Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection

By Taekyung Kim, Minki Jeong, Seunghyeon Kim, Seokeon Choi, Changick Kim. Computer Vision and Pattern Recognition, 2019

338 citations recorded by the source corpus.

We introduce a novel unsupervised domain adaptation approach for object detection. We aim to alleviate the imperfect translation problem of pixel-level adaptations, and the source-biased discriminativity problem of feature-level adaptations simultaneously. Our approach is composed of two stages, i.e., Domain Diversification (DD) and Multi-domain-invariant Representation Learning (MRL). At the DD stage, we diversify the distribution of the labeled data by generating various distinctive shifted domains from the source domain. At the MRL stage, we apply adversarial learning with a multi-domain discriminator to encourage feature to be indistinguishable among the domains. DD addresses the source-biased discriminativity, while MRL mitigates the imperfect image translation. We construct a structured domain adaptation framework for our learning paradigm and introduce a practical way of DD for implementation. Our method outperforms the state-of-the-art methods by a large margin of 3%~11% in terms of mean average precision (mAP) on various datasets.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c58a3c67f34b83146acab4cee21c062f08b02475

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Unbiased Mean Teacher for Cross-domain Object Detection (2020, methodology): “DM [23] yields various distinctive shifted domains from source domain and employs multidomain-invariant representation learning to encourage features to be indistinguishable among the domains.”
Spatial Attention Pyramid Network for Unsupervised Domain Adaptation (2020, neutral): “3 Diversify&match [21] 30.”
Object Detection in 20 Years: A Survey (2019, positive): “Cycle-consistent transformation [222] has also been applied to bridge the gap between source and target domains [223], [224].”
Unsupervised Domain Adaptation of Object Detectors: A Survey (2021, methodology): “Kim et al. [60] utilized domain randomization to adapt a Faster-RCNN based detection model.”
Progressive Domain Adaptation for Object Detection (2019, methodology): “Table 3 shows that our method reduces the domain gap across weather conditions and performs favorably against the state-of-the-art methods [3, 25, 37, 16].”
Harmonizing Transferability and Discriminability for Adapting Object Detectors (2020, methodology): “[26] solve the adaptation problem from the perspective of domain diversification by randomly augmenting source and target domains into multiple domains, and then learning the invariant representations among domains.”
Cross-Domain Adaptive Teacher for Object Detection (2021, methodology): “We compare our method with SCL [35], SWDA [32], DM [19], CRDA [42], HTCN [2], UMT [8], Source (F-RCNN), and Oracle (F-RCNN).”
Adapting Object Detectors with Conditional Domain Normalization (2020, neutral): “8 DDMRL [22] 30.”
Multiple Class Novelty Detection Under Data Distribution Shift (2020, background): “However, most of the work on this topic has been done for the task of classiﬁcation [52,49,11,14], segmentation [50,55,15], detection [16,9,19] etc. and to the best of our knowledge no work is available in the literature that addresses the distribution shift problem for novelty detection.”