PROJECTS
Here are the updated list of research projects conducted by our researchers.
HAHANet: Towards Accurate Image Classifiers with Less Parameters
Arren Matthew C. Antioquia, Macario Cordel II
We propose an efficient convolutional block which minimizes the computational requirements of a network. Our approach achieves state-of-the-art accuracy on several challenging fine-grained classification tasks. More importantly, HAHANet outperforms top networks while reducing parameter count by at most 54 times.