{"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/reltransformer-balancing-the-visual","title":"RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition","arxiv_id":"2104.11934","date":"2021-04-24","proceeding":"CVPR 2022 1","authors":["Jun Chen","Aniket Agarwal","Sherif Abdelkarim","Deyao Zhu","Mohamed Elhoseiny"],"abstract":"The visual relationship recognition (VRR) task aims at understanding the pairwise visual relationships between interacting objects in an image. These relationships typically have a long-tail distribution due to their compositional nature. This problem gets more severe when the vocabulary becomes large, rendering this task very challenging. This paper shows that modeling an effective message-passing flow through an attention mechanism can be critical to tackling the compositionality and long-tail challenges in VRR. The method, called RelTransformer, represents each image as a fully-connected scene graph and restructures the whole scene into the relation-triplet and global-scene contexts. It directly passes the message from each element in the relation-triplet and global-scene contexts to the target relation via self-attention. We also design a learnable memory to augment the long-tail relation representation learning. Through extensive experiments, we find that our model generalizes well on many VRR benchmarks. Our model outperforms the best-performing models on two large-scale long-tail VRR benchmarks, VG8K-LT (+2.0% overall acc) and GQA-LT (+26.0% overall acc), both having a highly skewed distribution towards the tail. It also achieves strong results on the VG200 relation detection task. Our code is available at https://github.com/Vision-CAIR/RelTransformer.","url_abs":"https://arxiv.org/abs/2104.11934v2","url_pdf":"https://arxiv.org/pdf/2104.11934v2.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":"reltransformer-balancing-the-visual","repo_url":"https://github.com/Vision-CAIR/RelTransformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":null,"task_name":"Triplet"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"visual-relationship-detection","task_name":"Visual Relationship Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.11934","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}