arXiv (All)
open access
What Must Replay Preserve? Separating Correctable Bias from Class Correspondence
Class-incremental learning must recognize all classes seen so far without task labels. Logit replay methods such as DER and DER++ mitigate forgetting by matching the model's past predictions on stored examples. Deleting this matching reveals its benefit, but the resulting accuracy cost cannot show w
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Domain-Incremental Learning for Multi-Channel Replay Speech Detection#998743
- Domain-Incremental Learning for Multi-Channel Replay Speech Detection#673415
- Contextual Memory Recall: A Novel Metric for Class Incremental Learning#1313518
- Auditing Information Disclosure During Large-Scale Gradient-Based Training via Gradient Uniqueness#1117259
- Erased, but Not Gone: Output Forgetting Is Not True Forgetting#1297182
Record · ID 1216452
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive