Search Results for author: Muhammad Maaz

Found 11 papers, 10 papers with code

On Orderings of Probability Vectors and Unsupervised Performance Estimation

1 code implementation16 Jun 2023 Muhammad Maaz, Rui Qiao, Yiheng Zhou, Renxian Zhang

We conduct numerous experiments on well-known NLP data sets and rigorously explore the performance of different score functions.

Binary Classification

SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications

2 code implementations ICCV 2023 Abdelrahman Shaker, Muhammad Maaz, Hanoona Rasheed, Salman Khan, Ming-Hsuan Yang, Fahad Shahbaz Khan

Using our proposed efficient additive attention, we build a series of models called "SwiftFormer" which achieves state-of-the-art performance in terms of both accuracy and mobile inference speed.

Fine-tuned CLIP Models are Efficient Video Learners

1 code implementation CVPR 2023 Hanoona Rasheed, Muhammad Uzair Khattak, Muhammad Maaz, Salman Khan, Fahad Shahbaz Khan

Since training on a similar scale for videos is infeasible, recent approaches focus on the effective transfer of image-based CLIP to the video domain.

MaPLe: Multi-modal Prompt Learning

2 code implementations CVPR 2023 Muhammad Uzair Khattak, Hanoona Rasheed, Muhammad Maaz, Salman Khan, Fahad Shahbaz Khan

Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks.

Prompt Engineering

EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications

7 code implementations21 Jun 2022 Muhammad Maaz, Abdelrahman Shaker, Hisham Cholakkal, Salman Khan, Syed Waqas Zamir, Rao Muhammad Anwer, Fahad Shahbaz Khan

Our EdgeNeXt model with 1. 3M parameters achieves 71. 2% top-1 accuracy on ImageNet-1K, outperforming MobileViT with an absolute gain of 2. 2% with 28% reduction in FLOPs.

Image Classification Object Detection +1

Self-Supervised Learning for Fine-Grained Visual Categorization

1 code implementation18 May 2021 Muhammad Maaz, Hanoona Abdul Rasheed, Dhanalaxmi Gaddam

The deconstruction learning forces the model to focus on local object parts, while reconstruction learning helps in learning the correlation between the parts.

Fine-Grained Visual Categorization Representation Learning +1

Viability of machine learning to reduce workload in systematic review screenings in the health sciences: a working paper

no code implementations22 Aug 2019 Muhammad Maaz

This shows that machine learning has the potential to significantly revolutionize the abstract screening process in healthcare systematic reviews.

BIG-bench Machine Learning General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.