WCCNet: Wavelet-context Cooperative Network for Efficient Multispectral Pedestrian Detection

TL;DR

WCCNet is an efficient multispectral pedestrian detection framework that uses asymmetric feature extraction and a novel fusion module to improve accuracy while reducing computational costs.

Contribution

The paper introduces WCCNet, featuring a dual-stream asymmetric backbone, Mixture of Wavelet Experts, and a crossmodal fusion module for enhanced multispectral pedestrian detection.

Findings

Outperforms state-of-the-art methods on KAIST and FLIR benchmarks.

Achieves higher accuracy with lower computational cost.

Effectively fuses multispectral features for improved detection.

Abstract

Multispectral pedestrian detection is essential to various tasks especially autonomous driving, for which both the accuracy and computational cost are of paramount importance. Most existing approaches treat RGB and infrared modalities equally. They typically adopt two symmetrical backbones for multimodal feature extraction, which ignore the substantial differences between modalities and bring great difficulty for the reduction of the computational cost as well as effective crossmodal fusion. In this work, we propose a novel and efficient framework named Wavelet-context Cooperative Network (WCCNet), which differentially extracts complementary features across spectra with low computational cost and further fuses these diverse features based on their spatially relevant cross-modal semantics. WCCNet explores an asymmetric but cooperative dual-stream backbone, in which WCCNet utilizes generic neural layers for texture-rich feature extraction from RGB modality, while proposing Mixture of Wavelet Experts (MoWE) to capture complementary frequency patterns of infrared modality. By assessing multispectral environmental context, MoWE generates routing scores to selectively activate specific learnable Adaptive DWT (ADWT) layers, alongside shared static DWT, which are both considerible lightwight and efficient to significantly reduce computational overhead and facilitate subsequent fusion. To further fuse these multispectral features with significant semantic differences, we elaborately design the crossmodal rearranging fusion module (CMRF), which aims to mitigate misalignment and merge semantically complementary features in spatially-related local regions to amplify the crossmodal reciprocal information. Results from comprehensive evaluations on KAIST and FLIR benchmarks indicate that WCCNet outperforms state-of-the-art methods with considerable computational efficiency and competitive accuracy.