Object Recognition is a computer vision technique for identifying or recognizing objects in images or videos. The ability of immediately recognizing the objects in a scene seems to be no longer a secret of evolution. With the development of deep learning, recognizing objects is one of the most important applications of vision systems, and is consequently highly developing.
Although we are nowhere near or surpass human performance on many experimental benchmark datasets, the final applications in the wild are more challenging and knotty due to the limitation of model discrimination, model cognition and model generalization. We work on a large variety of object recognition systems, ranging from image classification, face identification and image retrieval. Along the way, our works have achieved more discriminative feature representation and more robust embeddings.