Robust Semi-Supervised Traffic Sign Recognition via Self-Training and Weakly-Supervised Learning

• DOI: 10.3390/s20092684
• Publication Date: 2020-05-08T15:26:00Z
• Authors: Obed Tettey Nartey; Guowu Yang; Sarpong Kwadwo Asare; Jinzhao Wu; Lady Nadia Frempong
• Keywords: semi-supervised learning; traffic sign recognition; self-training; weakly-supervised learning; Chemical technology; 0202 electrical engineering, electronic engineering, information engineering; self-paced learning; TP1-1185; 02 engineering and technology; deep convolutional neural networks; Article

Traffic sign recognition is a classification problem that poses challenges for computer vision and machine learning algorithms. Although both computer vision and machine learning techniques have constantly been improved to solve this problem, the sudden rise in the number of unlabeled traffic signs has become even more challenging. Large data collation and labeling are tedious and expensive tasks that demand much time, expert knowledge, and fiscal resources to satisfy the hunger of deep neural networks. Aside from that, the problem of having unbalanced data also poses a greater challenge to computer vision and machine learning algorithms to achieve better performance. These problems raise the need to develop algorithms that can fully exploit a large amount of unlabeled data, use a small amount of labeled samples, and be robust to data imbalance to build an efficient and high-quality classifier. In this work, we propose a novel semi-supervised classification technique that is robust to small and unbalanced data. The framework integrates weakly-supervised learning and self-training with self-paced learning to generate attention maps to augment the training set and utilizes a novel pseudo-label generation and selection algorithm to generate and select pseudo-labeled samples. The method improves the performance by: (1) normalizing the class-wise confidence levels to prevent the model from ignoring hard-to-learn samples, thereby solving the imbalanced data problem; (2) jointly learning a model and optimizing pseudo-labels generated on unlabeled data; and (3) enlarging the training set to satisfy the hunger of deep learning models. Extensive evaluations on two public traffic sign recognition datasets demonstrate the effectiveness of the proposed technique and provide a potential solution for practical applications.