Unsupervised Learning of Discriminative Attributes and Visual Representations
By Chen Huang, Chen Change Loy, Xiaoou Tang. 2016
101 citations recorded by the source corpus.
Subfields: Artificial Intelligence, 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 Artificial Intelligence
- Stephen Gould
- Basura Fernando
- Mang Ye
- Tao A. Xiang
- Nikolaos Passalis
- Anoop Cherian
- Anastasios Tefas
- Yonghong Tian
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Yi Yang
- Xiaogang Wang
- Trevor Darrell
- Andrea Vedaldi
- Andrew Zisserman
- Ming-Hsuan Yang
In Representation & Self-Supervised Learning
- Mang Ye
- Tao A. Xiang
- Stephen Gould
- Basura Fernando
- Daniel Cremers
- Anastasios Tefas
- Pong Chi Yuen
- Xu Zhang
Citations in the corpus
- Unsupervised Embedding Learning via Invariant and Spreading Instance Feature (2019, methodology): “We report the cosine similarity distribution based on other category definitions (attributes in [19]) instead of semantic label in Fig.”
- Self-Supervised Feature Learning by Learning to Spot Artifacts (2018, neutral): “[17] 76.8% ± 0 .”
- Scaling the Scattering Transform: Deep Hybrid Networks (2017, neutral): “For an Exemplar CNN [9] or an Unsupervised Discriminative CNN [13], the weights of the CNNs are learned in an unsupervised manner from patches of the unlabeled images.”
- Deep Transfer Learning for Person Re-Identification (2016, background): “network [52]. The main limitation of an unsupervised model is that it cannot learn discriminative features. Hence soft-label self-training based deep unsupervised learning has become popular recently [16]. In this work, a novel co-training [36] based unsupervised domain adaptation method is proposed”
- Associative Deep Clustering: Training a Classification Network with No Labels (2018, background): “To circumvent this problem, a plethora of semi-supervised and unsupervised training schemes have been proposed [6, 8, 25, 19].”
- Learning Deep Representations with Probabilistic Knowledge Transfer (2018, methodology): “osed method was evaluated using the CIFAR10 dataset [25], that contains 60,000 32 32 color images that belongs to 10 different categories and it is frequently used for evaluating retrieval techniques [28, 19]. The knowledge was transfered from the penultimate layer of a deep neural network, the ResN”
- DeepPermNet: Visual Permutation Learning (2017, methodology): “However, there are methods that can discover binary visual attributes in an unsupervised way [36, 18].”