106 citations · 213 across the 42 of their papers we have counts for
47 papers
Hierarchical Prompt Learning for Hyperbolic Vision-Language Models
Andro Erdelez, Pascal Mettes, Behzad Bozorgtabar
Hyperbolic vision-language models (VLMs) represent image and text features in a geometry naturally suited to hierarchy, but their adaptation to downstream tasks has largely relied…
EnTrust: Modeling Inter-Modal Conflict for Trustworthy Multimodal Medical Image Analysis
Dwarikanath Mahapatra, Abhijit Das, Behzad Bozorgtabar +5
Multimodal medical imaging fuses complementary anatomical and functional information, yet modalities frequently disagree in pathologically heterogeneous regions. Current segmentati…
Scalable Training of Spatially Grounded 2D Vision-Language Models for Radiology
Yusuf Salcan, Simon Ging, Robin Tibor Schirrmeister +4
We study how to train visually grounded vision-language models (VLMs) for radiology without manual spatial annotations. We introduce RefRad2D, a large-scale bilingual (German/Engli…
Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance
Tianming Du, Peijie Yu, Sihan Shang +12
The most plausible near-term role of medical LLMs is to assist rather than replace physicians, yet current evaluations often test isolated capabilities: clinical knowledge, EHR sys…
VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs
Govinda Kolli, Adinath Madhavrao Dukre, Behzad Bozorgtabar +2
Medical Vision-Language Models (VLMs) often hallucinate by generating responses based on language priors rather than visual evidence, posing risks in clinical applications. We prop…
Refining 3D Medical Segmentation with Verbal Instruction
Kangxian Xie, Jiancheng Yang, Nandor Pinter +3
Accurate 3D anatomical segmentation is essential for clinical diagnosis and surgical planning. However, automated models frequently generate suboptimal shape predictions due to fac…
Learning to Read Where to Look: Disease-Aware Vision-Language Pretraining for 3D CT
Simon Ging, Philipp Arnold, Sebastian Walter +6
Recent 3D CT vision-language models align volumes with reports via contrastive pretraining, but typically rely on limited public data and provide only coarse global supervision. We…
LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs
Behzad Bozorgtabar, Dwarikanath Mahapatra, Sudipta Roy +3
Medical vision-language models (VLMs) are strong zero-shot recognizers for medical imaging, but their reliability under domain shift hinges on calibrated uncertainty with guarantee…
Positive Semi-definite Latent Factor Grouping-Boosted Cluster-reasoning Instance Disentangled Learning for WSI Representation
Chentao Li, Behzad Bozorgtabar, Yifang Ping +2
Multiple instance learning (MIL) has been widely used for representing whole-slide pathology images. However, spatial, semantic, and decision entanglements among instances limit it…
MuGa-VTON: Multi-Garment Virtual Try-On via Diffusion Transformers with Prompt Customization
Ankan Deria, Dwarikanath Mahapatra, Behzad Bozorgtabar +3
Virtual try-on seeks to generate photorealistic images of individuals in desired garments, a task that must simultaneously preserve personal identity and garment fidelity for pract…
ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
Guillaume Vray, Devavrat Tomar, Xufeng Gao +3
This paper introduces ReservoirTTA, a novel plug-in framework designed for prolonged test-time adaptation (TTA) in scenarios where the test domain continuously shifts over time, in…
Slide-Level Prompt Learning with Vision Language Models for Few-Shot Multiple Instance Learning in Histopathology
Devavrat Tomar, Guillaume Vray, Dwarikanath Mahapatra +3
In this paper, we address the challenge of few-shot classification in histopathology whole slide images (WSIs) by utilizing foundational vision-language models (VLMs) and slide-lev…
A Simple Framework for Open-Vocabulary Zero-Shot Segmentation
Thomas Stegmüller, Tim Lebailly, Nikola Dukic +3
Zero-shot classification capabilities naturally arise in models trained within a vision-language contrastive framework. Despite their classification prowess, these models struggle…
Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation
Devavrat Tomar, Guillaume Vray, Jean-Philippe Thiran +1
Recent test-time adaptation methods heavily rely on nuanced adjustments of batch normalization (BN) parameters. However, one critical assumption often goes overlooked: that of inde…
CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping
Tim Lebailly, Thomas Stegmüller, Behzad Bozorgtabar +2
Leveraging nearest neighbor retrieval for self-supervised representation learning has proven beneficial with object-centric images. However, this approach faces limitations when ap…
AMAE: Adaptation of Pre-Trained Masked Autoencoder for Dual-Distribution Anomaly Detection in Chest X-Rays
Behzad Bozorgtabar, Dwarikanath Mahapatra, Jean-Philippe Thiran
Unsupervised anomaly detection in medical images such as chest radiographs is stepping into the spotlight as it mitigates the scarcity of the labor-intensive and costly expert anno…
Distill-SODA: Distilling Self-Supervised Vision Transformer for Source-Free Open-Set Domain Adaptation in Computational Pathology
Guillaume Vray, Devavrat Tomar, Jean-Philippe Thiran +1
Developing computational pathology models is essential for reducing manual tissue typing from whole slide images, transferring knowledge from the source domain to an unlabeled, shi…
CrOC: Cross-View Online Clustering for Dense Visual Representation Learning
Thomas Stegmüller, Tim Lebailly, Behzad Bozorgtabar +2
Learning dense visual representations without labels is an arduous task and more so from scene-centric data. We propose to tackle this challenging problem by proposing a Cross-view…
TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation
Devavrat Tomar, Guillaume Vray, Behzad Bozorgtabar +1
Most recent test-time adaptation methods focus on only classification tasks, use specialized network architectures, destroy model calibration or rely on lightweight information fro…
Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learning
Tim Lebailly, Thomas Stegmüller, Behzad Bozorgtabar +2
Most self-supervised methods for representation learning leverage a cross-view consistency objective i.e., they maximize the representation similarity of a given image's augmented…
Self-supervised learning-based cervical cytology for the triage of HPV-positive women in resource-limited settings and low-data regime
Thomas Stegmüller, Christian Abbet, Behzad Bozorgtabar +4
Screening Papanicolaou test samples has proven to be highly effective in reducing cervical cancer-related mortality. However, the lack of trained cytopathologists hinders its wides…
Weakly Supervised Joint Whole-Slide Segmentation and Classification in Prostate Cancer
Pushpak Pati, Guillaume Jaume, Zeineb Ayadi +4
The segmentation and automatic identification of histological regions of diagnostic interest offer a valuable aid to pathologists. However, segmentation methods are hampered by the…
Unsupervised Domain Adaptation Using Feature Disentanglement And GCNs For Medical Image Classification
Dwarikanath Mahapatra
The success of deep learning has set new benchmarks for many medical image analysis tasks. However, deep models often fail to generalize in the presence of distribution shifts betw…
ScoreNet: Learning Non-Uniform Attention and Augmentation for Transformer-Based Histopathological Image Classification
Thomas Stegmüller, Behzad Bozorgtabar, Antoine Spahr +1
Progress in digital pathology is hindered by high-resolution images and the prohibitive cost of exhaustive localized annotations. The commonly used paradigm to categorize pathology…