AI Paper Atlas

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

DSeq-JEPA: Discriminative Sequential Joint-Embedding Predictive Architecture

Xiangteng He, Shunsuke SAKAI, Shivam Chandhok, Sara Beery, Kun yuan, Nicolas Padoy, Tatsuhito Hasegawa, Leonid Sigal

ECCV 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 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
add discriminative sequential prediction to I-JEPAI-JEPA · ImageNet-1K linear probe (ViT-B/16)top-1 accuracy: 72.4 -> 73.5Improved
add discriminative sequential prediction to I-JEPAI-JEPA · ImageNet-1K full fine-tune (ViT-B/16)top-1 accuracy: 83.5 -> 84.0Improved
add discriminative sequential prediction to I-JEPAI-JEPA · ImageNet-1K linear probe (ViT-H/16)top-1 accuracy: 81.1 -> 82.4Improved
add discriminative sequential prediction to C-JEPAC-JEPA · ImageNet-1K linear probe (ViT-B/16)top-1 accuracy: 73.5 -> 73.8Improved
add discriminative sequential prediction to I-JEPAI-JEPA · CUB-200-2011 and Cars (ViT-B/16)top-1 accuracy: +0.9 on CUB, +1.4 on CarsImproved
add discriminative region selection and sequential prediction together vs either alone (ablation)DSeq-JEPA · ImageNet-1K linear probe (ViT-B/16)top-1 accuracy: 72.4 -> 73.5Improved
add sequential prediction alone with uniform sampling (ablation)I-JEPA · ImageNet-1K linear probe (ViT-B/16)top-1 accuracy: 72.4 -> 72.3Hurt
add discriminative selection alone with flat prediction (ablation)I-JEPA · ImageNet-1K linear probe (ViT-B/16)top-1 accuracy: 72.4 -> 72.0Hurt
use discriminative order rather than random order (ablation)DSeq-JEPA · ImageNet-1K linear probe (ViT-B/16)top-1 accuracy: 71.7 -> 73.5Improved
use discriminative order rather than spatial order (ablation)DSeq-JEPA · ImageNet-1K linear probe (ViT-B/16)top-1 accuracy: 72.7 -> 73.5Improved
use forward discriminative order rather than inverse order (ablation)DSeq-JEPA · ImageNet-1K linear probe (ViT-B/16)top-1 accuracy: 71.3 -> 73.5Improved
predict all Top-5 regions rather than truncating at Top-3 (ablation)DSeq-JEPA · ImageNet-1K linear probe (ViT-B/16)top-1 accuracy: 73.0 -> 73.5Improved

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