Multi-adversarial Faster-RCNN for Unrestricted Object Detection

Abstract

Conventional object detection methods essentially suppose that the training and testing data are collected from a restricted target domain with expensive labeling cost. For alleviating the problem of domain dependency and cumbersome labeling, this paper proposes to detect objects in an unrestricted environment by leveraging domain knowledge trained from an auxiliary source domain with sufficient labels. Specifically, we propose a multi-adversarial Faster-RCNN (MAF) framework for unrestricted object detection, which inherently addresses domain disparity minimization for domain adaptation in feature representation. The paper merits are in three-fold: 1) With the idea that object detectors often becomes domain incompatible when image distribution resulted domain disparity appears, we propose a hierarchical domain feature alignment module, in which multiple adversarial domain classifier submodules for layer-wise domain feature confusion are designed; 2) An information invariant scale reduction module (SRM) for hierarchical feature map resizing is proposed for promoting the training efficiency of adversarial domain adaptation; 3) In order to improve the domain adaptability, the aggregated proposal features with detection results are feed into a proposed weighted gradient reversal layer (WGRL) for characterizing hard confused domain samples. We evaluate our MAF on unrestricted tasks, including Cityscapes, KITTI, Sim10k, etc. and the experiments show the state-of-the-art performance over the existing detectors.

arXiv commentThis paper is accepted in ICCV2019

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• YOLOv3: An Incremental Improvement
• DSSD : Deconvolutional Single Shot Detector
• Microsoft COCO Captions: Data Collection and Evaluation Server
• Conditional Adversarial Domain Adaptation
• Semantic Foggy Scene Understanding with Synthetic Data
• Unsupervised Domain Adaptation with Residual Transfer Networks
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• LSDA: Large Scale Detection Through Adaptation

Cited by in corpus (4)

• Control Distance IoU and Control Distance IoU Loss Function for Better Bounding Box Regression
• Spatial Attention Pyramid Network for Unsupervised Domain Adaptation
• Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection
• Learning from Synthetic Animals