Trident Pyramid Networks: The importance of processing at the feature pyramid level for better object detection
This work addresses the need for more effective feature pyramid processing in object detection systems, offering incremental improvements over existing methods.
The authors tackled the problem of improving object detection by proposing a deeper neck architecture called Trident Pyramid Network (TPN) that balances communication-based and self-processing in feature pyramids, resulting in a 0.5 AP gain over BiFPN on COCO and a 1.7 AP improvement over ResNet-101+FPN with similar computation using ResNet-50+TPN.
Feature pyramids have become ubiquitous in multi-scale computer vision tasks such as object detection. Given their importance, a computer vision network can be divided into three parts: a backbone (generating a feature pyramid), a neck (refining the feature pyramid) and a head (generating the final output). Many existing networks operating on feature pyramids, named necks, are shallow and mostly focus on communication-based processing in the form of top-down and bottom-up operations. We present a new neck architecture called Trident Pyramid Network (TPN), that allows for a deeper design and for a better balance between communication-based processing and self-processing. We show consistent improvements when using our TPN neck on the COCO object detection benchmark, outperforming the popular BiFPN baseline by 0.5 AP, both when using the ResNet-50 and the ResNeXt-101-DCN backbone. Additionally, we empirically show that it is more beneficial to put additional computation into the TPN neck, rather than into the backbone, by outperforming a ResNet-101+FPN baseline with our ResNet-50+TPN network by 1.7 AP, while operating under similar computation budgets. This emphasizes the importance of performing computation at the feature pyramid level in modern-day object detection systems. Code is available at https://github.com/CedricPicron/TPN .