Camouflaged object detection is a challenging task that aims to identify objects having similar texture to the surroundings.
It avoids the heavy computation of exhaustively searching all the cycle lengths in the video, and, instead, it propagates the coarse prediction for further refinement in a hierarchical manner.
Second, we develop a bidirectional feature pyramid network (BFPN) to aggregate shadow contexts spanned across different CNN layers by deploying two series of RAR modules in the network to iteratively combine and refine context features: one series to refine context features from deep to shallow layers, and another series from shallow to deep layers.
Ranked #3 on Shadow Detection on SBU
Based on these findings, we present a scale-insensitive convolutional neural network (SINet) for fast detecting vehicles with a large variance of scales.