Self-Supervised LearningSelf-supervised learning is essentially a method of unsupervised learning, and we will set up a "Pretext" and construct Pesdeo Labels to train the network model according to some characteristics of data. The self-supervised model can be used as a pre-training model for other learning tasks to provide a better initial training area. Therefore, self-supervised learning can also be regarded as a general visual representation for learning images.
ICLR, (2020)
We have convincing evidence that sentence order prediction is a more consistently-useful learning task that leads to better language representations, we hypothesize that there could be more dimensions not yet captured by the current self-supervised training losses that could crea...
Cited by86BibtexViews334Links
0
0
Grill Jean-Bastien, Strub Florian, Altché Florent, Tallec Corentin, Richemond Pierre H.,Buchatskaya Elena,Doersch Carl,Pires Bernardo Avila,Guo Zhaohan Daniel,Azar Mohammad Gheshlaghi,Piot Bilal,Kavukcuoglu Koray
NeurIPS 2020, (2020)
We show that Bootstrap Your Own Latent achieves state-of-the-art results on various benchmarks
Cited by20BibtexViews164Links
0
0
Ravanelli Mirco, Zhong Jianyuan, Pascual Santiago, Swietojanski Pawel, Monteiro Joao, Trmal Jan,Bengio Yoshua
ICASSP, pp.6989-6993, (2020)
The proposed problemagnostic speech encoder+ architecture is based on an online speech distortion module, a convolutional encoder coupled with a quasi-recurrent neural network layer, and a set of workers solving self-supervised problems
Cited by7BibtexViews105Links
0
0
NeurIPS 2020, (2020)
We demonstrate that these self-supervised representations learn occlusion invariance by employing an aggressive cropping strategy which heavily relies on an object-centric dataset bias
Cited by6BibtexViews100Links
0
0
ICLR, (2020)
We evaluate models on two benchmarks: TIMIT is a 5h dataset with phoneme labels and Wall Street Journal is a 81h dataset for speech recognition
Cited by6BibtexViews107Links
0
0
NeurIPS 2020, (2020)
We presented wav2vec 2.0, a framework for self-supervised learning of speech representations which masks latent representations of the raw waveform and solves a contrastive task over quantized speech representations
Cited by3BibtexViews134Links
0
0
AAAI, pp.12362-12369, (2020)
We presented a Tracklet Self-Supervised Learning method for unsupervised image and video person re-id
Cited by3BibtexViews89Links
0
0
Shaolei Wang,Wanxiang Che,Qi Liu, Pengda Qin,Ting Liu,William Yang Wang
national conference on artificial intelligence, (2020)
Experimental results on the commonly used English Switchboard test set show that our approach can achieve competitive performance compared to the previous systems by using less than 1% of the training data
Cited by3BibtexViews133Links
0
0
We first introduce various basic supervised learning pretext tasks for graphs and present detailed empirical study to understand when and why SSL works for graph neural networks and which strategy can better work with GNNs
Cited by2BibtexViews162Links
0
0
Similar approaches are common in NLP, we demonstrate that this approach can be a surprisingly strong baseline for semi-supervised learning in computer vision, outperforming the state-of-the-art by a large margin
Cited by0BibtexViews264Links
0
0
Zhao Nanxuan,Wu Zhirong, Lau Rynson W. H.,Lin Stephen
We identified a strong error pattern among self-supervised models in their failure to localize foreground objects
Cited by0BibtexViews89Links
0
0
We presented BADGR, an end-to-end learning-based mobile robot navigation system that can be trained entirely with selfsupervised, off-policy data gathered in real-world environments, without any simulation or human supervision, and can improve as it gathers more data
Cited by0BibtexViews140Links
0
0
ICCV, pp.3827-3837, (2019)
We showed how together they give a simple and efficient model for depth estimation, which can be trained with monocular video data, stereo data, or mixed monocular and stereo data
Cited by155BibtexViews89Links
0
0
CVPR, (2019): 6629-6638
In this paper we present two novel approaches, Reinforced Cross-Modal Matching and Supervised Imitation Learning, which combine the strength of reinforcement learning and self-supervised imitation learning for the visionlanguage navigation task
Cited by104BibtexViews156Links
0
0
CVPR, (2019)
As part of our study, we drastically boost the performance of previously proposed techniques and outperform previously published state-of-the-art results by a large margin
Cited by95BibtexViews72Links
0
0
Michelle A. Lee,Yuke Zhu, Krishnan Srinivasan, Parth Shah,Silvio Savarese,Li Fei-Fei,Animesh Garg,Jeannette Bohg
international conference on robotics and automation, (2019)
The primary goal of our experiments is to examine the effectiveness of the multimodal representations in contactrich manipulation tasks
Cited by80BibtexViews240Links
0
0
ICCV, pp.6390-6399, (2019)
We studied the effect of scaling two selfsupervised approaches along three axes: data size, model capacity and problem complexity
Cited by77BibtexViews117Links
0
0
Fangchang Ma, Guilherme Venturelli Cavalheiro,Sertac Karaman
international conference on robotics and automation, (2019)
This framework requires only sequences of RGB and sparse depth images, and outperforms a number of existing solutions trained with semi-dense annotations
Cited by74BibtexViews104Links
0
0
Xiaohua Zhai, Avital Oliver, Alexander Kolesnikov,Lucas Beyer
International Conference on Computer Vision, (2019): 1476-1485
We further showed that S4L methods are complementary to existing semisupervision techniques, and Mix Of All Models, our proposed combination of those, leads to state-of-the-art performance
Cited by67BibtexViews79Links
0
0
arXiv: Computer Vision and Pattern Recognition, (2019)
This paper provides an extensive review of deep learning-based self-supervised general visual feature learning methods from images or videos
Cited by65BibtexViews94Links
0
0