8 citations · 16 across the 6 of their papers we have counts for
6 papers · 1 filter
POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
Antonin Vobecky, Oriane Siméoni, David Hurych +4
We describe an approach to predict open-vocabulary 3D semantic voxel occupancy map from input 2D images with the objective of enabling 3D grounding, segmentation and retrieval of f…
The Robust Semantic Segmentation UNCV2023 Challenge Results
Xuanlong Yu, Yi Zuo, Zitao Wang +34
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segment…
Improving CLIP Robustness with Knowledge Distillation and Self-Training
Clement Laroudie, Andrei Bursuc, Mai Lan Ha +1
This paper examines the robustness of a multi-modal computer vision model, CLIP (Contrastive Language-Image Pretraining), in the context of unsupervised learning. The main objectiv…
Instance-Aware Observer Network for Out-of-Distribution Object Segmentation
Victor Besnier, Andrei Bursuc, David Picard +1
Recent works on predictive uncertainty estimation have shown promising results on Out-Of-Distribution (OOD) detection for semantic segmentation. However, these methods struggle to…
Active Learning Strategies for Weakly-supervised Object Detection
Huy V. Vo, Oriane Siméoni, Spyros Gidaris +3
Object detectors trained with weak annotations are affordable alternatives to fully-supervised counterparts. However, there is still a significant performance gap between them. We…
Improving Predictive Performance and Calibration by Weight Fusion in Semantic Segmentation
Timo Sämann, Ahmed Mostafa Hammam, Andrei Bursuc +2
Averaging predictions of a deep ensemble of networks is apopular and effective method to improve predictive performance andcalibration in various benchmarks and Kaggle competitions…