🏢 University of Melbourne
Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers
·3763 words·18 mins·
loading
·
loading
AI Generated
Computer Vision
Image Classification
🏢 University of Melbourne
BiXT, a novel bi-directional cross-attention Transformer, scales linearly with input size, achieving competitive performance across various tasks by efficiently processing longer sequences.
In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment
·2437 words·12 mins·
loading
·
loading
Computer Vision
3D Vision
🏢 University of Melbourne
In-N-Out: Lifting 2D Diffusion Priors for 3D Object Removal via Tuning-Free Latents Alignment enhances 3D scene reconstruction by aligning 2D diffusion model latents for consistent multi-view inpainti…
Bayesian-guided Label Mapping for Visual Reprogramming
·3607 words·17 mins·
loading
·
loading
Transfer Learning
🏢 University of Melbourne
Bayesian-guided Label Mapping (BLM) enhances visual reprogramming!