A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is
Due to the costliness of labelled data in real-world applications, semi-supervised object detectors, underpinned by pseudo labelling, are appealing. However, handling confusing samples is nontrivial: discarding valuable confusing samples would compromise the model generalisation while using them for training would exacerbate the confirmation bias issue caused by inevitable mislabelling. To solve this problem, this paper proposes to use confusing samples proactively without label correction.arXiv:2207.03433v2 fatcat:o5uppii2jnhillc3qnwee6gwkm