Hierarchical LSTM with MoE
Reported on 6 benchmarks across 2 tasks · 1 paper · 6 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Computer Vision6 results
- Global Average Precision· 2019-02-27SOTA81.1
- Hit@1· 2019-02-27SOTA86.8best: 87.7 (DCGN (self-attention graph pooling))
- mAP· 2019-02-27SOTA41.4
- Global Average Precision· 2019-02-27SOTA81.1
- Hit@1· 2019-02-27SOTA86.8best: 87.7 (DCGN (self-attention graph pooling))
- mAP· 2019-02-27SOTA41.4