SegIns: A simple extension to instance discrimination task for better localization learning

Melih Baydar, Emre Akbas

Abstract: Highlights•Convolutional Neural Networks lose localization info with instance discrimination task.•Augmenting instance discrimination with an extra dense task enhances localization.•Unsupervised foreground segmentation boosts localization in (non-)contrastive methods.•Improved localization in SSL enhances transfer learning in dense downstream tasks.