PETDet: Proposal Enhancement for Two-Stage Fine-Grained Object Detection
arXiv:2312.10515 · doi:10.1109/TGRS.2023.3343453
Abstract
Fine-grained object detection (FGOD) extends object detection with the capability of fine-grained recognition. In recent two-stage FGOD methods, the region proposal serves as a crucial link between detection and fine-grained recognition. However, current methods overlook that some proposal-related procedures inherited from general detection are not equally suitable for FGOD, limiting the multi-task learning from generation, representation, to utilization. In this paper, we present PETDet (Proposal Enhancement for Two-stage fine-grained object detection) to better handle the sub-tasks in two-stage FGOD methods. Firstly, an anchor-free Quality Oriented Proposal Network (QOPN) is proposed with dynamic label assignment and attention-based decomposition to generate high-quality oriented proposals. Additionally, we present a Bilinear Channel Fusion Network (BCFN) to extract independent and discriminative features of the proposals. Furthermore, we design a novel Adaptive Recognition Loss (ARL) which offers guidance for the R-CNN head to focus on high-quality proposals. Extensive experiments validate the effectiveness of PETDet. Quantitative analysis reveals that PETDet with ResNet50 reaches state-of-the-art performance on various FGOD datasets, including FAIR1M-v1.0 (42.96 AP), FAIR1M-v2.0 (48.81 AP), MAR20 (85.91 AP) and ShipRSImageNet (74.90 AP). The proposed method also achieves superior compatibility between accuracy and inference speed. Our code and models will be released at https://github.com/canoe-Z/PETDet.
arXiv commentIEEE TGRS 2023
References in corpus (14)
- Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
- Arbitrary-Oriented Scene Text Detection via Rotation Proposals
- Gliding vertex on the horizontal bounding box for multi-oriented object detection
- FoveaBox: Beyond Anchor-based Object Detector
- The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification
- MMRotate: A Rotated Object Detection Benchmark using PyTorch
- CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images
- Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence
- Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
- Probabilistic two-stage detection
- Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss
- Oriented Object Detection with Transformer
- Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer
- D2Q-DETR: Decoupling and Dynamic Queries for Oriented Object Detection with Transformers