Multi-adversarial Faster-RCNN for Unrestricted Object Detection

TL;DR

This paper introduces a multi-adversarial Faster-RCNN framework that enhances unrestricted object detection by minimizing domain disparity through hierarchical feature alignment and specialized modules, achieving state-of-the-art results.

Contribution

The paper presents a novel multi-adversarial Faster-RCNN with hierarchical domain feature alignment, scale reduction, and weighted gradient reversal for improved domain adaptation in object detection.

Findings

Achieves state-of-the-art performance on unrestricted detection tasks.

Effective domain disparity minimization through hierarchical feature alignment.

Improved training efficiency with the scale reduction module.

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.