18 citations · 38 across the 10 of their papers we have counts for
11 papers
TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation
Muhammad Sohail Danish, Muhammad Akhtar Munir, Syed Roshaan Ali Shah +5
Modern Earth observation (EO) increasingly leverages deep learning to harness the scale and diversity of satellite imagery across sensors and regions. While recent foundation model…
O-TPT: Orthogonality Constraints for Calibrating Test-time Prompt Tuning in Vision-Language Models
Ashshak Sharifdeen, Muhammad Akhtar Munir, Sanoojan Baliah +2
Test-time prompt tuning for vision-language models (VLMs) is getting attention because of their ability to learn with unlabeled data without fine-tuning. Although test-time prompt…
Cal-DETR: Calibrated Detection Transformer
Muhammad Akhtar Munir, Salman Khan, Muhammad Haris Khan +2
Albeit revealing impressive predictive performance for several computer vision tasks, deep neural networks (DNNs) are prone to making overconfident predictions. This limits the ado…
Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection
Muhammad Akhtar Munir, Muhammad Haris Khan, Salman Khan +1
Deep neural networks (DNNs) have enabled astounding progress in several vision-based problems. Despite showing high predictive accuracy, recently, several works have revealed that…
MSI: Maximize Support-Set Information for Few-Shot Segmentation
Seonghyeon Moon, Samuel S. Sohn, Honglu Zhou +4
FSS(Few-shot segmentation) aims to segment a target class using a small number of labeled images(support set). To extract information relevant to the target class, a dominant appro…
Self-Distilled Vision Transformer for Domain Generalization
Maryam Sultana, Muzammal Naseer, Muhammad Haris Khan +2
In the recent past, several domain generalization (DG) methods have been proposed, showing encouraging performance, however, almost all of them build on convolutional neural networ…
Video Instance Segmentation via Multi-scale Spatio-temporal Split Attention Transformer
Omkar Thawakar, Sanath Narayan, Jiale Cao +6
State-of-the-art transformer-based video instance segmentation (VIS) approaches typically utilize either single-scale spatio-temporal features or per-frame multi-scale features dur…
HM: Hybrid Masking for Few-Shot Segmentation
Seonghyeon Moon, Samuel S. Sohn, Honglu Zhou +4
We study few-shot semantic segmentation that aims to segment a target object from a query image when provided with a few annotated support images of the target class. Several recen…
Transformers in Medical Imaging: A Survey
Fahad Shamshad, Salman Khan, Syed Waqas Zamir +4
Following unprecedented success on the natural language tasks, Transformers have been successfully applied to several computer vision problems, achieving state-of-the-art results a…
Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook
Sajid Javed, Martin Danelljan, Fahad Shahbaz Khan +3
Accurate and robust visual object tracking is one of the most challenging and fundamental computer vision problems. It entails estimating the trajectory of the target in an image s…
Rich Semantics Improve Few-shot Learning
Mohamed Afham, Salman Khan, Muhammad Haris Khan +2
Human learning benefits from multi-modal inputs that often appear as rich semantics (e.g., description of an object's attributes while learning about it). This enables us to learn…