Experiments show that the PDP layer and SR module are effective and our PSNet outperforms previous methods. To sufficiently utilize the extracted multi-scale features for captioning, we propose a scale-aware reinforcement (SR) module and combine it with the Transformer decoding layer to progressively utilize the features from different PDP layers.
To sufficiently extract multi-scale visual features, multiple progressive difference perception (PDP) layers are stacked to progressively exploit the differencing features of bitemporal features. In this paper, we propose a progressive scale-aware network (PSNet) to address the problem. Pdplayer gives you the possibility to toggle the red, green, blue, alpha, luma and depth channel, play forward or backward, jump to the previous or next frame, show or hide layer properties. However, current methods still have some weaknesses in sufficiently extracting and utilizing multi-scale information.
Download a PDF of the paper titled Progressive Scale-aware Network for Remote sensing Image Change Captioning, by Chenyang Liu and 3 other authors Download PDF HTML (experimental) Abstract:Remote sensing (RS) images contain numerous objects of different scales, which poses significant challenges for the RS image change captioning (RSICC) task to identify visual changes of interest in complex scenes and describe them via language.
