4 papers · 1 filter
MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow Matching
Salim Khazem, Ibrahim Mohamed Serouis, Zakaria Ezzahed
Parameter-efficient adaptation of pretrained vision models is commonly performed through linear probes, prompts, low-rank updates, or lightweight residual modules. While effective,…
AdapterTune: Zero-Initialized Low-Rank Adapters for Frozen Vision Transformers
Salim Khazem
Frozen-backbone transfer with Vision Transformers faces two under-addressed issues: optimization instability when adapters are naively inserted into a fixed feature extractor, and…
Margin and Consistency Supervision for Calibrated and Robust Vision Models
Salim Khazem
Deep vision classifiers often achieve high accuracy while remaining poorly calibrated and fragile under small distribution shifts. We present Margin and Consistency Supervision (Ma…
TopoLoRA-SAM: Topology-Aware Parameter-Efficient Adaptation of Foundation Segmenters for Thin-Structure and Cross-Domain Binary Semantic Segmentation
Salim Khazem
Foundation segmentation models such as the Segment Anything Model (SAM) exhibit strong zero-shot generalization through large-scale pretraining, but adapting them to domain-specifi…