Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-training

By Yang Zou, Zhiding Yu, B. V. Vijaya Kumar, Jinsong Wang. 2018

1,499 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

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

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (2020, background): “The generality of self-training (i.e., using a model’s predictions to obtain artiﬁcial labels for unlabeled data) has led it to be been applied in a diversity of domains including NLP [26], object detection [37], image classiﬁcation [22, 46], domain adaptation [53], to name a few.”
Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation (2022, background): “C→I Step 1 [0, 2, 7, 9, 11, 27, 28, 29, 30, 33] Step 2 [37, 39, 40, 44, 45, 47, 50, 60, 62, 68] Step 3 [71, 75, 76, 82, 85, 86, 87, 88, 89, 90] Step 4 [92, 94, 96, 97, 106, 107, 108, 109, 110, 112] Step 5 [114, 115, 116, 123, 126, 128, 133, 134, 141, 145] Step 6 [146, 150, 151, 157, 160, 163, 165, 1”
PLOP: Learning without Forgetting for Continual Semantic Segmentation (2020, background): “Pseudo-labeling [39] is commonly used in domain adaptation for semantic segmentation [63, 41, 79, 58], where a model is trained on the union of real labels of a source dataset and pseudo labels assigned to an unlabeled target dataset.”
Unlabeled Data Improves Adversarial Robustness (2019, neutral): “Another line of work [59, 60] is based on iterative self-training coupled with refinements such as class balance or confidence regularization.”
Class-Balanced Loss Based on Effective Number of Samples (2019, background): “To solve this, novel samples can be either interpolated from neighboring samples [5] or synthesized [14, 50] for minor classes.”
ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation (2018, methodology): “In [51], self-training is employed for UDA on semantic segmentation which is further extended with class balancing and spatial prior.”
Continual Test-Time Domain Adaptation (2022, neutral): “In recent years, self-training has also shown promising results by iteratively using gradually-improving target pseudo-labels to train the network [19, 36, 62, 75].”
DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort (2021, background): “In domain adaptation [41, 57, 51, 10], several works aimed at translating a labeled image dataset into another domain, in which image annotation is either expensive or missing entirely, by leveraging image-to-image translation techniques.”
Unsupervised Domain Adaptation for Semantic Segmentation of Urban Scenes (2019, background): “Following these approaches, many works addressed the source to target domain shift problem with various techniques, such as cycle consistency [11], GANs [29], output space alignment [35], distillation loss [4], classbalanced self-training [46], conservative loss [45], geometrical guidance [3] and ad”
Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation (2019, methodology): “To address this issue, one promising approach is domain adaptation [1, 45, 15, 34, 36, 27, 33, 40, 47, 13] to reduce the domain shift and learn a shared discriminative model for both domains.”
Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID (2020, methodology): “Recently, some methods [41, 16, 6, 56, 67] incorporated the conception of self-paced learning into unsupervised learning tasks by starting the training process with the most confident pseudo labels.”
Bootstrapping Semantic Segmentation with Regional Contrast (2021, background): “Previousmethods include improving segmentationmodels via adversarial learning [12, 21] and self-training [34, 35, 33].”
FDA: Fourier Domain Adaptation for Semantic Segmentation (2020, methodology): “When the domains are aligned, unsupervised domain adaptation becomes SSL. CBST [55] and BDL [23] used “self-training” as a form of regularization [35], exploiting target images by treating pseudo-labels as ground truth.”
Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation (2021, background): “[45] further propose a self-training framework that alternately refines pseudo labels and performs model training.”
Taking a Closer Look at Domain Shift: Category-Level Adversaries for Semantics Consistent Domain Adaptation (2018, methodology): “We present the adaptation results on task GTA5 → Cityscapes in Table 1 with comparisons to the state-of-the-art domain adaptation methods [34, 44, 15, 14, 40, 49].”
A Review of Single-Source Deep Unsupervised Visual Domain Adaptation (2020, background): “ResNet-38 CBST [95] ECCV 2018 O 88.”
DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation (2021, methodology): “Also in UDA, re-weighting [53, 99] and class-balanced sampling for image classification [58] were applied.”
Domain Adaptation for Structured Output via Discriminative Patch Representations (2019, methodology): “, VGG-16 and ResNet-101, and compare with state-of-the-art approaches via feature adaptation [16, 46], pixel-level adaptation [15], pseudo label re-training [50] and output space alignment [5, 39].”