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

Abstract

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.

Towards Enhancing Traffic Sign Recognition through Sliding Windows

“…In [ 55 ] authors propose a lightweight CNN architecture for the recognition of the traffic sign GTSRB dataset, and they achieved 99.15% accuracy. In one another study [ 56 ], a novel semi supervised classification technique is adopted for TSR with weakly-supervised learning and self-training. An ensemble of CNN was used for the recognition of the traffic signs and achieved higher than 99% accuracy for the circular traffic signs of the German and BelgiumTSC datasets [ 57 ].…”

Lidar–Camera Semi-Supervised Learning for Semantic Segmentation

“…Focusing on the task of autonomous driving, [ 7 ] offered a review of methods and datasets, indicating the increment in labelling efficiency, transfer learning, semi-supervised learning, etc., as open questions for research to leverage lifelong learning by updating networks with continual data collection instead of re-training from scratch. One example of application is provided in [ 8 ], where a semi-supervised learning method that uses labelled and unlabelled camera images to improve traffic sign recognition is proposed. The semi-supervised learning is also used in [ 9 ], where Zhu et al define a teacher model which is trained in a supervised manner using labelled camera images.…”

Robust Semantic Segmentation With Multi-Teacher Knowledge Distillation

“…Compiling full human annotations for a large-scale database is an exceedingly time-consuming procedure [5]. This restriction has motivated the researchers to substitute the supervised learning perspective with various other techniques, such as the semi-supervised learning [6] approach, multi-source domain adaptation [7], and weakly supervised semantic segmentation [8], to take advantage of unlabeled data.…”