FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision

Khurram Azeem Hashmi1,2, Goutham Kallempudi2, Didier Stricker1,2, Muhammad Zeshan Afzal1,2,

ICCV 2023

1DFKI, 2 RPTU Kaiserslautern-Landau
CVF Paper Supplementary Material arXiv Code

Abstract

Extracting useful visual cues for the downstream tasks is especially challenging under low-light vision. Prior works create enhanced representations by either correlating visual quality with machine perception or designing illumination-degrading transformation methods that require pre-training on synthetic datasets. We argue that optimizing enhanced image representation pertaining to the loss of the downstream task can result in more expressive representations. Therefore, in this work, we propose a novel module, FeatEnHancer, that hierarchically combines multiscale features using multi-headed attention guided by task-related loss function to create suitable representations. Furthermore, our intra-scale enhancement improves the quality of features extracted at each scale or level, as well as combines features from different scales in a way that reflects their relative importance for the task at hand. FeatEnHancer is a general-purpose plug-and-play module and can be incorporated into any low-light vision pipeline. We show with extensive experimentation that the enhanced representation produced with FeatEnHancer significantly and consistently improves results in several dark vision tasks, including dark object detection (+5.7 mAP on ExDark), face detection (+1.5 mAP on DARK FACE), nighttime semantic segmentation (+5.1 mIoU on ACDC ), and video object detection (+1.8 mAP on DarkVision), highlighting the effectiveness of enhancing hierarchical features under low-light vision.

Method Overview

Network architecture of the proposed FeatEnHancer employed in a downstream vision task. Our FeatEnHancer takes a low-light image and adaptively boosts its semantic representation by enriching task-related hierarchical features.

BibTeX

@InProceedings{Hashmi_2023_ICCV,
    author    = {Hashmi, Khurram Azeem and Kallempudi, Goutham and Stricker, Didier and Afzal, Muhammad Zeshan},
    title     = {FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2023},
    pages     = {6725-6735}
}