Inverse Compositional Spatial Transformer Networks
In this paper, we establish a theoretical connection between the classical Lucas & Kanade (LK) algorithm and the emerging topic of Spatial Transformer Networks (STNs). STNs are of interest to the vision and learning communities due to their natural ability to combine alignment and classification within the same theoretical framework. Inspired by the Inverse Compositional (IC) variant of the LK algorithm, we present Inverse Compositional Spatial Transformer Networks (IC-STNs). We demonstrate that IC-STNs can achieve better performance than conventional STNs with less model capacity; in particular, we show superior performance in pure image alignment tasks as well as joint alignment/classification problems on real-world problems.
https://arxiv.org/abs/1612.03897
#arxiv #dl #cv
In this paper, we establish a theoretical connection between the classical Lucas & Kanade (LK) algorithm and the emerging topic of Spatial Transformer Networks (STNs). STNs are of interest to the vision and learning communities due to their natural ability to combine alignment and classification within the same theoretical framework. Inspired by the Inverse Compositional (IC) variant of the LK algorithm, we present Inverse Compositional Spatial Transformer Networks (IC-STNs). We demonstrate that IC-STNs can achieve better performance than conventional STNs with less model capacity; in particular, we show superior performance in pure image alignment tasks as well as joint alignment/classification problems on real-world problems.
https://arxiv.org/abs/1612.03897
#arxiv #dl #cv
Karpathy on ML trends for last 5 years:
https://medium.com/@karpathy/a-peek-at-trends-in-machine-learning-ab8a1085a106
#meta #arxiv
https://medium.com/@karpathy/a-peek-at-trends-in-machine-learning-ab8a1085a106
#meta #arxiv
Medium
A Peek at Trends in Machine Learning
Have you looked at Google Trends? It’s pretty cool — you enter some keywords and see how Google Searches of that term vary through time. I…
Google has set up a new milestone for speech generation: "Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model"
You can listen to generated samples at: https://google.github.io/tacotron/
Paper: https://arxiv.org/abs/1703.10135
#audio #arxiv #google #breakthrough #generative
You can listen to generated samples at: https://google.github.io/tacotron/
Paper: https://arxiv.org/abs/1703.10135
#audio #arxiv #google #breakthrough #generative
arXiv.org
Tacotron: Towards End-to-End Speech Synthesis
A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires...
Comparison of 13 classic ML algorithms on 165 datasets.
https://arxiv.org/pdf/1708.05070.pdf
#meta #arxiv #ml
https://arxiv.org/pdf/1708.05070.pdf
#meta #arxiv #ml
«Efficient Neural Architecture Search via Parameters Sharing»
Authors reduced the computational requirement (GPU-hrs) of standard Neural Architecture Search by 1000x via parameter sharing between models that are subgraphs within a large computational graph. ENAS achieves SOTA on PTB language modeling among all methods without post-training processing and strong performance on CIFAR-10.
Link: https://arxiv.org/pdf/1802.03268.pdf
#arxiv #optimization #neuralnetworks
Authors reduced the computational requirement (GPU-hrs) of standard Neural Architecture Search by 1000x via parameter sharing between models that are subgraphs within a large computational graph. ENAS achieves SOTA on PTB language modeling among all methods without post-training processing and strong performance on CIFAR-10.
Link: https://arxiv.org/pdf/1802.03268.pdf
#arxiv #optimization #neuralnetworks
Neural Voice Cloning with a Few Samples
Paper behind Baidu's Neural Voice Cloning with Few samples: http://research.baidu.com/neural-voice-cloning-samples/
Arxiv: https://arxiv.org/abs/1802.06006
#arxiv #baidu #neuralnetworks #voice #sound #dl
Paper behind Baidu's Neural Voice Cloning with Few samples: http://research.baidu.com/neural-voice-cloning-samples/
Arxiv: https://arxiv.org/abs/1802.06006
#arxiv #baidu #neuralnetworks #voice #sound #dl
Nature has published an article with a #superresolution approach for #CT scans.
https://www.sciencedaily.com/releases/2018/03/180321155324.htm
#arxiv: https://arxiv.org/abs/1704.08841
https://www.sciencedaily.com/releases/2018/03/180321155324.htm
#arxiv: https://arxiv.org/abs/1704.08841
ScienceDaily
New artificial intelligence technique dramatically improves the quality of medical imaging
Researchers have developed a new technique based on artificial intelligence and machine learning that should enable clinicians to acquire high-quality images from limited data.
New paper on generating images from scene description using GANs
https://arxiv.org/abs/1804.01622
#arxiv #gan
https://arxiv.org/abs/1804.01622
#arxiv #gan