Ahmed Radwan

Ahmed Radwan

Auto-generated profile, based on publicly available information

Ahmed Radwan

The University of British Columbia

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 August 2026
Verified
Book Chapter
Closed access
PDF file
OAOmar Abdelaziz
Omar Abdelaziz
MSMahmoud Soliman
Mahmoud Soliman
ARAhmed Radwan
Ahmed Radwan
AEAhmed Elgazwy
Ahmed Elgazwy
MSMohamed S. Shehata
Mohamed S. Shehata

4 August 2026
Verified
Book Chapter
Closed access
PDF file
MSMahmoud Soliman
Mahmoud Soliman
ARAhmed Radwan
Ahmed Radwan
OAOmar Abdelaziz
Omar Abdelaziz
MSMohamed S. Shehata
Mohamed S. Shehata

8 July 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
OAOmar Abdelaziz
Omar Abdelaziz
ARAhmed Radwan
Ahmed Radwan
MSMahmoud Soliman
Mahmoud Soliman
MSMohamed S. Shehata
Mohamed S. Shehata
Deploying transformer-based single object trackers on resource-constrained devices remains challenging because adapting a pre-trained backbone conventionally requires fine-tuning on the order of 90M parameters. Parameter-Efficient Fine-Tuning (PEFT) mitigates this cost, yet existing PEFT trackers often trade tracking accuracy for efficiency. We introduce SVDTrack, a PEFT method that uses the Singular Value Decomposition (SVD) of the pre-trained attention and MLP weight matrices to decide where adaptation should occur. SVDTrack combines two targeted modifications: (1) a learnable reweighting of the singular values, S = w ⊙ Σ + b, and (2) low-rank adaptation restricted to the singular vectors associated with the least significant singular values. We show that any update confined to this residual singular subspace provably preserves the optimal rank-k approximation of the pre-trained weights—the model’s core knowledge—and we introduce a constrained Residual LoRA variant that satisfies this condition by construction, which is essential when adapting weights already fine-tuned on tracking data. After training, all learned modifications are reparameterized back into standard weight matrices, so the deployed model incurs zero additional inference latency or memory. On four benchmarks (LaSOT, LaSOText, TrackingNet, GOT-10k), SVDTrack sets a new state of the art among PEFT trackers and matches or surpasses fully fine-tuned models on several metrics, while training only 9.57M parameters—an 89.6% reduction relative to full fine-tuning. Controlled ablations show that adapting the residual subspace outperforms adapting the most significant or randomly selected components under a matched parameter budget, supporting principled, SVD-guided adaptation as a practical route to efficient, high-performance tracking on edge devices.

3 November 2026 in Computer Vision and Image Understanding
Verified
Journal Article
Closed access
MSMahmoud Soliman
Mahmoud Soliman
ARAhmed Radwan
Ahmed Radwan
OAOmar Abdelaziz
Omar Abdelaziz
AEAhmed Elgazwy
Ahmed Elgazwy
AAAhmad Abdel-Qader
Ahmad Abdel-Qader
MSMohamed S. Shehata
Mohamed S. Shehata