Abstract In this paper, we propose a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN) through domain-collaborative and domainadversarial training of neural networks. We add several domain classififiers on multiple CNN feature extraction blocks1, in which each domain classififier is connected to the hidden representations from one block and one loss function is de- fifined based on the hidden presentation and the domain labels (e.g., source and target). We design a new loss function by integrating the losses from all blocks in order to learn domain informative representations from lower blocks through collaborative learning and learn domain uninformative representations from higher blocks through adversarial learning. We further extend our CAN method as Incremental CAN (iCAN), in which we iteratively select a set of pseudolabelled target samples based on the image classififier and the last domain classififier from the previous training epoch and re-train our CAN model by using the enlarged training set. Comprehensive experiments on two benchmark datasets Offifice and ImageCLEF-DA clearly demonstrate the effectiveness of our newly proposed approaches CAN and iCAN for unsupervised domain adaptation