[PDF][PDF] Deep unsupervised domain adaptation: A review of recent advances and perspectives
Deep learning has become the method of choice to tackle real-world problems in different
domains, partly because of its ability to learn from data and achieve impressive performance …
domains, partly because of its ability to learn from data and achieve impressive performance …
Recent advances in optimal transport for machine learning
Recently, Optimal Transport has been proposed as a probabilistic framework in Machine
Learning for comparing and manipulating probability distributions. This is rooted in its rich …
Learning for comparing and manipulating probability distributions. This is rooted in its rich …
Freemask: Synthetic images with dense annotations make stronger segmentation models
Semantic segmentation has witnessed tremendous progress due to the proposal of various
advanced network architectures. However, they are extremely hungry for delicate …
advanced network architectures. However, they are extremely hungry for delicate …
Deep verifier networks: Verification of deep discriminative models with deep generative models
AI Safety is a major concern in many deep learning applications such as autonomous
driving. Given a trained deep learning model, an important natural problem is how to reliably …
driving. Given a trained deep learning model, an important natural problem is how to reliably …
Only a few classes confusing: Pixel-wise candidate labels disambiguation for foggy scene understanding
Not all semantics become confusing when deploying a semantic segmentation model for
real-world scene understanding of adverse weather. The true semantics of most pixels have …
real-world scene understanding of adverse weather. The true semantics of most pixels have …
Classification-aware semi-supervised domain adaptation
Deep neural networks are usually data-starved, but manually annotation can be costly in
many specific tasks. For instance, the emotion recognition from the audio. However, there is …
many specific tasks. For instance, the emotion recognition from the audio. However, there is …
Exploiting shape cues for weakly supervised semantic segmentation
Weakly supervised semantic segmentation (WSSS) aims to produce pixel-wise class
predictions with only image-level labels for training. To this end, previous methods adopt the …
predictions with only image-level labels for training. To this end, previous methods adopt the …
[HTML][HTML] Improving semantic segmentation of urban scenes for self-driving cars with synthetic images
Semantic segmentation of an incoming visual stream from cameras is an essential part of
the perception system of self-driving cars. State-of-the-art results in semantic segmentation …
the perception system of self-driving cars. State-of-the-art results in semantic segmentation …
Meta optimal transport
We study the use of amortized optimization to predict optimal transport (OT) maps from the
input measures, which we call Meta OT. This helps repeatedly solve similar OT problems …
input measures, which we call Meta OT. This helps repeatedly solve similar OT problems …
Recursively conditional gaussian for ordinal unsupervised domain adaptation
The unsupervised domain adaptation (UDA) has been widely adopted to alleviate the data
scalability issue, while the existing works usually focus on classifying independently discrete …
scalability issue, while the existing works usually focus on classifying independently discrete …