Jinheng Xie issues

Results 15 issues of


Jinheng Xie

The complete scripts for training and evaluating I2C on CUB-200-2011 dataset and bugs

Hi, Great thanks for your great work I2C. When I ran the code, I met many problems. I have changed the code for training I2C on CUB-200-2011 dataset, however, I...

Please add our CVPR 2022 paper on Weakly Supervised Learning

Great repository! Please add our CVPR 2022 paper on Weakly Supervised Learning CCAM: Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation Paper: https://arxiv.org/abs/2203.13505 Code:...

have you succeeded in writing a demo in c++？ It‘s too slow testing in python

what's your original learning rate? on my training，the loss is in plateau.

what's version of your opencv

I got error : no matching function for call to ‘cv::Mat::Mat(int, int, int, const float*)’

Will you plan to provide the trained weights of PuzzlCAM(ResNet50)?

I want to make a visual camparison with PuzzleCAM, however, I cannot reimplemet the performance. For PuzzleCAM with ResNet50, only 48.53 mIOU can be obtained, which is lower than 51.53...

can you provide the loss tendencies？

I want to know the train loss of your training

Hello, will you plan to release the training code on COCO dataset?

Is the `control_sd15_seg.pth` trained only on the ADE20K dataset? How about the controlnet for MSCOCO.

I found that `control_sd15_seg.pth` use uniformer to segment images and returns the semantic maps in the format of ADE20K. It seems that the model was only trained on ADE20K. And...

A collection of Diffusion papers (ICCV 2023)

Hope the collection of diffusion papers in ICCV 2023 (https://github.com/Sierkinhane/ICCV2023-Diffusion-Papers) helps.