Zoom-shot: Fast and Efficient Unsupervised Zero-Shot Transfer of CLIP to Vision Encoders with Multimodal Loss

no code implementations • 22 Jan 2024 • Jordan Shipard, Arnold Wiliem, Kien Nguyen Thanh, Wei Xiang, Clinton Fookes

To address this issue, we propose Zoom-shot, a novel method for transferring the zero-shot capabilities of CLIP to any pre-trained vision encoder.

Knowledge Distillation Zero-Shot Learning

Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusion

1 code implementation • 7 Feb 2023 • Jordan Shipard, Arnold Wiliem, Kien Nguyen Thanh, Wei Xiang, Clinton Fookes

In this work, we investigate the problem of Model-Agnostic Zero-Shot Classification (MA-ZSC), which refers to training non-specific classification architectures (downstream models) to classify real images without using any real images during training.

Classification Diversity +2

Im2Mesh GAN: Accurate 3D Hand Mesh Recovery from a Single RGB Image

no code implementations • 27 Jan 2021 • Akila Pemasiri, Kien Nguyen Thanh, Sridha Sridharan, Clinton Fookes

This work addresses hand mesh recovery from a single RGB image.