CSI
CSI copied to clipboard
alinlab
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances (NeurIPS 2020)
Hi, congrats on the interesting work! Do you have the code for the baseline methods in the paper, e.g., Rot[25]? Thanks in advance.
Excuse me, I recently paid attention to this paper. when I use the Supervised_NT_xent loss, I find that there are some question maybe. In SupCLR paper, when calculate the loss,...
Thanks for the nice work! I have one question about the image size you used in one-class ImageNet-30 setting. I used four 3080ti gpus with a batch-size of 32 for...
Hello, The CIFAR100 super-class used [here](https://github.com/alinlab/CSI/blob/master/datasets/datasets.py#L17) are quite different from the standard division described [here](https://www.cs.toronto.edu/~kriz/cifar.html) This can be easily seen by comparing to other implementations that follow the standard division,...
Hello, thank you for implemantation. I would like to train it on my custom data? What should i change to make it work?
Hi I tried to rerun your code for cifar100 multi-class with the following command: `CUDA_VISIBLE_DEVICES=4,5,6,7 python -m torch.distributed.launch --nproc_per_node=4 train.py --dataset 'cifar100' --model 'resnet18' --mode sup_simclr_CSI --shift_trans_type rotation --batch_size 32...
Can you please tell me the hyper parmeter of your retrained Rot(resnet18) and Rot+Trans(resnet18), such as batch size, learning rate, the weight of rotation-loss and trans-loss in Rot+Trans. Or you...
joint_labels = torch.cat([labels + P.n_classes * i for i in range(4)], dim=0) I do not understand what is the meaning of this code.
Hi, you have done an excellent work. However, I can not find the codes for the noise condition.
Hi. Thanks for your work. In the following line, where does the simclr, and penultimate parameters come from? I dont see it in the forward of REsnet class. https://github.com/alinlab/CSI/blob/60742b60a16501350eca823fcc910ddd10f7a379/training/unsup/simclr.py#L53
