activity
20172023
most citedFoundational Models Defining a New Era in Vision: A Survey and Outlook

68 citations · 131 across the 14 of their papers we have counts for

collaborators
Showing 2021 · cs.CVShow all

5 papers · 2 filters

cs.CV2021

MC-SSL0.0: Towards Multi-Concept Self-Supervised Learning

Sara Atito, Muhammad Awais, Ammarah Farooq +2

Self-supervised pretraining is the method of choice for natural language processing models and is rapidly gaining popularity in many vision tasks. Recently, self-supervised pretrai…

cs.CV2021

Global Interaction Modelling in Vision Transformer via Super Tokens

Ammarah Farooq, Muhammad Awais, Sara Ahmed +1

With the popularity of Transformer architectures in computer vision, the research focus has shifted towards developing computationally efficient designs. Window-based local attenti…

cs.CV2021

SiT: Self-supervised vIsion Transformer

Sara Atito, Muhammad Awais, Josef Kittler

Self-supervised learning methods are gaining increasing traction in computer vision due to their recent success in reducing the gap with supervised learning. In natural language pr…

cs.CV2021★ 7 cited

NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition

Syed Safwan Khalid, Muhammad Awais, Chi-Ho Chan +4

Face recognition (FR) using deep convolutional neural networks (DCNNs) has seen remarkable success in recent years. One key ingredient of DCNN-based FR is the appropriate design of…

cs.CV2021

AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification

Ammarah Farooq, Muhammad Awais, Josef Kittler +1

Cross-modal person re-identification (Re-ID) is critical for modern video surveillance systems. The key challenge is to align cross-modality representations induced by the semantic…