AI Paper Atlas

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

Time2Agri: Temporal Pretext Tasks for Agricultural Monitoring

Moti Rattan Gupta, Anupam Sobti

AAAI 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervision in supervised pipelines · 3 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
pretrain with future-frame prediction instead of MAEViT-S · SICKLE crop type mappingIoU: 0.67138 -> 0.69595Improved
pretrain with temporal frequency prediction instead of MAEViT-S · SICKLE crop yield (in-season)MAPE: 0.32701 -> 0.30727Improved
pretrain with temporal frequency prediction instead of FF for crop typeViT-S · SICKLE crop type mappingIoU: 0.69595 -> 0.61976Hurt
use temporal pretext tasks vs supervised baselines on date predictionFF, FP, TD · SICKLE sowing/transplanting/harvest dateMAPE: harvest: 0.047596 (UNet3D) vs 0.068059 (FF)No clear effect
pretrain regionally (Tamil Nadu) rather than nationally (India) with FF (ablation)FF · SICKLE crop type mappingIoU: 0.60483 -> 0.69595Improved
pretrain regionally rather than nationally with FF (ablation)FF · SICKLE crop yield (in-season)MAPE: 0.37407 -> 0.32516Improved
restrict FF bitemporal pairs to exactly 3 months apart (ablation)FF · SICKLE crop type mappingIoU: 0.69595 -> 0.58737Hurt
use 3 and 6 month gaps for FF pairs (ablation)FF · SICKLE crop yield (region)MAPE: 0.36765 -> 0.33411Improved
use 3, 6 and 9 month gaps for FF pairs (ablation)FF · SICKLE harvest dateMAPE: 0.068059 -> 0.05391Improved
use FF pretraining instead of MAEViT-S with supervised pretraining on France then India finetune · FTW IndiaIoU: 0.465626 -> 0.490628Improved
use FF pretraining instead of MAE when supervised on India onlyViT-S · FTW India (India-only)IoU: 0.497104 -> 0.492768No clear effect
use FF instead of global RSFMs DoFA and CopernicusFMViT-S · SICKLE crop type mappingIoU: 0.58363 / 0.57229 -> 0.69595Improved

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