Detecting and classifying vehicles as objects from images and videos is challenging in
appearance-based representation, yet plays a significant role in the substantial real-time …

Bounding box (bbox) regression is a fundamental task in computer vision. So far, the most
commonly used loss functions for bbox regression are the Intersection over Union (IoU) loss …

Abstract Mixed-Precision Quantization (MQ) can achieve a competitive accuracy-complexity
trade-off for models. Conventional training-based search methods require time-consuming …

Few-shot object detection, the problem of modelling novel object detection categories with
few training instances, is an emerging topic in the area of few-shot learning and object …

Unsupervised domain adaption (UDA) aims to reduce the domain gap between labeled
source and unlabeled target domains. Many prior works exploit adversarial learning that …

Abstract We propose Rank & Sort (RS) Loss, a ranking-based loss function to train deep
object detection and instance segmentation methods (ie visual detectors). RS Loss …

Person re-identification is a hot topic in computer vision, and the loss function plays a vital
role in improving the discrimination of the learned features. However, most existing models …

Generalising robustly to distribution shift is a major challenge that is pervasive across most
real-world applications of machine learning. A recent study highlighted that many advanced …

Significant progress has been achieved in automating the design of various components in
deep networks. However, the automatic design of loss functions for generic tasks with …

In recommendation systems, the choice of loss function is critical since a good loss may
significantly improve the model performance. However, manually designing a good loss is a …