YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
핵심 개념
Proposing Programmable Gradient Information (PGI) to address information bottleneck in deep networks and introducing Generalized Efficient Layer Aggregation Network (GELAN) for improved object detection.
YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934, 2020.
Reversible column networks. In International Conference on Learning Representations (ICLR), 2023.
End-to-end object detection with transformers. In Proceedings of the European Conference on Computer Vision (ECCV), 2020.
AP-loss for accurate one-stage object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 43(11):3782–3798, 2020.
SdAE: Self-distillated masked autoencoder. In Proceedings of the European Conference on Computer Vision (ECCV), 2022.
YOLO-MS: rethinking multi-scale representation learning for real-time object detection. arXiv preprint arXiv:230
인용구
"Existing methods ignore a fact that when input data undergoes layer-by-layer feature extraction and spatial transformation, large amount of information will be lost."
"We proposed the concept of programmable gradient information (PGI) to cope with the various changes required by deep networks to achieve multiple objectives."
"The results show that GELAN only uses conventional convolution operators to achieve better parameter utilization than the state-of-the-art methods developed based on depth-wise convolution."