N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras
This work addresses the problem of deploying event-based object recognition in real-world conditions for robotics or vision applications, but it is incremental as it builds on existing datasets and methods.
The authors introduced N-ImageNet, a large-scale dataset for robust, fine-grained object recognition with event cameras, and showed that pretraining on it improves classifier performance and enables learning with few labeled data.
We introduce N-ImageNet, a large-scale dataset targeted for robust, fine-grained object recognition with event cameras. The dataset is collected using programmable hardware in which an event camera consistently moves around a monitor displaying images from ImageNet. N-ImageNet serves as a challenging benchmark for event-based object recognition, due to its large number of classes and samples. We empirically show that pretraining on N-ImageNet improves the performance of event-based classifiers and helps them learn with few labeled data. In addition, we present several variants of N-ImageNet to test the robustness of event-based classifiers under diverse camera trajectories and severe lighting conditions, and propose a novel event representation to alleviate the performance degradation. To the best of our knowledge, we are the first to quantitatively investigate the consequences caused by various environmental conditions on event-based object recognition algorithms. N-ImageNet and its variants are expected to guide practical implementations for deploying event-based object recognition algorithms in the real world.