Abstract:Object detection is essential to many perception algorithms used in modern robotics applications. Unfortunately, the existing models share a tendency to assign high confidence scores for out-of-distribution (OOD) samples. Although OOD detection has been extensively studied in recent years by the computer vision (CV) community, most proposed solutions apply only to the image recognition task. Real-world applications such as perception in autonomous vehicles struggle with far more complex challenges than classification. In our work, we focus on the prevalent field of object detection, introducing Neuron Activation PaTteRns for out-of-distribution samples detection in Object detectioN (NAPTRON). Performed experiments show that our approach outperforms state-of-the-art methods, without the need to affect in-distribution (ID) performance. By evaluating the methods in two distinct OOD scenarios and three types of object detectors we have created the largest open-source benchmark for OOD object detection.
Abstract:Deep neural networks (DNN) have outstanding performance in various applications. Despite numerous efforts of the research community, out-of-distribution (OOD) samples remain significant limitation of DNN classifiers. The ability to identify previously unseen inputs as novel is crucial in safety-critical applications such as self-driving cars, unmanned aerial vehicles and robots. Existing approaches to detect OOD samples treat a DNN as a black box and assess the confidence score of the output predictions. Unfortunately, this method frequently fails, because DNN are not trained to reduce their confidence for OOD inputs. In this work, we introduce a novel method for OOD detection. Our method is motivated by theoretical analysis of neuron activation patterns (NAP) in ReLU based architectures. The proposed method does not introduce high computational workload due to the binary representation of the activation patterns extracted from convolutional layers. The extensive empirical evaluation proves its high performance on various DNN architectures and seven image datasets. ion.
Abstract:The quality of training datasets for deep neural networks is a key factor contributing to the accuracy of resulting models. This is even more important in difficult tasks such as object detection. Dealing with errors in these datasets was in the past limited to accepting that some fraction of examples is incorrect or predicting their confidence and assigning appropriate weights during training. In this work, we propose a different approach. For the first time, we extended the confident learning algorithm to the object detection task. By focusing on finding incorrect labels in the original training datasets, we can eliminate erroneous examples in their root. Suspicious bounding boxes can be re-annotated in order to improve the quality of the dataset itself, thus leading to better models without complicating their already complex architectures. We can effectively point out 99\% of artificially disturbed bounding boxes with FPR below 0.3. We see this method as a promising path to correcting well-known object detection datasets.
Abstract:Noise reduction is one the most important and still active research topic in low-level image processing due to its high impact on object detection and scene understanding for computer vision systems. Recently, we can observe a substantial increase of interest in the application of deep learning algorithms in many computer vision problems due to its impressive capability of automatic feature extraction and classification. These methods have been also successfully applied in image denoising, significantly improving the performance, but most of the proposed approaches were designed for Gaussian noise suppression. In this paper, we present a switching filtering design intended for impulsive noise removal using deep learning. In the proposed method, the impulses are identified using a novel deep neural network architecture and noisy pixels are restored using the fast adaptive mean filter. The performed experiments show that the proposed approach is superior to the state-of-the-art filters designed for impulsive noise removal in digital color images.
Abstract:Machine learning (ML) applications generate a continuous stream of success stories from various domains. ML enables many novel applications, also in a safety-related context. With the advent of Autonomous Driving, ML gets used in automotive domain. In such a context, ML-based systems are safety-related. In the automotive industry, the applicable functional safety standard is ISO 26262, which it does not cover specific aspects of ML. In a safety-related ML project, all ISO 26262 work products are typically necessary and have to be delivered. However, specific aspects of ML (like data set requirements, special analyses for ML) must be addressed within some work products. In this paper, we propose how the organization of a ML project could be done according to ISO 26262 phases, sub-phases and work-products.