- FasterRCNN for object detection
- MaskRCNN for instance segmentation
- KeypointRCNN for human keypoint detection
Baseline (left) vs Compressed (right) model inference.
To underscore the practical advantages of NORTON, an experiment was meticulously conducted, involving a direct comparison between a baseline model and a compressed model, both tailored for object detection tasks. Leveraging the FasterRCNN_ResNet50_FPN architecture on a RTX 3060 GPU, the experiment robustly highlights the substantial performance enhancement achieved by NORTON. The accompanying GIFs offer a vivid visual depiction: the baseline model showcases an inference speed of approximately 9 FPS, while the NORTON-compressed model boasts a remarkable twofold acceleration in throughput. This notable disparity effectively showcases NORTON's efficacy and scalability, firmly establishing its relevance and applicability across diverse deployment scenarios.
Note: For replication of this experiment, please refer to detection/README.md.
