Ismail Ben Ayed

Histopath-C: Towards Realistic Domain Shifts for Histopathology Vision-Language Adaptation WACV 2026 ORION: ORthonormal Text Encoding for Universal VLM AdaptatION CVPR 2026 Revisiting Layer Normalization for Point Cloud Test Time Adaptation WACV 2026 SoC: Semantic Orthogonal Calibration for Test-Time Prompt Tuning CVPR 2026 AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples AAAI 2025 CLIPArTT: Adaptation of CLIP to New Domains at Test Time WACV 2025 Conformal Prediction for Zero-Shot Models CVPR 2025 FDS: Feedback-Guided Domain Synthesis with Multi-Source Conditional Diffusion Models for Domain Generalization WACV 2025 Few-Shot, Now for Real: Medical VLMs Adaptation without Balanced Sets or Validation MICCAI 2025 Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation WACV 2025 Purge-Gate: Backpropagation-Free Test-Time Adaptation for Point Clouds Classification via Token purging ICCV 2025 Realistic Test-Time Adaptation of Vision-Language Models CVPR 2025 Reflect: Rectified Flows for Efficient Brain Anomaly Correction Transport MICCAI 2025 Regularized Low-Rank Adaptation for Few-Shot Organ Segmentation MICCAI 2025 SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds ICML 2025 Sparsity Outperforms Low-Rank Projections in Few-Shot Adaptation ICCV 2025 Spectral Informed Mamba for Robust Point Cloud Processing CVPR 2025 Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averaging WACV 2025 Trustworthy Few-Shot Transfer of Medical VLMs through Split Conformal Prediction MICCAI 2025 UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning CVPR 2025 ViLU: Learning Vision-Language Uncertainties for Failure Prediction ICCV 2025 A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models CVPR 2024 Bag of Tricks for Fully Test-Time Adaptation WACV 2024 Boosting Vision-Language Models with Transduction NeurIPS 2024 Class and Region-Adaptive Constraints for Network Calibration MICCAI 2024 Few-shot Adaptation of Medical Vision-Language Models MICCAI 2024 LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP CVPR 2024 NC-TTT: A Noise Constrastive Approach for Test-Time Training CVPR 2024 On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning? CVPR 2024 Prompting Classes: Exploring the Power of Prompt Class Learning in Weakly Supervised Semantic Segmentation WACV 2024 Robust Calibration of Large Vision-Language Adapters ECCV 2024 Transductive Zero-Shot and Few-Shot CLIP CVPR 2024 WATT: Weight Average Test Time Adaptation of CLIP NeurIPS 2024 When is an Embedding Model More Promising than Another? NeurIPS 2024 A Strong Baseline for Generalized Few-Shot Semantic Segmentation CVPR 2023 Class Adaptive Network Calibration CVPR 2023 ClusT3: Information Invariant Test-Time Training ICCV 2023 Open-Set Likelihood Maximization for Few-Shot Learning CVPR 2023 Parametric Information Maximization for Generalized Category Discovery ICCV 2023 Proximal Splitting Adversarial Attack for Semantic Segmentation CVPR 2023 TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos WACV 2023 TTTFlow: Unsupervised Test-Time Training With Normalizing Flow WACV 2023 F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling WACV 2022 Negative Evidence Matters in Interpretable Histology Image Classification MIDL 2022 Parameter-Free Online Test-Time Adaptation CVPR 2022 The Devil Is in the Margin: Margin-Based Label Smoothing for Network Calibration CVPR 2022 Augmented Lagrangian Adversarial Attacks ICCV 2021 Beyond pixel-wise supervision for segmentation: A few global shape descriptors might be surprisingly good! MIDL 2021 Deep Active Learning for Joint Classification & Segmentation With Weak Annotator WACV 2021 Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need? CVPR 2021 Learning Data Augmentation With Online Bilevel Optimization for Image Classification WACV 2021 On the Texture Bias for Few-Shot CNN Segmentation WACV 2021 Realistic evaluation of transductive few-shot learning NeurIPS 2021 Variational Fair Clustering AAAI 2021 A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses ECCV 2020 Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision MIDL 2020 Information Maximization for Few-Shot Learning NeurIPS 2020 Laplacian Regularized Few-Shot Learning ICML 2020 On Direct Distribution Matching for Adapting Segmentation Networks MIDL 2020 Pose Guided Gated Fusion for Person Re-identification WACV 2020 Beyond Gradient Descent for Regularized Segmentation Losses CVPR 2019 Boundary loss for highly unbalanced segmentation MIDL 2019 Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses CVPR 2019 On Regularized Losses for Weakly-supervised CNN Segmentation ECCV 2018 Scalable Laplacian K-modes NeurIPS 2018 DOPE: Distributed Optimization for Pairwise Energies CVPR 2017 Secrets of GrabCut and Kernel K-Means ICCV 2015 Volumetric Bias in Segmentation and Reconstruction: Secrets and Solutions ICCV 2015 Submodularization for Binary Pairwise Energies CVPR 2014 Auxiliary Cuts for General Classes of Higher Order Functionals CVPR 2013