AI Paper Atlas

Research map / Time series / Foundation models for time series

Divide and Contrast: Learning Robust Temporal Features without Augmentation

Abdul-Kazeem Shamba, Kerstin Bach, Gavin Taylor

ICML 2026 · Time series › Foundation models for time series · approach: Time series representation learning · 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 50% overlap between sub-blocks (ablation)Di-COT · Large datasetsaverage accuracy (%): 81.22 -> 83.07Improved
add 50% overlap between sub-blocks (ablation)Di-COT · UCRaverage accuracy (%): 81.12 -> 81.33Improved
add 50% overlap between sub-blocks (ablation)Di-COT · UEAaverage accuracy (%): 70.13 -> 71.24Improved
add temperature scaling (tau=0.07) (ablation)Di-COT · Large, UEA, UCRaverage accuracy (%): 82.47 -> 83.07 (Large); no change on UCR (81.33)Mixed
sample sub-block splits uniformly per iteration instead of a fixed global split (ablation)Di-COT · UEAaverage accuracy (%): 69.69 -> 71.24Improved
sample sub-block splits uniformly per iteration instead of a fixed global split (ablation)Di-COT · UCRaverage accuracy (%): 81.32 -> 81.33No clear effect
use preceding sub-block as positive instead of shuffled sub-blocks (ablation)Di-COT · Large datasetsaverage accuracy (%): 81.80 -> 83.07Improved
use preceding instead of next sub-block contrast (ablation)Di-COT · Large datasetsaverage accuracy (%): 82.22 -> 83.07Improved
use InceptionTime backbone instead of FCN or ResNet (ablation)Di-COT · Large datasetsaverage accuracy (%): 80.11 (ResNet) -> 83.07Improved
add non-linear projection layer (ablation)Di-COT · Large datasetsaverage accuracy (%): 83.07 -> 81.85Hurt
contrast sub-blocks instead of every timestep (Di-COT vs CaTT)temporal contrastive learning · UCR (124 datasets)average accuracy (%): 77.42 -> 81.33Improved
contrast sub-blocks instead of every timestep (Di-COT vs CaTT)temporal contrastive learning · six large-scale datasets, training timetraining time (hours): 3.47 -> 2.88Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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