Progressive Adversarial Networks for Fine-Grained Domain Adaptation

Wang, Sinan; Chen, Xinyang; Wang, Yunbo; Long, Mingsheng; Wang, Jianmin

doi:10.1109/cvpr42600.2020.00923

Cited by 43 publications

(32 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The effectiveness of ILA-DA is reflected by improved adaptation accuracy on popular benchmarks like Digits and Office-31 datasets. We also achieve state-of-the-art results on a challenging adaptation dataset Birds-31 [30] without using complementary information such as label-hierarchies and class structure unlike [30], which indicates the usefulness of our MSC loss in handling wide variety of scenarios. We further perform extensive ablations and analysis on our methodological choices.…”

Section: Introductionmentioning

confidence: 78%

See 1 more Smart Citation

Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation

Sharma

Kalluri

Chandraker

2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 78%

“…This dataset is recently proposed by [30] for fine grained adaptation consisting of different types of birds. We use it to verify our argument that our MSC loss performs efficiently even with datasets that possess large intra-class and small inter-class variation.…”

Section: Birds-31mentioning

confidence: 99%

Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation

Sharma

Kalluri

Chandraker

2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

“…Adversarial adaptation has been first introduced for image classification, both at pixel and feature levels, in order to produce a target-like artificial supervision [28,3] or to learn a domain invariant latent space [19,59]. A variety of techniques have been proposed to tackle the UDA task, ranging from completely non-adversarial approaches [67,16,1,68,12,43] to enhanced adversarial strategies [14,63]. UDA for Semantic Segmentation.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Domain Adaptation in Semantic Segmentation: A Review

et al. 2020

View full text Add to dashboard Cite

The aim of this paper is to give an overview of the recent advancements in the Unsupervised Domain Adaptation (UDA) of deep networks for semantic segmentation. This task is attracting a wide interest since semantic segmentation models require a huge amount of labeled data and the lack of data fitting specific requirements is the main limitation in the deployment of these techniques. This field has been recently explored and has rapidly grown with a large number of ad-hoc approaches. This motivates us to build a comprehensive overview of the proposed methodologies and to provide a clear categorization. In this paper, we start by introducing the problem, its formulation and the various scenarios that can be considered. Then, we introduce the different levels at which adaptation strategies may be applied: namely, at the input (image) level, at the internal features representation and at the output level. Furthermore, we present a detailed overview of the literature in the field, dividing previous methods based on the following (non mutually exclusive) categories: adversarial learning, generative-based, analysis of the classifier discrepancies, self-teaching, entropy minimization, curriculum learning and multi-task learning. Novel research directions are also briefly introduced to give a hint of interesting open problems in the field. Finally, a comparison of the performance of the various methods in the widely used autonomous driving scenario is presented.

show abstract

“…We evaluate our method on three benchmarks. Two of them are based on the domain adaptation of bird images, including the CUB-200-2011 [17], CUB-200-Painting [18], NABirds [4] and iNaturalist2017 [19] datasets, and the other is based on the domain adaptation of vehicle images, including the Stanford [8] dataset. The extensive experimental results show that the proposed adversarial networks with circular attention mechanism achieve excellent performance in fine-grained domain adaptation tasks.…”

Section: Figure 1 Birds Under Different Fine Labels In Different Datasetsmentioning

confidence: 99%

“…After extracting the local images from the circular attention mechanism, progressive granularity learning method [18] is used to complete the training from coarse-grained to finegrained for the recognition tasks. As shown in Figure 2, the coarse labels are divided into K levels.…”

Section: B Progressive Granularity Learningmentioning

confidence: 99%

Adversarial Networks With Circular Attention Mechanism for Fine-Grained Domain Adaptation

Zhu

2021

IEEE Access

View full text Add to dashboard Cite

Fine-grained Image Analysis (FGIA) as a branch of the image analysis tasks has received more and more attention in recent years. Compared with ordinary image analysis tasks, FGIA requires more detailed human data annotation, which not only requires the annotator to have professional knowledge, but also requires greater labor costs. An effective solution is to apply the domain adaptation (DA) method to transfer knowledge from existing fine-grained image datasets to massive unlabeled data. This paper presents the circular attention mechanism to cyclically extract deep-level image features to match the label hierarchy from coarse to fine. What is more, the networks effectively improve the distinguishability and transferability of fine-grained features based on the adversarial learning framework. Experimental results show that our proposed method achieves excellent transfer performance on three fine-grained recognition benchmarks.

show abstract

Progressive Adversarial Networks for Fine-Grained Domain Adaptation

Cited by 43 publications

References 31 publications

Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation

Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation

Unsupervised Domain Adaptation in Semantic Segmentation: A Review

Adversarial Networks With Circular Attention Mechanism for Fine-Grained Domain Adaptation

Contact Info

Product

Resources

About