Goto

Collaborating Authors

 ieee


Learning Conditional Deformable Templates with Convolutional Networks

Adrian Dalca, Marianne Rakic, John Guttag, Mert Sabuncu

Neural Information Processing Systems

In these frameworks, templates are constructed using an iterative process of template estimation and alignment, which is often computationally very expensive. Due in part to this shortcoming, most methods compute asingle template for the entire population of images, or a few templates for specific sub-groups of the data.






A Training Objectives Our model is trained from scratch with the semantic loss L

Neural Information Processing Systems

The computational overhead of CluB is 1.2 / 1.3 times that of the BEV -only A detailed comparison is shown in the following table. GPUs and the batch size per GPU is set as 2. Table 2: Ablation study on the effect of the two kinds of object queries for the transformer decoder. Red boxes and green boxes are the predictions and ground-truth, respectively. Transfusion: Robust lidar-camera fusion for 3d object detection with transformers. Fully sparse 3d object detection.




Estimators for Multivariate Information Measures in General Probability Spaces

Arman Rahimzamani, Himanshu Asnani, Pramod Viswanath, Sreeram Kannan

Neural Information Processing Systems

A key quantity of interest is the mutual information and generalizations thereof, including conditional mutual information, multivariate mutual information, total correlation and directed information.