Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection

TL;DR

This paper introduces a hierarchical feature refinement network for fusing event data and frame images to improve object detection, especially under challenging conditions, outperforming state-of-the-art methods.

Contribution

The proposed coarse-to-fine fusion module with bidirectional interaction and adaptive refinement effectively combines heterogeneous modalities for enhanced detection.

Findings

Outperforms state-of-the-art by 8.0% on DSEC dataset

Shows significantly improved robustness under image corruption

Effective fusion of event and frame data for object detection

Abstract

In frame-based vision, object detection faces substantial performance degradation under challenging conditions due to the limited sensing capability of conventional cameras. Event cameras output sparse and asynchronous events, providing a potential solution to solve these problems. However, effectively fusing two heterogeneous modalities remains an open issue. In this work, we propose a novel hierarchical feature refinement network for event-frame fusion. The core concept is the design of the coarse-to-fine fusion module, denoted as the cross-modality adaptive feature refinement (CAFR) module. In the initial phase, the bidirectional cross-modality interaction (BCI) part facilitates information bridging from two distinct sources. Subsequently, the features are further refined by aligning the channel-level mean and variance in the two-fold adaptive feature refinement (TAFR) part. We conducted extensive experiments on two benchmarks: the low-resolution PKU-DDD17-Car dataset and the high-resolution DSEC dataset. Experimental results show that our method surpasses the state-of-the-art by an impressive margin of $\textbf{8.0}\%$ on the DSEC dataset. Besides, our method exhibits significantly better robustness (\textbf{69.5}\% versus \textbf{38.7}\%) when introducing 15 different corruption types to the frame images. The code can be found at the link (https://github.com/HuCaoFighting/FRN).