Original article was published on Artificial Intelligence on Medium
The experiments are conducted for object detection as well as for the task of image classification to demonstrate the versatility of the proposed architecture.
The ResNet-FPN backbone model is replaced with the RetinaNet detector for the task of object detection. The model is evaluated on the COCO test-dev dataset and is trained on the train2017 split.
- The following results (Figure 6) demonstrate that SpineNet models outperform other popular detectors by large margins. The largest SpineNet-190 achieves the highest 52.1% AP. Generally, SpineNet architectures require a fewer number of FLOPs and a lesser number of parameters making the models computationally less expensive.
- The following results (figure 7) on COCO val2017 demonstrate that SpineNet-49 requires ~10% lesser FLOPs and AP has improved to 40.8 as opposed to 37.8 in R50-FPN.
- RetinaNet model adopting SpineNet backbones achieves a higher AP score with considerably less number of FLOPs as compared to ResNet-FPN and NAS-FPN backbones (figure 8).
SpineNet is trained on two datasets- ImageNet ILSVRC-2012 and iNaturalist-2017 for the purpose of image classification.
- On ImageNet, the Top-1% and Top-5% accuracy are at par with ResNet and in addition to that, the number of FLOPs is considerably reduced.
- On iNaturalist, ResNet is outperformed by SpineNet with a large margin of 5% along with a reduction in FLOPs.
The above results demonstrate that SpineNet not only works better for object detection but also proves to be versatile enough for other visual learning tasks like image classification.