78 citations · 159 across the 16 of their papers we have counts for
18 papers
Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning
Muhammad Akhtar Munir, Muhammad Haris Khan, M. Saquib Sarfraz +1
Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Most current methods align domains by usi…
Generalizing Across Domains in Diabetic Retinopathy via Variational Autoencoders
Sharon Chokuwa, Muhammad H. Khan
Domain generalization for Diabetic Retinopathy (DR) classification allows a model to adeptly classify retinal images from previously unseen domains with various imaging conditions…
Unsupervised Landmark Discovery Using Consistency Guided Bottleneck
Mamona Awan, Muhammad Haris Khan, Sanoojan Baliah +4
We study a challenging problem of unsupervised discovery of object landmarks. Many recent methods rely on bottlenecks to generate 2D Gaussian heatmaps however, these are limited in…
Multiclass Alignment of Confidence and Certainty for Network Calibration
Vinith Kugathasan, Muhammad Haris Khan
Deep neural networks (DNNs) have made great strides in pushing the state-of-the-art in several challenging domains. Recent studies reveal that they are prone to making overconfiden…
Exploring the Transfer Learning Capabilities of CLIP in Domain Generalization for Diabetic Retinopathy
Sanoojan Baliah, Fadillah A. Maani, Santosh Sanjeev +1
Diabetic Retinopathy (DR), a leading cause of vision impairment, requires early detection and treatment. Developing robust AI models for DR classification holds substantial potenti…
Unsupervised Deep Graph Matching Based on Cycle Consistency
Siddharth Tourani, Carsten Rother, Muhammad Haris Khan +1
We contribute to the sparsely populated area of unsupervised deep graph matching with application to keypoint matching in images. Contrary to the standard \emph{supervised} approac…
Multiclass Confidence and Localization Calibration for Object Detection
Bimsara Pathiraja, Malitha Gunawardhana, Muhammad Haris Khan
Albeit achieving high predictive accuracy across many challenging computer vision problems, recent studies suggest that deep neural networks (DNNs) tend to make overconfident predi…
Single-branch Network for Multimodal Training
Muhammad Saad Saeed, Shah Nawaz, Muhammad Haris Khan +4
With the rapid growth of social media platforms, users are sharing billions of multimedia posts containing audio, images, and text. Researchers have focused on building autonomous…
Towards Improving Calibration in Object Detection Under Domain Shift
Muhammad Akhtar Munir, Muhammad Haris Khan, M. Saquib Sarfraz +1
With deep neural network based solution more readily being incorporated in real-world applications, it has been pressing requirement that predictions by such models, especially in…
Learning Branched Fusion and Orthogonal Projection for Face-Voice Association
Muhammad Saad Saeed, Shah Nawaz, Muhammad Haris Khan +3
Recent years have seen an increased interest in establishing association between faces and voices of celebrities leveraging audio-visual information from YouTube. Prior works adopt…
Generative Cooperative Learning for Unsupervised Video Anomaly Detection
Muhammad Zaigham Zaheer, Arif Mahmood, Muhammad Haris Khan +3
Video anomaly detection is well investigated in weakly-supervised and one-class classification (OCC) settings. However, unsupervised video anomaly detection methods are quite spars…
Fusion and Orthogonal Projection for Improved Face-Voice Association
Muhammad Saad Saeed, Muhammad Haris Khan, Shah Nawaz +2
We study the problem of learning association between face and voice, which is gaining interest in the computer vision community lately. Prior works adopt pairwise or triplet loss f…
Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection
Muhammad Akhtar Munir, Muhammad Haris Khan, M. Saquib Sarfraz +1
We study adapting trained object detectors to unseen domains manifesting significant variations of object appearance, viewpoints and backgrounds. Most current methods align domains…
Deep Contextual Attention for Human-Object Interaction Detection
Tiancai Wang, Rao Muhammad Anwer, Muhammad Haris Khan +4
Human-object interaction detection is an important and relatively new class of visual relationship detection tasks, essential for deeper scene understanding. Most existing approach…
Mask-Guided Attention Network for Occluded Pedestrian Detection
Yanwei Pang, Jin Xie, Muhammad Haris Khan +3
Pedestrian detection relying on deep convolution neural networks has made significant progress. Though promising results have been achieved on standard pedestrians, the performance…
AnimalWeb: A Large-Scale Hierarchical Dataset of Annotated Animal Faces
Muhammad Haris Khan, John McDonagh, Salman Khan +5
Being heavily reliant on animals, it is our ethical obligation to improve their well-being by understanding their needs. Several studies show that animal needs are often expressed…
Cross-Domain Transferability of Adversarial Perturbations
Muzammal Naseer, Salman H. Khan, Harris Khan +2
Adversarial examples reveal the blind spots of deep neural networks (DNNs) and represent a major concern for security-critical applications. The transferability of adversarial exam…
Pushing the boundaries of audiovisual word recognition using Residual Networks and LSTMs
Themos Stafylakis, Muhammad Haris Khan, Georgios Tzimiropoulos
Visual and audiovisual speech recognition are witnessing a renaissance which is largely due to the advent of deep learning methods. In this paper, we present a deep learning archit…