GitHub - hustvl GKT: Efficient and Robust 2D-to-BEV Representation . . . We present a novel and efficient 2D-to-BEV transformation, Geometry-guided Kernel Transformer (GKT) GKT leverages geometric priors to guide the transformers to focus on discriminative regions for generating BEV representation with surrouding-view image features
GKT: A Novel Guidance-Based Knowledge Transfer Framework For Efficient . . . To address these issues, we introduce a novel and intuitive Guidance-based Knowledge Transfer (GKT) framework This approach leverages a larger LLM as a ''teacher'' to create guidance prompts, paired with a smaller ''student'' model to finalize responses