Image-to-Image Translation with Conditional Adversarial Networks
- Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros
- Computer ScienceComputer Vision and Pattern Recognition
- 21 November 2016
Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
- Richard Zhang, Phillip Isola, Alexei A. Efros, Eli Shechtman, O. Wang
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 11 January 2018
A new dataset of human perceptual similarity judgments is introduced and it is found that deep features outperform all previous metrics by large margins on this dataset, and suggests that perceptual similarity is an emergent property shared across deep visual representations.
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks
- Jun-Yan Zhu, Taesung Park, Phillip Isola, Alexei A. Efros
- Computer ScienceIEEE International Conference on Computer Vision
- 30 March 2017
This work presents an approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples, and introduces a cycle consistency loss to push F(G(X)) ≈ X (and vice versa).
Supervised Contrastive Learning
- Prannay Khosla, Piotr Teterwak, Dilip Krishnan
- Computer ScienceNeural Information Processing Systems
- 23 April 2020
A novel training methodology that consistently outperforms cross entropy on supervised learning tasks across different architectures and data augmentations is proposed, and the batch contrastive loss is modified, which has recently been shown to be very effective at learning powerful representations in the self-supervised setting.
Colorful Image Colorization
- Richard Zhang, Phillip Isola, Alexei A. Efros
- Computer ScienceEuropean Conference on Computer Vision
- 28 March 2016
This paper proposes a fully automatic approach to colorization that produces vibrant and realistic colorizations and shows that colorization can be a powerful pretext task for self-supervised feature learning, acting as a cross-channel encoder.
CyCADA: Cycle-Consistent Adversarial Domain Adaptation
- Judy Hoffman, Eric Tzeng, Trevor Darrell
- Computer ScienceInternational Conference on Machine Learning
- 8 November 2017
A novel discriminatively-trained Cycle-Consistent Adversarial Domain Adaptation model that adapts representations at both the pixel-level and feature-level, enforces cycle-consistency while leveraging a task loss, and does not require aligned pairs is proposed.
Contrastive Multiview Coding
- Yonglong Tian, Dilip Krishnan, Phillip Isola
- Computer ScienceEuropean Conference on Computer Vision
- 13 June 2019
Key properties of the multiview contrastive learning approach are analyzed, finding that the contrastive loss outperforms a popular alternative based on cross-view prediction, and that the more views the authors learn from, the better the resulting representation captures underlying scene semantics.
Contrastive Representation Distillation
- Yonglong Tian, Dilip Krishnan, Phillip Isola
- Computer ScienceInternational Conference on Learning…
- 23 October 2019
The resulting new objective outperforms knowledge distillation and other cutting-edge distillers on a variety of knowledge transfer tasks, including single model compression, ensemble distillation, and cross-modal transfer.
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
- Tongzhou Wang, Phillip Isola
- Computer ScienceInternational Conference on Machine Learning
- 20 May 2020
This work identifies two key properties related to the contrastive loss: alignment (closeness) of features from positive pairs, and uniformity of the induced distribution of the (normalized) features on the hypersphere.
What makes for good views for contrastive learning
- Yonglong Tian, Chen Sun, Ben Poole, Dilip Krishnan, C. Schmid, Phillip Isola
- Computer ScienceNeural Information Processing Systems
- 20 May 2020
This paper uses empirical analysis to better understand the importance of view selection, and argues that the mutual information (MI) between views should be reduced while keeping task-relevant information intact, and devise unsupervised and semi-supervised frameworks that learn effective views by aiming to reduce their MI.
...
...