang

et al. 2023

2023 8th International Conference on Signal and Image Processing (ICSIP)

View full text Add to dashboard Cite

Image quality assessment based on self-supervised learning and knowledge distillation

Cited by 6 publications

References 59 publications

Research on the restoration of costumes in the paintings of ladies in the Ming Dynasty

Research on the restoration of costumes in the paintings of ladies in the Ming Dynasty

QualityNet: A multi-stream fusion framework with spatial and channel attention for blind image quality assessment

Review of Quality Assessment Algorithms on the Realistic Blurred Image Database (BID2011)

Contact Info

Product

Resources

About