- Rating
- 2
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
FROST is an exemplar-free FSCIL method that freezes a base-adapted pretrained encoder and incrementally updates two memories: a closed-form ridge-based correlation memory and a class-prototype memory. The method is evaluated on multiple 2D and 3D benchmarks, where it reports strong improvements over prior FSCIL baselines.
Critical strengths
- Strong empirical performance across diverse 2D/3D FSCIL and cross-domain benchmarks.
- Simple exemplar-free design with no session-wise gradient updates, offering good efficiency and practicality.
Critical weaknesses
-
CorrMem closely follows prior analytical ridge-based continual learning (e.g., RanPAC), while ProtoMem is a standard prototype-based classifier. The main contribution is largely their simple fusion.
-
The paper lacks strong direct baselines such as RanPAC adapted to the same FSCIL protocol, with and without prototype fusion, making it difficult to isolate where the reported gains come from.
Questions for authors
-
How does FROST differ technically from RanPAC/ACIL beyond adding ProtoMem and fixed logit fusion? Please clarify the methodological novelty.
-
Could you report a direct baseline of RanPAC under the identical FSCIL protocol, as well as RanPAC + prototype fusion, to isolate the contribution of FROST?
-
FROST substantially outperforms the joint-training Oracle in several settings. Could you clarify why this occurs and whether the Oracle uses exactly the same backbone, adaptation, and training protocol?