Congratulations to Eddy Wu for passing his defense. His thesis title is “Deep Learning Techniques for Supervised Pedestrian Detection and Critically-Supervised Object Detection” with three major topics, as follow:
In the first topic, a boosted convolutional neural network (BCNN) system is proposed to enhance the pedestrian detection performance. Being inspired by the classic boosting idea, we develop a weighted loss function that emphasizes challenging samples in training a convolutional neural network (CNN). Two types of samples are considered challenging: 1) samples with detection scores falling in the decision boundary, and 2) temporally associated samples with inconsistent scores. Finally, we train a boosted fusion layer to benefit from the integration of these two weighting schemes. We test the corresponding BCNN on the Caltech pedestrian dataset in the experiment and observe a significant performance gain over the Fast-RCNN baseline.
In the second topic, a semi-supervised learning method is proposed for pedestrian detection in a domain adaptation setup. The proposed clustered deep representation adaptation (CDRA) method uses a small amount of labeled data to train an intial detector, extracts the deep representation and, then, clusters samples based on the space spanned by the deep representation. A purity measurement mechanism is applied to each cluster to provide a confident score to the estimated class of unlabeled data. Along with a weighted training approach, the CDRA method is shown to achieve the state-of-the-art performance against some large scale datasets.
In the third topic, we propose a new framework called critically-supervised learning that mimics children learing behaviors. Several novel components are proposed to fulfill the high level concept, including negative object proposal, critical example mining, and a machine-guided labeling process based on question answering. A labeling time model is proposed to evaluate the final performance. Extensive experiments are conducted to shed light on several novel ideas, and the effectiveness of the proposed method is not only evaluated on the Caltech benchmark datasets, but also on the PASCAL VOC datasets for the general object detection task. In general, the proposed method provides excellent performances while saving up to 95% of the labeling time in these datasets.
Eddy also encourages everyone to dream big, as we are in a new era that technologies change so fast and many new opportunities are waiting for us. At the same time, it is important to work very hard and always think critically under Prof. Kuo guidance. Team work is also extremely important in the big family. He believes that everyone will learn a lot in the lab and have a bright future.
