2 papers
cs.CV2025
RT-DETRv2 Explained in 8 Illustrations
Ethan Qi Yang Chua, Jen Hong Tan
Object detection architectures are notoriously difficult to understand, often more so than large language models. While RT-DETRv2 represents an important advance in real-time detec…
cs.CV2024
How Lightweight Can A Vision Transformer Be
Jen Hong Tan
In this paper, we explore a strategy that uses Mixture-of-Experts (MoE) to streamline, rather than augment, vision transformers. Each expert in an MoE layer is a SwiGLU feedforward…