Other

TS2Vec

Timeline (last 90 days)

Oct 21

TS2Vec is a time-series self-supervised method proposed in 2022 that performs self-supervised pretraining independently on each dataset followed by linear probing.

Unverified50%

Oct 21

Under the frozen-encoder linear probing setting, TS2Vec-FM surpasses TS2Vec trained separately on each target dataset.

Unverified50%

All Facts (2)

Unverified

TS2Vec is a time-series self-supervised method proposed in 2022 that performs self-supervised pretraining independently on each dataset followed by linear probing.

50%Unverified

Under the frozen-encoder linear probing setting, TS2Vec-FM surpasses TS2Vec trained separately on each target dataset.

50%

Source Articles

TS2Vec Becomes a Foundation Model: 1.6M-Parameter Frozen Encoder Approaches SOTAOct 21