Overlapped 10 1 On Pascal Voc 2012
평가 지표
mIoU
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | mIoU |
|---|---|
| learning-without-forgetting | 4.8 |
| mitigating-background-shift-in-class | 77.19 |
| ssul-semantic-segmentation-with-unknown-label | 59.25 |
| sats-self-attention-transfer-for-continual | 69.27 |
| continual-semantic-segmentation-via-repulsion | 25.1 |
| incremental-learning-techniques-for-semantic | 5.5 |
| representation-compensation-networks-for | 34.3 |
| tackling-catastrophic-forgetting-and | 40.83 |
| sats-self-attention-transfer-for-continual | 61.6 |
| plop-learning-without-forgetting-for | 30.45 |
| modeling-the-background-for-incremental | 20.1 |
| attribution-aware-weight-transfer-a-warm | 60.7 |
| ssul-semantic-segmentation-with-unknown-label | 64.12 |