AI Paper Atlas

Research map / Detection and segmentation / CNN features

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

Khurram Azeem Hashmi, Goutham Kallempudi, Didier Stricker, Muhammad Zeshan Afzal

ICCV 2023 · Detection and segmentation › CNN features · approach: RGB-D salient object detection · 109 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add FeatEnHancer to FQ R-CNN instead of LLIE preprocessingFQ R-CNN · ExDarkmAP50: 74.5 -> 86.3Improved
add FeatEnHancer to RetinaNetRetinaNet · ExDarkmAP50: 72.1 -> 72.6Improved
add FeatEnHancer to RetinaNetRetinaNet · DARK FACEAP50: 47.3 -> 47.2No clear effect
add FeatEnHancer to FQ R-CNNFQ R-CNN · DARK FACEAP50: 67.5 -> 69.0Improved
add FeatEnHancer to DeepLabV3+DeepLabV3+ · ACDC nighttimemIoU: 45.7 -> 54.9Improved
preprocess frames with existing LLIE methodsSELSA · DarkVisionmAP: 32.8 -> 7.83 (Zero-DCE, illumination 3.2)Hurt
add FeatEnHancer to SELSASELSA · DarkVision illumination 3.2mAP: 32.8 -> 34.6Improved
use scale-aware attentional feature aggregation (SAFA) instead of averaging or skip connections (ablation)FeatEnHancer · ExDarkmAP: 70.3 -> 72.6Improved
apply SAFA first then skip connection rather than reversed order (ablation)FeatEnHancer · ExDarkmAP: 70.9 -> 72.6Improved
use convolutional downsampling instead of pooling or interpolation (ablation)FeatEnHancer · ExDarkmAP: 70.7 -> 72.6Improved
use scales (4, 8) instead of (8, 16) (ablation)FeatEnHancer · ACDCmIoU: 45.6 -> 54.9Improved
increase attention blocks N from 8 to 12 (ablation)SAFA · ExDarkmAP: 72.6 -> 72.4No clear effect

Later papers that compared with this method

4 later accepted papers report FeatEnHancer as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy