Publications
カンファレンス (国際) Retrieval of LoRA Models based on Layer-Wise Weight Embedding without Metadata
Yuro Kanada (Shizuoka University), Yuma Oe (Shizuoka University), Huu-Long Pham (University of Tsukuba), Makoto P. Kato (University of Tsukuba), Hiroaki Ohshima (University of Hyogo), Sumio Fujita, Yoshiyuki Shoji (Shizuoka University)
The 16th ACM International Conference on Multimedia Retrieval (ICMR 2026)
2026.6.15
This paper proposes a method for learning embedding representations of style-transfer LoRA models based on their internal weight parameters, capturing transformation characteristics without relying on output examples or metadata. To vectorize LoRA models with multiple layers, we extract internal parameters layer-wise, then flatten and reduce dimensionality, representing each model as a sequence of low-dimensional vectors. Using this vector sequence as input, we perform triplet-based metric learning with a Triplet Network composed of three weight-sharing Transformer encoders and an MLP aggregation module. This framework estimates visual similarity between images transformed by different LoRA models. We conduct automatic evaluation of training validity, verify alignment with human relative similarity judgments, and perform retrieval-based ranking assessment. The results demonstrate that the proposed method learns embeddings consistent with human perception and enables stable retrieval of similar LoRA models.
Paper :
Retrieval of LoRA Models based on Layer-Wise Weight Embedding without Metadata
（外部サイト）