AI Paper Atlas

Research map / Detection and segmentation / CNN features

DETR is Secretly a Multispectral Detector: Zero-Parameter Adaptation via Semantic Alignment

Xiangyang Li, Zhiwei Jiang, Wushuai Jin, Pengyang Niu, Chunna Tian, Lingqiao Liu

ECCV 2026 · Detection and segmentation › CNN features · approach: RGB-D salient object detection · 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 asymmetric input organization (AIO) (ablation)RT-DETR, query IR memory RGB · FLIRmAP (%): 33.88 -> 47.62Improved
add asymmetric input organization (AIO) (ablation)RT-DETR, query RGB memory IR · FLIRmAP (%): 45.19 -> 49.21Improved
add spatial semantic alignment (ablation)AIO, query IR memory RGB · FLIRmAP (%): 47.62 -> 47.95Improved
add channel semantic alignment (ablation)AIO, query IR memory RGB · FLIRmAP (%): 47.62 -> 47.80Improved
add both spatial and channel alignment (ablation)AIO, query IR memory RGB · FLIRmAP (%): 47.62 -> 48.16Improved
add spatial semantic alignment (ablation)AIO, query RGB memory IR · FLIRmAP (%): 49.21 -> 49.48Improved
add channel semantic alignment (ablation)AIO, query RGB memory IR · FLIRmAP (%): 49.21 -> 49.58Improved
add both spatial and channel alignment (ablation)AIO, query RGB memory IR · FLIRmAP (%): 49.21 -> 49.82Improved
use RGB as query and IR as memory instead of reverseZPA-MDETR · FLIRmAP (%): 48.16 -> 49.82Improved
use IR as query and RGB as memory instead of reverseZPA-MDETR · M3FDmAP (%): 48.39 -> 50.58Improved
use RGB as query and IR as memory instead of reverseZPA-MDETR · LLVIPmAP (%): 64.88 -> 69.14Improved
use RGB query IR memory instead of reverseZPA-MDETR · RGBTDronePersonmAP (%): 20.08 -> 21.01Improved

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