Munawar Hayat

Ar2Can: An Architect and an Artist Leveraging a Canvas for Multi-Human Generation CVPR 2026 DEVA: Fine-tuning Multimodal Large Language Models for Visual Perception Tasks CVPR 2026 Memory-Efficient Fine-Tuning Diffusion Transformers via Dynamic Patch Sampling and Block Skipping CVPR 2026 Resolving the Identity Crisis in Text-to-Image Generation CVPR 2026 ConsNoTrainLoRA: Data-driven Weight Initialization of Low-rank Adapters using Constraints ICCV 2025 CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation CVPR 2025 DuoLoRA : Cycle-consistent and Rank-disentangled Content-Style Personalization ICCV 2025 Erasing Undesirable Influence in Diffusion Models CVPR 2025 HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories CVPR 2025 Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning CVPR 2025 Understanding Personal Concept in Open-Vocabulary Semantic Segmentation ICCV 2025 Concealing Sensitive Samples against Gradient Leakage in Federated Learning AAAI 2024 FouRA: Fourier Low-Rank Adaptation NeurIPS 2024 OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation CVPR 2024 Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training CVPR 2023 Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation ICCV 2023 Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation CVPR 2023 LAVA: Label-Efficient Visual Learning and Adaptation WACV 2023 MARLIN: Masked Autoencoder for Facial Video Representation LearnINg CVPR 2023 ProtoCon: Pseudo-Label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-Supervised Learning CVPR 2023 Transformer Scale Gate for Semantic Segmentation CVPR 2023 Zero-Shot Point Cloud Segmentation by Semantic-Visual Aware Synthesis ICCV 2023 Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds CVPR 2022 MTGLS: Multi-Task Gaze Estimation With Limited Supervision WACV 2022 ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues CVPR 2022 Restormer: Efficient Transformer for High-Resolution Image Restoration CVPR 2022 Semantic-Aware Domain Generalized Segmentation CVPR 2022 Towards Robust and Reproducible Active Learning Using Neural Networks CVPR 2022 D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations ICCV 2021 Intriguing Properties of Vision Transformers NeurIPS 2021 Multi-Stage Progressive Image Restoration CVPR 2021 On Generating Transferable Targeted Perturbations ICCV 2021 Orthogonal Projection Loss ICCV 2021 A Self-supervised Approach for Adversarial Robustness CVPR 2020 CycleISP: Real Image Restoration via Improved Data Synthesis CVPR 2020 iTAML: An Incremental Task-Agnostic Meta-learning Approach CVPR 2020 Learning Enriched Features for Real Image Restoration and Enhancement ECCV 2020 Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks ICCV 2019 Gaussian Affinity for Max-Margin Class Imbalanced Learning ICCV 2019 Random Path Selection for Continual Learning NeurIPS 2019 Striking the Right Balance With Uncertainty CVPR 2019 Unsupervised Primitive Discovery for Improved 3D Generative Modeling CVPR 2019 Joint Registration and Representation Learning for Unconstrained Face Identification CVPR 2017 Scene Categorization With Spectral Features ICCV 2017 Contractive Rectifier Networks for Nonlinear Maximum Margin Classification ICCV 2015 Learning Non-Linear Reconstruction Models for Image Set Classification CVPR 2014