2 papers
cs.CV2025
Feature Space Analysis by Guided Diffusion Model
Kimiaki Shirahama, Miki Yanobu, Kaduki Yamashita +1
One of the key issues in Deep Neural Networks (DNNs) is the black-box nature of their internal feature extraction process. Targeting vision-related domains, this paper focuses on a…
cs.CL2025
Domain Adaptation for Japanese Sentence Embeddings with Contrastive Learning based on Synthetic Sentence Generation
Zihao Chen, Hisashi Handa, Miho Ohsaki +1
Several backbone models pre-trained on general domain datasets can encode a sentence into a widely useful embedding. Such sentence embeddings can be further enhanced by domain adap…