Meta-Faster-R-CNN
Meta-Faster-R-CNN copied to clipboard
GuangxingHan
Code for AAAI 2022 Oral paper: 'Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment'
Hello, thank you for your work. I am counfusized on your `crop_support()` function in `datasets/pascal_voc/2_gen_support_pool.py` during support pool generation. What is the meaning of `context_pixel` variable? And how to properly...
Hello, thank you very much for your work, but I have a question. I want to run my own dataset on your work. It is in voc format. How can...
"Hello, I've been trying to use your code as a reference, but unfortunately, I've encountered some issues that prevent it from running successfully. I appreciate your work, and I was...
Hello, to avoid disturbing you, could I ask you for the source code of the final predicted frame in your visualization?
"Hello, I'm sorry to bother you. Could you please provide the source code for visualizing the affinity matrix for alignment and foreground attention masks?"
>  I don't know why such a problem occurs，Hope you can get some advice, thank you
Where should I obtain this pkl file？？
I have a question. For VOC datasets, they are not randomly divided into three splits. Instead, I am renting a server online. I can rent three graphics cards of the...
Why is running 2_ Gen_ Support_ There was an issue with the pool.py file:AttributeError: 'NoneType' object has no attribute 'shape' Is it because there are grayscale images？
I can't find the following text file： log/meta_training_pascalvoc_split1_resnet101_stage_1.txt log/meta_training_pascalvoc_split1_resnet101_stage_2.txt log/meta_training_pascalvoc_split1_resnet101_stage_3.txt log/meta_training_coco_resnet101_stage_1.txt log/meta_training_coco_resnet101_stage_2.txt log/meta_training_coco_resnet101_stage_3.txt log/1shot_finetune_pascalvoc_split1_resnet101.txt log/faster_rcnn_with_fpn_coco_base_classes_branch.txt ... If you could provide it to me, I would be very grateful！Thank you！
Metadata
Owner
Metadata
Code for AAAI 2022 Oral paper: 'Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment'