… detection, ie, the adaptation on bounding box regression. To this end, we propose D-adapt, …
Decoupled Adaptation, to decouple the adversarial adaptation and the training of the detector…

… features, limiting the small object detection performance. To solve this issue, we propose a
… decoupling module to emphasizes small object features by eliminating large object features …

… decoupling high-order dynamic mode decomposition (FDHODMD) method is developed for
fault detection … Flow 1 and Flow 2 denote the water flows of these two tanks. Level 2 at the …

… This paper presents a new Fourier-based approach to the separation or decoupling of m …
local basis to compute a dense instantaneous optical flow field for the image sequence, even in …

… change detection (OFCD) task and proposes a method based on frequency decoupling
interaction (FDINet). Specifically, in order to enhance the model’s ability to detect change types …

… updating method, ie, multi-scale Feature Decoupling and Similarity Distillation (mFDSD), …
-based feature decoupling distillation module and a similarity-regulated feature distillation …

… First, we propose a novel flow-based method to generate body feature representation by
warping each pixel towards object inner parts through a learned offset field to maintain the …

… First, we design an efficient communication mechanism based on feature decoupling to
transmit exclusive and common feature maps among heterogeneous agents to provide …

… We carefully schedule the computing flow of the proposed decoupled GFLN in the grid
processing mode to accomplish satisfactory performance. Here, we take the first two CatMax …

… another possibility of decoupling the node representation learning and the classification
for anomaly detection. We conduct a preliminary study to show that decoupled training using …