Papers › Continual Learning of Object Instances
Continual Learning of Object Instances
Kishan Parshotam, Mert Kilickaya
We propose continual instance learning - a method that applies the concept of continual learning to the task of distinguishing instances of the same object category. We specifically focus on the car object, and incrementally learn to distinguish car instances from each other with metric learning. We begin our paper by evaluating current techniques. Establishing that catastrophic forgetting is evident in existing methods, we then propose two remedies. Firstly, we regularise metric learning via Normalised Cross-Entropy. Secondly, we augment existing models with synthetic data transfer. Our extensive experiments on three large-scale datasets, using two different architectures for five different continual learning methods, reveal that Normalised cross-entropy and synthetic transfer leads to less forgetting in existing techniques.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections