Towards improved proxy-based deep metric learning via data-augmented domain adaptation
Abstract Deep Metric Learning (DML) plays an important role in modern computer vision
research, where we learn a distance metric for a set of image representations. Recent DML …
research, where we learn a distance metric for a set of image representations. Recent DML …
Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning
Deep Metric Learning (DML) has long attracted the attention of the machine learning
community as a key objective. Existing solutions concentrate on fine-tuning the pre-trained …
community as a key objective. Existing solutions concentrate on fine-tuning the pre-trained …
Dual Variational Generation Framework for Enhanced Cross-Modal Face Recognition
One of the major challenges in face recognition is accurately identifying faces under varying
lighting conditions, leading to a problem known as Heterogeneous Face Recognition (HFR) …
lighting conditions, leading to a problem known as Heterogeneous Face Recognition (HFR) …
基于表示学习的跨模态检索方法研究进展
杜锦丰， 王海荣， 梁焕， 王栋 - 《 广西师范大学学报》(自然科学版 …, 2022 - gxsf.magtech.com.cn
多模态数据的急剧增长带来了跨模态检索的应用需求, 促进了对跨模态检索方法的研究.
本文追溯该领域最新进展, 跟踪并深入研究国内外基于表示学习的跨模态检索方法 …
本文追溯该领域最新进展, 跟踪并深入研究国内外基于表示学习的跨模态检索方法 …
Prompt Distribution Matters: Tuning Visual Prompt Through Semantic Metric Guidance
L Ren, C Chen, L Wang, KA Hua - openreview.net
Visual Prompt Tuning (VPT) has become a promising solution for Parameter-Efficient Fine-
Tuning (PEFT) of pre-trained Vision Transformer (ViT) models on downstream vision tasks …
Tuning (PEFT) of pre-trained Vision Transformer (ViT) models on downstream vision tasks …