Perception techniques for autonomous driving should be adaptive to various environments. In essential perception modules for traffic line detection, many conditions should be considered, such as a number of traffic lines and computing power of the target system. To address these problems, in this paper, we propose a traffic line detection method called Point Instance Network (PINet); the method is based on the key points estimation and instance segmentation approach. The PINet includes several hourglass models that are trained simultaneously with the same loss function. Therefore, the size of the trained models can be chosen according to the target environment’s computing power. We cast a clustering problem of the predicted key points as an instance segmentation problem; the PINet can be trained regardless of the number of the traffic lines. The PINet achieves competitive accuracy and false positive on CULane and TuSimple datasets, popular public datasets for lane detection. Our code is available at https://github.com/koyeongmin/PINet_new

We present adversarial event prediction (AEP), a novel approach to detecting abnormal events through an event prediction setting. Given normal event samples, AEP derives the prediction model, which can discover the correlation between the present and future of events in the training step. In obtaining the prediction model, we propose adversarial learning for the past and future of events. The proposed adversarial learning enforces AEP to learn the representation for predicting future events and restricts the representation learning for the past of events. By exploiting the proposed adversarial learning, AEP can produce the discriminative model to detect an anomaly of events without complementary information, such as optical flow and explicit abnormal event samples in the training step. We demonstrate the efficiency of AEP for detecting anomalies of events using the UCSD-Ped, CUHK Avenue, Subway, and UCF-Crime data sets. Experiments include the performance analysis depending on hyperparameter settings and the comparison with existing state-of-the-art methods. The experimental results show that the proposed adversarial learning can assist in deriving a better model for normal events on AEP, and AEP trained by the proposed adversarial learning can surpass the existing state-of-the-art methods.

License plate (LP) detection in the wild remains challenging due to the diversity of environmental conditions. Nevertheless, prior solutions have focused on controlled environments, such as when LP images frequently emerge as from an approximately frontal viewpoint and without scene text which might be mistaken for an LP. However, even for state-of-the-art object detectors, their detection performance is not satisfactory for real-world environments, suffering from various types of degradation. To solve these problems, we propose a novel end-to-end framework for robust LP detection, designed for such challenging settings. Our contribution is threefold: (1) A novel information-theoretic learning that takes advantage of a shared encoder, an LP detector and a scene text detector (excluding LP) simultaneously; (2) Localization refinement for generalizing the bounding box regression network to complement ambiguous detection results; (3) a large-scale, comprehensive dataset, LPST-110K, representing real-world unconstrained scenes including scene text annotations. Computational tests show that the proposed model outperforms other state-of-the-art methods on a variety of challenging datasets.

Image de-raining is an important task in many robot vision applications since rain effects and hazy air largely threaten the performance of visual analytics. While deep neural de-raining models have greatly boosted performance by learning rich representations of rainy input data, they are still likely to indicate incongruent information to spoil de-raining. We find that the process of extracting the feature representations in the rainy image space is surprisingly important for perceptual de-raining performance. We further probe the limitations of the universal restoration learning method and formulate explicitly relevant and irrelevant information onto feature representations. To handle this issue, we employ an information-theoretic concept to define disentangled representation which is divided into shared and excluded characteristics. Our key idea is to remove excluded feature representations from a set of co-occurrence features while preserving details using mutual information. To achieve this, we propose a novel stage-wise training strategy that captures a more discriminative and pure factor that preserves details. Specifically, we utilize an adversarial objective that explicitly defines each representation to enforce disentanglement. Extensive computational experiments on six benchmark datasets show the superiority of our new model against state-of-the-art methods.

Recently, deep learning models have achieved great success in computer vision applications, relying on large-scale class-balanced datasets. However, imbalanced class distributions still limit the wide applicability of these models due to degradation in performance. To solve this problem, in this paper, we concentrate on the study of cross entropy which mostly ignores output scores on incorrect classes. This work discovers that neutralizing predicted probabilities on incorrect classes improves the prediction accuracy for imbalanced image classification. This paper proposes a simple but effective loss named complement cross entropy based on this finding. The proposed loss makes the ground truth class overwhelm the other classes in terms of softmax probability, by neutralizing probabilities of incorrect classes, without additional training procedures. Along with it, this loss facilitates the models to learn key information especially from samples on minority classes. It ensures more accurate and robust classification results on imbalanced distributions. Extensive experiments on imbalanced datasets demonstrate the effectiveness of the proposed method.