Hamed Damirchi — accepted AI-conference papers

2025

Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling

Cristian Rodriguez-Opazo, Ehsan Abbasnejad, Damien Teney, Hamed Damirchi, Edison Marrese-Taylor, Anton van den Hengel

ICLR 2025poster

Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. Various architectures, from vision transformers~(ViTs) to convolutional networks (ResNets) have been trained with CLIP to serve as general solutions to diverse vision tasks. This paper e…

Cited by 1 Source ↗PDF ↗Scholar ↗

2023

A Consistency-Based Loss for Deep Odometry Through Uncertainty Propagation

Hamed Damirchi, Roohollah Khorrambakht, Hamid D. Taghirad, Behzad Moshiri

ICRA 2023poster

Conventionally, deep odometry networks use objective functions that only penalize short-term deviations from the true path. Since such an objective does not impose any constraints on the long-term deviations from the path, a second consistency-based loss term may be added to lower long-term drift. H…

Cited by 3 Source ↗Scholar ↗