He, K. and Dollar, P. (2017) Focal Loss for Dense Object Detection. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 2980-2988.

Transfer learning with a graph attention network and weighted loss function provides a high-throughput method for identifying PBMT chemicals with high reliability and broad applicability domains.

Hi, I recently upgraded from Keras 2 to Keras 3 and noticed some strange behavior when using a custom loss function with model.fit (). The model trains without throwing any errors, but the loss values ...

Loss functions measure algorithmic errors in artificial-intelligence models, but there’s more than one way to do that. Here’s why the right function is so important.

Learn about the advantages and disadvantages of cross-entropy, IoU, focal loss, and GIoU for object detection in deep learning.

The obtained embeddings as pattern vectors/tensors permit us an accelerated but non-parametric visual similarity computation as the decision rule for final detection. Our approach to few-shot object ...

The Dice loss function is widely used to train deep learning algorithms in medical segmentation tasks. However, in multi-class segmentation tasks, the Dice loss function can result in imbalanced ...