AI Paper Atlas

Research map / Detection and segmentation / CNN features

TorchAdapt: Towards Light-Agnostic Real-Time Visual Perception

Khurram Azeem Hashmi, Karthik Palyakere Suresh, Didier Stricker, Muhammad Zeshan Afzal

ICCV 2025 · Detection and segmentation › CNN features · approach: Convolution-transformer backbones · 0 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 Torch module to the baseline (ablation)YOLOv3 · ExDark object detection (low-light)mAP50: 78.8 -> 79.1Improved
add Torch module to the baseline (ablation)RTMDet-Ins-tiny · LIS instance segmentation (low-light)SegAP: 46.0 -> 51.1Improved
add Adapt module on top of Torch (ablation)YOLOv3 · COCO+ExDark object detection (light-agnostic)mAP50: 62.9 -> 63.5Improved
add Adapt module on top of Torch (ablation)RTMDet-Ins-tiny · LIS instance segmentation (low-light)SegAP: 51.1 -> 53.3Improved
add illumination scaling without Adapt module (ablation)YOLOv3 · COCO+ExDark object detection (light-agnostic)mAP50: 62.9 -> 62.7Hurt
add illumination scaling without Adapt module (ablation)RTMDet-Ins-tiny · COCO+LIS instance segmentation (light-agnostic)SegAP: 34.8 -> 34.1Hurt
add illumination scaling to Torch + Adapt (ablation)YOLOv3 · COCO+ExDark object detection (light-agnostic)mAP50: 63.5 -> 64.0Improved
add illumination scaling to Torch + Adapt (ablation)RTMDet-Ins-tiny · COCO+LIS instance segmentation (light-agnostic)SegAP: 36.2 -> 36.6Improved
raise maximum scale factor kappa from 3 to 5 (ablation)TorchAdapt · COCO+ExDark object detection (light-agnostic)mAP50: 64.0 -> 61.1Hurt
use gamma curve instead of ISP darkening to synthesize low-light view (ablation)TorchAdapt · COCO+ExDark object detection (light-agnostic)mAP50: 61.7 -> 64.0Improved
apply off-the-shelf LLIE (Zero-DCE) as preprocessing instead of noneYOLOv3 · COCO+ExDark object detection (light-agnostic)mAP50: 62.4 -> 57.6Hurt
train Zero-DCE end-to-end on the task instead of off-the-shelfYOLOv3 · COCO+ExDark object detection (light-agnostic)mAP50: 57.6 -> 62.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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