Adaptive Object Detection with Dual Multi-Label Prediction
arXiv:2003.12943
Abstract
In this paper, we propose a novel end-to-end unsupervised deep domain adaptation model for adaptive object detection by exploiting multi-label object recognition as a dual auxiliary task. The model exploits multi-label prediction to reveal the object category information in each image and then uses the prediction results to perform conditional adversarial global feature alignment, such that the multi-modal structure of image features can be tackled to bridge the domain divergence at the global feature level while preserving the discriminability of the features. Moreover, we introduce a prediction consistency regularization mechanism to assist object detection, which uses the multi-label prediction results as an auxiliary regularization information to ensure consistent object category discoveries between the object recognition task and the object detection task. Experiments are conducted on a few benchmark datasets and the results show the proposed model outperforms the state-of-the-art comparison methods.
arXiv commentECCV 2020
References in corpus (14)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Conditional Generative Adversarial Nets
- YOLOv3: An Incremental Improvement
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- Fully Convolutional Networks for Semantic Segmentation
- Unsupervised Domain Adaptation by Backpropagation
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Conditional Adversarial Domain Adaptation
- Semantic Foggy Scene Understanding with Synthetic Data
- Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
- Wasserstein Distance Guided Representation Learning for Domain Adaptation
- Training generative neural networks via Maximum Mean Discrepancy optimization
- SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses