Active and semi-supervised learning for object detection with imperfect data

In a few other works, the combination of active learning and Semi-Supervised Learning was addressed.

“In a few other works [61,67], the combination of AL and Semi-Supervised Learning (SSL) was addressed.”

In hybrid methods combining uncertainty- and diversity-based methods, diversity can prevent instances from overlapping or becoming redundant in queries, producing better sampling results, or can overcome noisy labels.

“For example, in the combination of uncertainty- and diversity-based methods, diversity can prevent instances from overlapping or becoming redundant in queries producing better sampling results [36,67], or can overcome noisy labels [61].”

Proposed methods do not always fully explore their potential by focusing on an exclusive criterion when considering several complementary sampling strategies simultaneously is possible.

“However, the proposed methods do not always fully explore their potential by focusing on an exclusive criteria-among the previously referenced ones-when considering several complementary sampling strategies simultaneously is possible [36,37,44,45,57,61,67].”

Clustering algorithms have been widely applied to optimise criteria such as diversity, representativeness, rarity, and density.

“Clustering algorithms, for example, have been widely applied to optimise criteria such as diversity [49], representativeness [67], rarity [15,50], and density [16,78].”