Proxy-FDA aligns the local neighborhood structure of pre-trained and fine-tuned feature spaces, generating synthetic proxies to reduce concept forgetting during fine-tuning.
Contrastive Neighborhood Alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We present Contrastive Neighborhood Alignment (CNA), a manifold learning approach to maintain the topology of learned features whereby data points that are mapped to nearby representations by the source (teacher) model are also mapped to neighbors by the target (student) model. The target model aims to mimic the local structure of the source representation space using a contrastive loss. CNA is an unsupervised learning algorithm that does not require ground-truth labels for the individual samples. CNA is illustrated in three scenarios: manifold learning, where the model maintains the local topology of the original data in a dimension-reduced space; model distillation, where a small student model is trained to mimic a larger teacher; and legacy model update, where an older model is replaced by a more powerful one. Experiments show that CNA is able to capture the manifold in a high-dimensional space and improves performance compared to the competing methods in their domains.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
Proxy-FDA aligns the local neighborhood structure of pre-trained and fine-tuned feature spaces, generating synthetic proxies to reduce concept forgetting during fine-tuning.