Yifan Zhang

icon indicating a website link https://sites.google.com/view/yifan-zhang/ icon indicating an email [email protected]

icon company MiroMind AI & National University of Singapore icon location Singapore

Results 5 comments of Yifan Zhang

Accuracy on ImageNet-LT

I obtain similar results. Do you solve this problem?

Visualizaiton of the learned features

To obtain this visualization, you need an additional 3-dimensional MLP projection between features and classification predictions. For example, on CIFAR10: (1) You need to first train the following network architecture:...

Visualizaiton of the learned features

> Hi, thanks for the answer. Do you also have a ready-to-run script for this experiment and visualization? Hi, thanks for your interest. You may refer to: https://github.com/SCUT-AILab/CPGA/tree/main/visualization.

codes to run Places and ImageNet data

Hi, Thanks for sharing the codes. I am wondering whether you are going to release the codes for dataset Places and ImageNet.

Question about the CLIP model

> See; https://github.com/openai/glide-text2im/blob/main/model-card.md#datasets > > > ### Datasets > > GLIDE (filtered) was trained on a filtered version of a dataset comprised of several hundred million text-image pairs > >...