← Back to all news
arXiv AI By Kyle Stein, Andrew Arash Mahyari, Guillermo Francia III, Eman El-Sheikh, Jiangpeng He

LSA-PAST: Layer-Specific Adaptation and Prototype Transport for Compositional Incremental Learning

Read the original on arXiv AI →

The paper introduces LSA-PAST, a parameter‑efficient approach for compositional incremental learning that addresses the challenge of learning new state‑object compositions while preserving knowledge of previously seen compositions. It combines Layer‑Specific Adaptation using Low‑Rank Adaptation (LoRA) with depth‑specialized adapters for states, objects, and compositions, and employs Prototype‑Anchored Adapter‑Space Transport (PAST) to map past prototypes into the current adapter space without rehearsal. Experiments show that LSA-PAST achieves state‑of‑the‑art accuracy‑forgetting trade‑off performance in this setting.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Oct 9

C-LoRA: Continual Low-Rank Adaptation for Pre-trained Visual Models

C-LoRA introduces a continual learning approach for pre‑trained visual models that uses a single shared Low‑Rank Adaptation (LoRA) adapter. It employs a learnable routing matrix split into a stability component (R_base) and a plasticity component (R_delta) to balance preserving past knowledge and adapting to new tasks. This design eliminates the need for expanding modules or complex inference fusion while maintaining competitive performance on multiple benchmarks.

By Xin Zhang, Liang Bai, Xian Yang
computer-visionfine-tuningbenchmarks
More like this →
arXiv Machine Learning
Oct 21

Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning

The paper introduces HASTEN, a hierarchical semantic tree anchoring framework that enhances CLIP-based class‑incremental learning by incorporating external hierarchical knowledge into hyperbolic space. By treating classes as part of a structured hierarchy rather than isolated labels, HASTEN stabilizes visual and textual feature mappings, reduces feature drift, and mitigates catastrophic forgetting across incremental tasks. Experiments on nine benchmarks demonstrate that HASTEN consistently outperforms existing methods.

By Tao Hu, Lan Li, Zhen-Hao Xie, Da-Wei Zhou
llmsmultimodalbenchmarks
More like this →
arXiv AI
2d ago

Drift-adaptive Representation Preservation for Domain-Incremental Learning

The paper proposes a drift‑adaptive method for Domain‑Incremental Learning that tracks representation drift for each past domain‑class pair. By measuring how much a concept’s current representation deviates from a fixed anchor, the method assigns stronger preservation to high‑drift pairs and down‑weights highly drifted domains during prototype construction. Experiments on DomainNet, Office‑Home, CORe50, and CDDB‑Hard show that this approach maintains a strong accuracy‑forgetting balance while using less training memory and the smallest storage compared to other methods.

By Hyunmin Kong, Gyutae Oh, Jitae Shin
ragbenchmarks
More like this →