Issue about "trainval_1shot.txt"

[whsun21]

Issue about "trainval_1shot.txt"

[Ze-Yang]

Hi SUN Wenhao, our transfer setting follows the image-shot setup in LSTD task2, except that we use VOC07+12 for the second stage finetuning. As a result, you need to combine the trainval_nshot.txt files in VOC07+12 to form the final few-shot dataset for finetuning, which may explain why you only observe 11 categories (maybe only the part in VOC2007).

Besides, an image may contain several boxes belonging to different categories, however it is counted only according to one of its box categories, leaving remaining boxes uncounted yet used. This explains why some categories own number of boxes greater than N-shot. I think it is a characteristic of image-shot setting. You may also refer to issue #3. Hope that it clarifies your confusion. Thanks.

[whsun21]

Thank you for your prompt reply, I did miss the part in VOC2012. Your detailed explanation helped me a lot, thank you very much!