rpn
Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution
Thang Vu, Hyunjun Jang, Trung X. Pham, Chang Yoo
Recent high-performing object detectors, such asFaster R-CNN [34],formulate thedetection problem as atwo-stage pipeline.
Consistency-based Semi-supervised Learning for Object detection
Jisoo Jeong, Seungeui Lee, Jeesoo Kim, Nojun Kwak
While the object detection task requires a huge number of annotated samples to guarantee its performance, placing bounding boxes for every object in each sample is time-consuming and costs alot.
Regression Planning Networks
Danfei Xu, Roberto Martín-Martín, De-An Huang, Yuke Zhu, Silvio Savarese, Li F. Fei-Fei
Performing real-world tasks such as cooking meals or assembling furniture requires an agent to determine long-term strategies. This is often formulated as aplanning problem.
** Our method: The proposed co-attention augments the feature maps (for RPN) of a target image
Also see our response in 1.4.
Regression Planning Networks
Danfei Xu, Roberto Martín-Martín, De-An Huang, Yuke Zhu, Silvio Savarese, Li F. Fei-Fei
Neural Information Processing Systems http://nips.cc/
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun
Neural Information Processing Systems http://nips.cc/
Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution
Thang Vu, Hyunjun Jang, Trung X. Pham, Chang Yoo
RPN relies on a single anchor per location and performs multi-stage refinement.