Object Recognition

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.


Highlights

Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering
Binghui Chen, Weihong Deng
Association for the Advancement of Artificial Intelligence (AAAI), 2019

In this paper, we propose the Energy Confused Adversarial Metric Learning (ECAML) framework, a generally applicable methods to various conventional metric learning approaches, for ZSRC tasks by explicitly intensifying the generalization ability within the learned embedding with the help of our Energy Confusion term. Extensive experiments on the popular ZSRC benchmarks(CUB, CARS, Stanford Online Products and In-Shop) demonstrate the significance and necessity of our idea of learning metric with good generalization by energy confusion.
pdf


Virtual Class Enhanced Discriminative Embedding Learning
Binghui Chen, Weihong Deng, Haifeng Shen
Conference on Neural Information Processing Systems (NeurIPS), 2018, Spotlight

In this paper, we propose a novel yet extremely simple method Virtual Softmax to enhance the discriminative property of learned features by injecting a dynamic virtual negative class into the original softmax. Injecting virtual class aims to enlarge inter-class margin and compress intra-class distribution by strengthening the decision boundary constraint. Although it seems weird to optimize with this additional virtual class, we show that our method derives from an intuitive and clear motivation, and it indeed encourages the features to be more compact and separable. This paper empirically and experimentally demonstrates the superiority of Virtual Softmax, improving the performances on a variety of object classification and face verification tasks.
PDF


Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation
Binghui Chen, Weihong Deng, Junping Du
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

In this paper, we propose Noisy Softmax, a novel technique of early softmax desaturation. This is mainly achieved by injecting annealed noise directly into softmax activations during each iteration. In another word, Noisy Softmax allows SGD to escape from a bad local-minima and explore more by postponing the early individual saturation. Furthermore, it improves the generalization ability of system by reducing over-fitting as a direct consequence of more exploration.
PDF