Learning Deep Neural Networks with Massive Learned Knowledge, Z. Hu, Z. Yang, R. Salakhutdinov, E. Xing
https://www.cs.cmu.edu/~zhitingh/data/emnlp16deep.pdf
#paper #dl
https://www.cs.cmu.edu/~zhitingh/data/emnlp16deep.pdf
#paper #dl
👍1
Spatially Adaptive Computation Time for Residual Networks
with Michael Figurnov et al.
https://arxiv.org/abs/1612.02297
#paper #dl
with Michael Figurnov et al.
https://arxiv.org/abs/1612.02297
#paper #dl
VirTex: Learning Visual Representations from Textual Annotations
The authors offer an alternative approach to pre-training backbones for CV tasks – using semantically dense captions to learn visual representations.
Recent methods have explored unsupervised pretraining to scale to vast quantities of unlabeled images. In contrast, the authors aim to learn high-quality visual representations from fewer images. They revisit supervised pretraining and seek data-efficient alternatives to classification-based pretraining.
VirTex (CNN + Transformer) is pre-trained on COCO captions. On downstream tasks it can reach performance similar to pre-training on ImageNet, but with 10x less images!
Paper: https://arxiv.org/abs/2006.06666
Code: https://github.com/kdexd/virtex
Site: https://kdexd.github.io/virtex/
#imagecaptioning #cv #visual #annotation #transformer #pretraining #transferlearning #deeplearning #paper
The authors offer an alternative approach to pre-training backbones for CV tasks – using semantically dense captions to learn visual representations.
Recent methods have explored unsupervised pretraining to scale to vast quantities of unlabeled images. In contrast, the authors aim to learn high-quality visual representations from fewer images. They revisit supervised pretraining and seek data-efficient alternatives to classification-based pretraining.
VirTex (CNN + Transformer) is pre-trained on COCO captions. On downstream tasks it can reach performance similar to pre-training on ImageNet, but with 10x less images!
Paper: https://arxiv.org/abs/2006.06666
Code: https://github.com/kdexd/virtex
Site: https://kdexd.github.io/virtex/
#imagecaptioning #cv #visual #annotation #transformer #pretraining #transferlearning #deeplearning #paper
Forwarded from Gradient Dude
LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions
A framework that learns meaningful directions in GANs' latent space using unsupervised contrastive learning. Instead of discovering fixed directions such as in previous work, this method can discover non-linear directions in pretrained StyleGAN2 and BigGAN models. The discovered directions may be used for image manipulation.
Authors use the differences caused by an edit operation on the feature activations to optimize the identifiability of each direction. The edit operations are modeled by several separate neural nets
📝 Paper
🛠 Code (next week)
#paper_tldr #cv #gan
A framework that learns meaningful directions in GANs' latent space using unsupervised contrastive learning. Instead of discovering fixed directions such as in previous work, this method can discover non-linear directions in pretrained StyleGAN2 and BigGAN models. The discovered directions may be used for image manipulation.
Authors use the differences caused by an edit operation on the feature activations to optimize the identifiability of each direction. The edit operations are modeled by several separate neural nets
∆_i(z) and learning. Given a latent code z and its generated image x = G(z), we seek to find edit operations ∆_i(z) such that the image x' = G(∆_i(z)) has semantically meaningful changes over x while still preserving the identity of x.📝 Paper
🛠 Code (next week)
#paper_tldr #cv #gan