Unsupervised learning of visual invariance with temporal coherence

By Will Y. Zou. 2011

56 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images (2015, background): “Enforcing temporal slowness during learning has previously been found to be a good proxy for learning representations in reinforcement learning [39, 40], and representation learning from videos [41].”
Representation Learning: A Review and New Perspectives (2012, background): “Much has been written about the properties and alternative interpretations of CD and its similarity to auto-encoder training, e.g. Carreira-Perpiñan and Hinton (2005); Yuille (2005); Bengio and Delalleau (2009); Sutskever and Tieleman (2010).”
Practical Recommendations for Gradient-Based Training of Deep Architectures (2012, methodology): “One approach (Ranzato et al., 2008b; Le et al., 2011; Zou et al., 2011) is simply to penalize the L1 norm of the representation or another function of the hidden units activation (such as the studentt log-prior).”
Slow and Steady Feature Analysis: Higher Order Temporal Coherence in Video (2015, methodology): “Our goal is to exploit unlabeled video, as might be obtained freely from the web, to improve visual feature learning.”
Object-Centric Representation Learning from Unlabeled Videos (2016, methodology): “Some methods attempt to learn feature representations of video frames as a whole [6,20,9,10], while others track local patches to learn a localized representation [7,21,22].”
Multi-Modal Neuroimaging Feature Learning for Multi-Class Diagnosis of Alzheimer’s Disease (2014, methodology): “1) Pretraining SAEs: We applied SAEs [45], [52], [53] to learn the high-level features in an unsupervised way as shown in Fig.”
A review of unsupervised feature learning and deep learning for time-series modeling (2014, unknown): “[135], where an auto-encoder with a L1-cost on the temporal difference on the pooling units is used to learn features that improve object recognition on still images.”
Semi-supervised tuning from temporal coherence (2015, methodology): “This is conceptually similar to the unsupervised feature learning proposed in Zou et al. (2011), Zou et al. (2012), Goroshin et al. (2015).”
Deep learning for visual understanding (2017, unknown): “The sparsity of the representation can either be achieved by penalizing the hidden unit biases [28, 85, 113] or by directly penalizing the output of hidden unit activations [114, 115].”
Deep learning for visual understanding: A review (2016, background): “The sparsity of the representation can either be achieved by penalizing the hidden unit biases [50,59,80] or by directly penalizing the output of hidden unit activations [81,82].”
Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives (2012, methodology): “…negative) (Ranzato et al. , 2007; Lee et al. , 2008; Goodfellow et al. , 2009; Larochelle and Bengio, 2008) and some by directly penalizing the output of the hidden unit activations (making them closer to their saturating value at 0) (Ranzato et al. , 2008; Le et al. , 2011a; Zou et al. , 2011).”