AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

InfMAE: A Foundation Model in The Infrared Modality

Fangcen Liu, Chenqiang Gao, Yaming Zhang, Junjie Guo, Jinghao Wang, Deyu Meng

ECCV 2024 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Masked autoencoder pretraining · 28 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 information-aware masking and multi-scale encoder together (ablation)InfMAE · MSRS-inf segmentation (UperNet)mIoU (%): 71.4 -> 74.3Improved
add information-aware masking alone (ablation)InfMAE · M3FD-inf detection (Mask R-CNN)AP50 (%): 81.5 -> 78.9Hurt
add multi-scale encoder alone (ablation)InfMAE · M3FD-inf detection (Mask R-CNN)AP50 (%): 81.5 -> 86.3Improved
use shallow infrared decoder (depth 2) instead of deeper decoders (ablation)InfMAE · MSRS-inf segmentation (UperNet)mIoU (%): 72.9 -> 74.3 (vs depth 4)Improved
increase masking sampling stride from 14 to 4 (ablation)InfMAE · MSRS-inf segmentation (UperNet)mIoU (%): 70.4 -> 74.3Improved
decrease masking stride from 4 to 2 (ablation)InfMAE · MSRS-inf segmentation (UperNet)mIoU (%): 74.3 -> 74.2No clear effect
extend pre-training from 400 to 1600 epochs (ablation)InfMAE · MSRS-inf segmentation (UperNet)mIoU (%): 74.3 -> 74.9Improved
extend pre-training from 400 to 1600 epochs (ablation)InfMAE · M3FD-inf detection (Mask R-CNN)mAP (%): 56.2 -> 56.0No clear effect
scale pre-training data from 100K (Inf10) to 300K (Inf30) (ablation)InfMAE · MSRS-inf segmentation (UperNet)mIoU (%): 69.1 -> 74.3Improved
scale pre-training data from curated 300K to unprocessed 500K (ablation)InfMAE · MSRS-inf segmentation (UperNet)mIoU (%): 74.3 -> 73.0Hurt
pre-train vanilla MAE on infrared Inf30 instead of visible IN1K-30 (ablation)Vanilla MAE · MSRS-inf segmentation (UperNet)mIoU (%): 66.7 -> 71.6Improved
self-supervised pre-training vs supervised training from scratch (ablation)InfMAE encoder · MSRS-inf segmentation (UperNet)mIoU (%): 61.1 -> 74.3Improved

Later papers that compared with this method

1 later accepted paper reports InfMAE as a baseline in their results tables; 1 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