I2I: Initializing Adapters with Improvised Knowledge

4 April 2023

Papers citing "I2I: Initializing Adapters with Improvised Knowledge"

6 / 6 papers shown

Title
CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models Saurav Jha Dong Gong Lina Yao CLIP VLM 31 7 0 28 Mar 2024
Cross-domain Multi-modal Few-shot Object Detection via Rich Text Zeyu Shangguan Daniel Seita Mohammad Rostami ObjD 42 1 0 24 Mar 2024
Dynamic Transformer Architecture for Continual Learning of Multimodal Tasks Yuliang Cai Mohammad Rostami 30 4 0 27 Jan 2024
Robust Internal Representations for Domain Generalization Mohammad Rostami OOD 25 0 0 27 Sep 2023
Improved Region Proposal Network for Enhanced Few-Shot Object Detection Zeyu Shangguan Mohammad Rostami ObjD 23 3 0 15 Aug 2023
Task-Attentive Transformer Architecture for Continual Learning of Vision-and-Language Tasks Using Knowledge Distillation Yuliang Cai Jesse Thomason Mohammad Rostami VLM CLL 19 11 0 25 Mar 2023