{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/trident-pyramid-networks-the-importance-of","title":"Trident Pyramid Networks: The importance of processing at the feature pyramid level for better object detection","arxiv_id":"2110.04004","date":"2021-10-08","proceeding":null,"authors":["Cédric Picron","Tinne Tuytelaars"],"abstract":"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 .","url_abs":"https://arxiv.org/abs/2110.04004v3","url_pdf":"https://arxiv.org/pdf/2110.04004v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"trident-pyramid-networks-the-importance-of","repo_url":"https://github.com/cedricpicron/detseg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bifpn","method_name":"BiFPN"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"tpn","method_name":"TPN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.04004","atlas_url":"https://app.syntology.ai/?focus=2110.04004","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}