Harmonizing Transferability and Discriminability for Adapting Object Detectors

TL;DR

This paper introduces HTCN, a hierarchical network that balances transferability and discriminability in adaptive object detection by calibrating features at multiple levels, leading to improved performance.

Contribution

It proposes a novel hierarchical calibration framework with three components to enhance feature transferability and discriminability simultaneously in domain adaptation.

Findings

HTCN outperforms state-of-the-art methods on benchmark datasets.

The model effectively balances transferability and discriminability.

Experimental results validate the superiority of the proposed approach.

Abstract

Recent advances in adaptive object detection have achieved compelling results in virtue of adversarial feature adaptation to mitigate the distributional shifts along the detection pipeline. Whilst adversarial adaptation significantly enhances the transferability of feature representations, the feature discriminability of object detectors remains less investigated. Moreover, transferability and discriminability may come at a contradiction in adversarial adaptation given the complex combinations of objects and the differentiated scene layouts between domains. In this paper, we propose a Hierarchical Transferability Calibration Network (HTCN) that hierarchically (local-region/image/instance) calibrates the transferability of feature representations for harmonizing transferability and discriminability. The proposed model consists of three components: (1) Importance Weighted Adversarial Training with input Interpolation (IWAT-I), which strengthens the global discriminability by re-weighting the interpolated image-level features; (2) Context-aware Instance-Level Alignment (CILA) module, which enhances the local discriminability by capturing the underlying complementary effect between the instance-level feature and the global context information for the instance-level feature alignment; (3) local feature masks that calibrate the local transferability to provide semantic guidance for the following discriminative pattern alignment. Experimental results show that HTCN significantly outperforms the state-of-the-art methods on benchmark datasets.