AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities

Xu Zheng, Yuanhuiyi Lyu, Lin Wang

ECCV 2024 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 14 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 semantic KD loss L_se (RGB only) (ablation)Any2Seg (SegFormer-B0) · DELIVER RGBmIoU: 51.39 -> 53.03Improved
add L_se with R+E input (ablation)Any2Seg (SegFormer-B0) · DELIVER R+EmAcc: mAcc 60.36 -> 60.20; mIoU 52.21 -> 53.11Mixed
add inter-modal correlation KD L_cr (R+D) (ablation)Any2Seg (SegFormer-B0) · DELIVER R+DmIoU: +0.83 mIoU, +2.46 AccImproved
add all three losses vs base loss only (ablation)Any2Seg (SegFormer-B0) · DELIVER R+D (MSS)mIoU: 61.93 -> 63.74Improved
add fine-grained feature selection to MFF (ablation)MFF (SegFormer-B0) · DELIVER 4 modalities (MISS)mIoU: 35.47 -> 44.49Improved
add fine-grained feature selection to MFF (ablation)MFF (SegFormer-B0) · MCubeS 4 modalities (MSS)mIoU: 39.63 -> 42.49Improved
add residual connection without selection (ablation)MFF (SegFormer-B0) · MCubeS 4 modalities (MISS)mIoU: 27.88 -> 25.10Hurt
add residual connection to selection (ablation)MFF (SegFormer-B0) · DELIVER 4 modalities (MISS)mIoU: 44.49 -> 47.79Improved
replace CMNeXt fusion with Any2Seg (LSCD+MFF)DELIVER system-level MISS · DELIVER MISS meanmIoU: 25.25 -> 45.04Improved
Any2Seg vs CMNeXt on R+LAny2Seg · DELIVER MSS R+LmIoU: 58.04 -> 57.92Hurt
Any2Seg in sparse modality (Event, LiDAR only) inputsAny2Seg · DELIVER system-level MISSmIoU: L: 0.72 -> 0.31Mixed

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