Code of paper “Knowledge Decomposition and Replay: A Novel Cross-modal Image-Text Retrieval Continual Learning Method”

Code of paper “Transcending Fusion A Multi Scale Alignment Method for Remote Sensing Image Text Retrieval”

Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models

Code for paper "Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters" CVPR2024

A curated list of awesome vision and language resources for earth observation.

🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox

[CVPR 2024 Highlight] - Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements (notable top 2.8%)

Single Shot Tracker