Future Interaction @ Samsung AI Center Cambridge

edgevit

[ECCV 2022] EdgeViT: Competing Light-weight CNNs on Mobile Devices with Vision Transformers

Bayesian-Prompt-Learning

[ICCV 2023] Bayesian Prompt Learning for Image-Language Model Generalization

LFA

[ICCV 2023] Black Box Few-Shot Adaptation for Vision-Language models

xvit_video_transformers

[NeurIPS 2021] Space-time Mixing Attention for Video Transformer

SSLight

[ICLR'23] Effective Self-supervised Pre-training on Low-compute networks without Distillation

lofi_action_localization

[NeurIPS 2021] Low-Fidelity Video Encoder Optimization for Temporal Action Localization

.github