Search Results for author: Anas Mahmoud

Found 7 papers, 3 papers with code

Image-to-Lidar Relational Distillation for Autonomous Driving Data

no code implementations1 Sep 2024 Anas Mahmoud, Ali Harakeh, Steven Waslander

To bridge this gap, we propose a relational distillation framework enforcing intra-modal and cross-modal constraints, resulting in distilled 3D representations that closely capture the structure of the 2D representation.

3D Semantic Segmentation Autonomous Driving +3

Sieve: Multimodal Dataset Pruning Using Image Captioning Models

1 code implementation CVPR 2024 Anas Mahmoud, Mostafa Elhoushi, Amro Abbas, Yu Yang, Newsha Ardalani, Hugh Leather, Ari Morcos

We propose a pruning signal, Sieve, that employs synthetic captions generated by image-captioning models pretrained on small, diverse, and well-aligned image-text pairs to evaluate the alignment of noisy image-text pairs.

Diversity Image Captioning +2

Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss

1 code implementation CVPR 2023 Anas Mahmoud, Jordan S. K. Hu, Tianshu Kuai, Ali Harakeh, Liam Paull, Steven L. Waslander

However, image-to point representation learning for autonomous driving datasets faces two main challenges: 1) the abundance of self-similarity, which results in the contrastive losses pushing away semantically similar point and image regions and thus disturbing the local semantic structure of the learned representations, and 2) severe class imbalance as pretraining gets dominated by over-represented classes.

3D Semantic Segmentation Autonomous Driving +4

Dense Voxel Fusion for 3D Object Detection

no code implementations2 Mar 2022 Anas Mahmoud, Jordan S. K. Hu, Steven L. Waslander

Sequential fusion methods suffer from a limited number of pixel and point correspondences due to point cloud sparsity, or their performance is strictly capped by the detections of one of the modalities.

3D Object Detection Object +1

Cannot find the paper you are looking for? You can Submit a new open access paper.