Survey of methods for handling distribution shifts for robust computer vision
Survey of methods for handling distribution shifts for robust computer vision
Robust Computer Vision in an Ever-Changing World: A Survey of Techniques for Tackling Distribution Shifts
arXiv paper abstract https://arxiv.org/abs/2312.01540
arXiv PDF paper https://arxiv.org/pdf/2312.01540.pdf
… There is … gap between … computer vision models and … the real world. One … is … distribution shift.
… In … paper, … discuss the identification of such a prominent gap, exploring the concept of distribution shift and its critical significance.
… provide an in-depth overview of various types of distribution shifts, elucidate their distinctions, and explore techniques within the realm of the data-centric domain employed to address them.
Distribution shifts can occur during every phase of the machine learning pipeline, from the data collection stage to the stage of training a machine learning model to the stage of final model deployment.
… compare and contrast numerous AI models that are built for mitigating shifts in hidden stratification and spurious correlations, adversarial attack shift, and unseen data shifts.
… summarize the innovations and major contributions in the literature, give new perspectives toward robustness, and highlight the limitations of those proposed ideas …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
