Fig 2 - uploaded by Shixiang Tang
Content may be subject to copyright.
Faster R-CNN network incorporates with CDN. The CDN is adopted in both backbone network and bounding box head network to adaptively address the domain shift at different representation levels.
Source publication
Real-world object detectors are often challenged by the domain gaps between different datasets. In this work, we present the Conditional Domain Normalization (CDN) to bridge the domain gap. CDN is designed to encode different domain inputs into a shared latent space, where the features from different domains carry the same domain attribute. To achi...
Contexts in source publication
Context 1
... this observation, CNN based object detectors naturally exhibit different types of domain shift at various levels' representations. Hence we incorporate CDN into different convolution stages in object detectors to address the domain mismatch adaptively, as shown in Fig.2. ...
Context 2
... shown in Fig. 2, taking faster-RCNN model [34] with ResNet [12] backbone as an example, we incorporate CDN in the last residual block at each stage. Thus the global alignment loss can be computed ...
Context 3
... λ is a weight to balance the global and local alignment regularization. Discussion Existing adversarial domain adaptation methods try to handle the domain shift at one or a few specific convolution stages. However, the domain mismatch at different representation levels is not identical due to the nature of deep convolutional networks. As shown in Fig. 2, we incorporate CDN at various representation levels to adaptively align the source and target domain ...
Context 4
... this observation, CNN based object detectors naturally exhibit different types of domain shift at various levels' representations. Hence we incorporate CDN into different convolution stages in object detectors to address the domain mismatch adaptively, as shown in Fig.2. ...
Similar publications
Infrared-visible image patches matching has many applications, such as target recognition, vision-based navigation, and others. At present, deep learning has achieved excellent performance in visible image patches matching. Due to imaging differences in infrared-visible images and the small number of supervised samples, the existing networks cannot...
Visual object tracking methods based on Siamese network are often difficult to distinguish objects with the same semantic or similar appearance as tracking target in tracking process due to the lack of discriminating strategies for the confusing objects. We propose a visual object tracking method based on Siamese modulation network. It takes the gi...
