Structured Sparse R-CNN for Direct Scene Graph Generation
arXiv:2106.10815
Abstract
Scene graph generation (SGG) is to detect object pairs with their relations in an image. Existing SGG approaches often use multi-stage pipelines to decompose this task into object detection, relation graph construction, and dense or dense-to-sparse relation prediction. Instead, from a perspective on SGG as a direct set prediction, this paper presents a simple, sparse, and unified framework, termed as Structured Sparse R-CNN. The key to our method is a set of learnable triplet queries and a structured triplet detector which could be jointly optimized from the training set in an end-to-end manner. Specifically, the triplet queries encode the general prior for object pairs with their relations, and provide an initial guess of scene graphs for subsequent refinement. The triplet detector presents a cascaded architecture to progressively refine the detected scene graphs with the customized dynamic heads. In addition, to relieve the training difficulty of our method, we propose a relaxed and enhanced training strategy based on knowledge distillation from a Siamese Sparse R-CNN. We perform experiments on several datasets: Visual Genome and Open Images V4/V6, and the results demonstrate that our method achieves the state-of-the-art performance. In addition, we also perform in-depth ablation studies to provide insights on our structured modeling in triplet detector design and training strategies. The code and models are made available at https://github.com/MCG-NJU/Structured-Sparse-RCNN.
Camera-ready version of CVPR 2022
References in corpus (8)
- Distilling the Knowledge in a Neural Network
- Decoupled Weight Decay Regularization
- Deformable DETR: Deformable Transformers for End-to-End Object Detection
- The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
- Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
- Long-tail learning via logit adjustment
- CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning
- Unbiased Teacher for Semi-Supervised Object Detection