Search Results for author:
Found 6 papers, 4 papers with code
Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class Incremental Learning
Considering this challenge, we propose a novel framework of fine-grained knowledge selection and restoration.
Masked Autoencoders are Efficient Class Incremental Learners
Moreover, MAEs can reliably reconstruct original input images from randomly selected patches, which we use to store exemplars from past tasks more efficiently for CIL.
Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes
Modern autonomous driving systems are typically divided into three main tasks: perception, prediction, and planning.
Ranked #1 on
Trajectory Planning
on nuScenes
SLAN: Self-Locator Aided Network for Vision-Language Understanding
By aggregating vision-language information, the region filter selects key regions and the region adaptor updates their coordinates with text guidance.
Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning
EFCIL is of interest because it mitigates concerns about privacy and long-term storage of data, while at the same time alleviating the problem of catastrophic forgetting in incremental learning.
SLAN: Self-Locator Aided Network for Cross-Modal Understanding
By aggregating cross-modal information, the region filter selects key regions and the region adaptor updates their coordinates with text guidance.
