U-2-Net
U-2-Net copied to clipboard
有基于bounding box的显著目标检测算法吗?
我只想检测图片中是否有物体,而不管他的类别,类似SS(Selective Search), 我搜了一圈,最近3年都没有相关的文章,只有物体检测的,是我没有搜索对吗?
You are right. Recently, most of the papers turns to work on object detection, which gives both the bounding boxes and the category. In addition to Selective Search, BING, EdgeBOX are all old ones. There are almost no new models for class agostic detection. But you could search for instance detection and segmentation. This task is only focusing on object other than their labels or categories.
On Mon, Aug 9, 2021 at 11:05 AM qingzhouzhen @.***> wrote:
我只想检测图片中是否有物体,而不管他的类别,类似SS(Selective Search), 我搜了一圈,最近3年都没有相关的文章,只有物体检测的,是我没有搜索对吗?
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/xuebinqin/U-2-Net/issues/242, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADSGORLXKDN25FAP6BSJOQDT35425ANCNFSM5BZNCSTQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&utm_campaign=notification-email .
-- Xuebin Qin PhD Department of Computing Science University of Alberta, Edmonton, AB, Canada Homepage:https://webdocs.cs.ualberta.ca/~xuebin/
Why almost no research on class agostic detection? I guess:
- no dataset for class agostic detection, (As I know, ImageNet has a subtask about class agostic detection, but seems not populary)
- it is Not challenging enough Am I right?