Multiple Instance Detection Network with Online Instance Classifier Refinement
Citations
749 citations
Cites methods from "Multiple Instance Detection Network..."
...Context information [223], instance classifier refinement [224] and image segmentation [225], [226] are adopted to tackle hardly optimized problems....
[...]
539 citations
Cites background from "Multiple Instance Detection Network..."
...is to develop object recognition methods that can learn from unlabeled or weakly labeled images [14, 32]....
[...]
425 citations
379 citations
261 citations
Cites methods from "Multiple Instance Detection Network..."
...As a counterpart of the weakly-supervised video TAL, the weaklysupervised image object detection has been significantly improved via combining Multiple Instance Learning (MIL) [12] and deep networks [49,30,59,5,32]: built upon Fast-RCNN [18], these methods first generated candidate proposals beforehand; then they employed deep networks to classify each proposal and the scores from all proposals were fused together to obtain one label prediction for the whole image to be compared with the image-level label....
[...]
...Weakly-supervised deep learning methods have been also widely studied in other vision tasks such as object detection [74,75,49,35,30,14,59,71,57,5,32,20], semantic segmentation [34,24,41,4], video captioning [48], visual relation detection [70], etc....
[...]
References
73,978 citations
49,914 citations
49,639 citations
"Multiple Instance Detection Network..." refers background or methods in this paper
...With the development of Convolutional Neural Network (CNN) [17, 19], great improvements have been achieved on object detection [12, 13, 23, 25, 26], due to the availability of large scale datasets with accurate boundingbox-level annotations [8, 11, 22]....
[...]
...Implementation details Our method is built on two pretrained ImageNet [8] networks: VGG M [6] and VGG16 [27], each of which has some conv layers with max-pooling layer and three fc layers....
[...]
42,067 citations
30,462 citations
"Multiple Instance Detection Network..." refers background in this paper
...With the development of Convolutional Neural Network (CNN) [17, 19], great improvements have been achieved on object detection [12, 13, 23, 25, 26], due to the availability of large scale datasets with accurate boundingbox-level annotations [8, 11, 22]....
[...]