weixin_39906192
2020-11-20 22:41 阅读 7

IOU threshold

Hi,

I wonder if you use IOU threshold for box matching.

If you do, can you explain me what criterion to decide the anchor size?

Thanks in advance. Byeonghak

该提问来源于开源项目:BichenWuUCB/squeezeDet

  • 点赞
  • 写回答
  • 关注问题
  • 收藏
  • 复制链接分享

6条回答 默认 最新

  • weixin_39525313 weixin_39525313 2020-11-20 22:41

    You can find the answers to all go your questions in the various config.py files On Fri, 24 Mar 2017 at 3:51 PM, ByeonghakYim wrote:

    Hi,

    I wonder if you use IOU threshold for box matching.

    If not, what size of anchors do you use? and what is your input resolution?

    Thanks in advance. Byeonghak

    — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/BichenWuUCB/squeezeDet/issues/25, or mute the thread https://github.com/notifications/unsubscribe-auth/AN_wJk9uSrjkfZ3-gwbph2qXB0_GXeRwks5ro3YLgaJpZM4Mn2S7 .

    点赞 评论 复制链接分享
  • weixin_39906192 weixin_39906192 2020-11-20 22:41

    Thanks, I've just checked and find that the set_anchors gives me the anchor box information. But still can not find IOU threshold

    点赞 评论 复制链接分享
  • weixin_39525313 weixin_39525313 2020-11-20 22:41

    NMS_tresh on the config should be the IOU threshold for the non max suppression algorithm

    On Fri, 24 Mar 2017 at 4:02 PM, ByeonghakYim wrote:

    https://github.com/AndreaPisoni Thanks, I've just checked and find that the set_anchors gives me the anchor box information. But still can not find IOU threshold

    — You are receiving this because you were mentioned.

    Reply to this email directly, view it on GitHub https://github.com/BichenWuUCB/squeezeDet/issues/25#issuecomment-288957427, or mute the thread https://github.com/notifications/unsubscribe-auth/AN_wJv8Hr00spbKoKAqn5AVGrau0ZTPpks5ro3ipgaJpZM4Mn2S7 .

    点赞 评论 复制链接分享
  • weixin_39906192 weixin_39906192 2020-11-20 22:41

    Most of detection algorithm has IOU threshold to assign positive and negative during the training. In the paper they said they choose the largest IOU anchor as positive, but in this way IOU with 0.01 also could be positive. They set the largest anchor as 366 x 174, but what if the object size is 700 x 700. Just I think, not definitely, that this cause the downside on the localization. How do you think of this? I would like to know your opinion.

    点赞 评论 复制链接分享
  • weixin_39643336 weixin_39643336 2020-11-20 22:41

    Sorry for the delay to answer your question. Let me make sure if I understand your question correctly. You are wondering how we assign a ground truth bounding box to a reference anchor during training, is that right? Essentially, we assign the ground truth bbox to the anchor that has the largest IOU with it. It is possible that for extremely large or small objects, even the best IOU is very small. But that's just the candidate -- we also will compute bbox deltas to transform reference anchor to match the gt-bbox.

    In order to make our pre-selected anchor shapes to best match with the bbox distribution, we used a trick proposed in our previous paper.

    Does it make sense?

    点赞 评论 复制链接分享
  • weixin_39906192 weixin_39906192 2020-11-20 22:41

    Yes, thanks so much. I think that anchor selection is the most important issue for performance, so I'm trying to find the best anchor box set without sacrificing processing time. Thanks again

    点赞 评论 复制链接分享

相关推荐