Unlike cloud-based deep learning models that are often large and uniform...
Optical Music Recognition (OMR) is an important technology in music and ...
Novel Class Discovery (NCD) aims at inferring novel classes in an unlabe...
Out-of-Distribution (OOD) detection is critical for the reliable operati...
Modern machine learning models deployed in the wild can encounter both
c...
Recent large vision-language models such as CLIP have shown remarkable
o...
Syntax-guided synthesis is a paradigm in program synthesis in which the
...
Out-of-distribution (OOD) detection is a critical task for reliable
pred...
Out-of-distribution (OOD) detection is essential for the reliable and sa...
This work studies the generalization issue of face anti-spoofing (FAS) m...
Modern machine learning models may be susceptible to learning spurious
c...
Out-of-distribution (OOD) detection is indispensable for safely deployin...
Place recognition is an important technique for autonomous cars to achie...
Place recognition is a key module for long-term SLAM systems. Current
Li...
In the presence of noisy labels, designing robust loss functions is crit...
Recognizing out-of-distribution (OOD) samples is critical for machine
le...
Supervised learning aims to train a classifier under the assumption that...
Out-of-distribution (OOD) detection is vital to safety-critical machine
...
Strong static type systems help programmers eliminate many errors withou...
Autoregressive language models, which use deep learning to produce human...
Modern deep generative models can assign high likelihood to inputs drawn...
Recent advance in contrastive learning has shown remarkable performance....
Despite the recent advances in out-of-distribution(OOD) detection, anoma...
Out-of-distribution (OOD) detection is indispensable for machine learnin...
Detecting out-of-distribution inputs is critical for safe deployment of
...
Out-of-distribution (OOD) detection is a critical task for deploying mac...
Deep neural networks may be susceptible to learning spurious correlation...
Out-of-distribution (OOD) detection is a critical task for reliable mach...
Building reliable object detectors that can detect out-of-distribution (...
Out-of-distribution (OOD) detection is important for machine learning mo...
Out-of-distribution (OOD) detection has received much attention lately d...
Image inpainting approaches have achieved significant progress with the ...
Partial label learning (PLL) is an important problem that allows each
tr...
Out-of-distribution (OOD) detection is important for deploying machine
l...
Out-of-distribution (OOD) detection has received much attention lately d...
Detecting out-of-distribution (OOD) inputs is a central challenge for sa...
Machine learning models often encounter samples that are diverged from t...
Out-of-distribution (OOD) detection is critical to ensuring the reliabil...
Despite the impressive performance of deep networks in vision, language,...
Detecting out-of-distribution (OOD) data has become a critical component...
Estimating out-of-distribution (OOD) uncertainty is a central challenge ...
Modern neural networks can assign high confidence to inputs drawn from
o...
Spatio-temporal action detection is an important and challenging problem...
Detecting out-of-distribution (OOD) inputs is a central challenge for sa...
Out-of-distribution (OOD) detection is essential to prevent anomalous in...
Determining whether inputs are out-of-distribution (OOD) is an essential...
Classifiers in machine learning are often brittle when deployed. Particu...
We present a multi-agent actor-critic method that aims to implicitly add...
The existing action tubelet detectors mainly depend on heuristic anchor ...
A plethora of recent work has shown that convolutional networks are not
...