Generalized out-of-distribution detection: A survey
Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of machine
learning systems. For instance, in autonomous driving, we would like the driving system to …
learning systems. For instance, in autonomous driving, we would like the driving system to …
Energy-based out-of-distribution detection
Determining whether inputs are out-of-distribution (OOD) is an essential building block for
safely deploying machine learning models in the open world. However, previous methods …
safely deploying machine learning models in the open world. However, previous methods …
React: Out-of-distribution detection with rectified activations
Out-of-distribution (OOD) detection has received much attention lately due to its practical
importance in enhancing the safe deployment of neural networks. One of the primary …
importance in enhancing the safe deployment of neural networks. One of the primary …
Enhancing the reliability of out-of-distribution image detection in neural networks
We consider the problem of detecting out-of-distribution images in neural networks. We
propose ODIN, a simple and effective method that does not require any change to a pre-trained …
propose ODIN, a simple and effective method that does not require any change to a pre-trained …
Convergent learning: Do different neural networks learn the same representations?
Recent success in training deep neural networks have prompted active investigation into the
features learned on their intermediate layers. Such research is difficult because it requires …
features learned on their intermediate layers. Such research is difficult because it requires …
[HTML][HTML] Deep learning in optical metrology: a review
With the advances in scientific foundations and technological implementations, optical
metrology has become versatile problem-solving backbones in manufacturing, fundamental …
metrology has become versatile problem-solving backbones in manufacturing, fundamental …
Out-of-distribution detection with deep nearest neighbors
Out-of-distribution (OOD) detection is a critical task for deploying machine learning models
in the open world. Distance-based methods have demonstrated promise, where testing …
in the open world. Distance-based methods have demonstrated promise, where testing …
HDACs and HDAC inhibitors in cancer development and therapy
Over the last several decades, it has become clear that epigenetic abnormalities may be
one of the hallmarks of cancer. Posttranslational modifications of histones, for example, may …
one of the hallmarks of cancer. Posttranslational modifications of histones, for example, may …
Exploring the limits of weakly supervised pretraining
State-of-the-art visual perception models for a wide range of tasks rely on supervised pretraining.
ImageNet classification is the de facto pretraining task for these models. Yet, ImageNet …
ImageNet classification is the de facto pretraining task for these models. Yet, ImageNet …
[PDF][PDF] Deep-learning-enabled dual-frequency composite fringe projection profilometry for single-shot absolute 3D shape measurement
Single-shot high-speed 3D imaging is important for reconstructions of dynamic objects. For
fringe projection profilometry (FPP), however, it is still challenging to recover accurate 3D …
fringe projection profilometry (FPP), however, it is still challenging to recover accurate 3D …