Two-phase Pseudo Label Densification for Self-training based Domain
Adaptation
- URL: http://arxiv.org/abs/2012.04828v1
- Date: Wed, 9 Dec 2020 02:35:25 GMT
- Title: Two-phase Pseudo Label Densification for Self-training based Domain
Adaptation
- Authors: Inkyu Shin, Sanghyun Woo, Fei Pan and InSo Kweon
- Abstract summary: We propose a novel Two-phase Pseudo Label Densification framework, referred to as TPLD.
In the first phase, we use sliding window voting to propagate the confident predictions, utilizing intrinsic spatial-correlations in the images.
In the second phase, we perform a confidence-based easy-hard classification.
To ease the training process and avoid noisy predictions, we introduce the bootstrapping mechanism to the original self-training loss.
- Score: 93.03265290594278
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recently, deep self-training approaches emerged as a powerful solution to the
unsupervised domain adaptation. The self-training scheme involves iterative
processing of target data; it generates target pseudo labels and retrains the
network. However, since only the confident predictions are taken as pseudo
labels, existing self-training approaches inevitably produce sparse pseudo
labels in practice. We see this is critical because the resulting insufficient
training-signals lead to a suboptimal, error-prone model. In order to tackle
this problem, we propose a novel Two-phase Pseudo Label Densification
framework, referred to as TPLD. In the first phase, we use sliding window
voting to propagate the confident predictions, utilizing intrinsic
spatial-correlations in the images. In the second phase, we perform a
confidence-based easy-hard classification. For the easy samples, we now employ
their full pseudo labels. For the hard ones, we instead adopt adversarial
learning to enforce hard-to-easy feature alignment. To ease the training
process and avoid noisy predictions, we introduce the bootstrapping mechanism
to the original self-training loss. We show the proposed TPLD can be easily
integrated into existing self-training based approaches and improves the
performance significantly. Combined with the recently proposed CRST
self-training framework, we achieve new state-of-the-art results on two
standard UDA benchmarks.
Related papers
- Incremental Self-training for Semi-supervised Learning [56.57057576885672]
IST is simple yet effective and fits existing self-training-based semi-supervised learning methods.
We verify the proposed IST on five datasets and two types of backbone, effectively improving the recognition accuracy and learning speed.
arXiv Detail & Related papers (2024-04-14T05:02:00Z) - Rethinking Self-training for Semi-supervised Landmark Detection: A Selection-free Approach [4.511384690621755]
Self-Training for Landmark Detection (STLD) is a method that does not require explicit pseudo-label selection.
STLD constructs a task curriculum to deal with confirmation bias.
Experiments on three facial and one medical landmark detection benchmark show that STLD outperforms the existing methods.
arXiv Detail & Related papers (2024-04-06T08:45:07Z) - Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple
Logits Retargeting Approach [102.0769560460338]
We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class.
Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
arXiv Detail & Related papers (2024-03-01T03:27:08Z) - Decoupled Prototype Learning for Reliable Test-Time Adaptation [50.779896759106784]
Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference.
One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels.
This study reveals that minimizing the classification error of each sample causes the cross-entropy loss's vulnerability to label noise.
We propose a novel Decoupled Prototype Learning (DPL) method that features prototype-centric loss computation.
arXiv Detail & Related papers (2024-01-15T03:33:39Z) - DaMSTF: Domain Adversarial Learning Enhanced Meta Self-Training for
Domain Adaptation [20.697905456202754]
We propose a new self-training framework for domain adaptation, namely Domain adversarial learning enhanced Self-Training Framework (DaMSTF)
DaMSTF involves meta-learning to estimate the importance of each pseudo instance, so as to simultaneously reduce the label noise and preserve hard examples.
DaMSTF improves the performance of BERT with an average of nearly 4%.
arXiv Detail & Related papers (2023-08-05T00:14:49Z) - TWINS: A Fine-Tuning Framework for Improved Transferability of
Adversarial Robustness and Generalization [89.54947228958494]
This paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks.
We propose a novel statistics-based approach, Two-WIng NormliSation (TWINS) fine-tuning framework.
TWINS is shown to be effective on a wide range of image classification datasets in terms of both generalization and robustness.
arXiv Detail & Related papers (2023-03-20T14:12:55Z) - Constraining Pseudo-label in Self-training Unsupervised Domain
Adaptation with Energy-based Model [26.074500538428364]
unsupervised domain adaptation (UDA) is developed to introduce the knowledge in the labeled source domain to the unlabeled target domain.
Recently, deep self-training presents a powerful means for UDA, involving an iterative process of predicting the target domain.
We resort to the energy-based model and constrain the training of the unlabeled target sample with an energy function minimization objective.
arXiv Detail & Related papers (2022-08-26T22:50:23Z) - Boosting Cross-Domain Speech Recognition with Self-Supervision [35.01508881708751]
Cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to mismatch between training and testing distributions.
Previous work has shown that self-supervised learning (SSL) or pseudo-labeling (PL) is effective in UDA by exploiting the self-supervisions of unlabeled data.
This work presents a systematic UDA framework to fully utilize the unlabeled data with self-supervision in the pre-training and fine-tuning paradigm.
arXiv Detail & Related papers (2022-06-20T14:02:53Z) - Cycle Self-Training for Domain Adaptation [85.14659717421533]
Cycle Self-Training (CST) is a principled self-training algorithm that enforces pseudo-labels to generalize across domains.
CST recovers target ground truth, while both invariant feature learning and vanilla self-training fail.
Empirical results indicate that CST significantly improves over prior state-of-the-arts in standard UDA benchmarks.
arXiv Detail & Related papers (2021-03-05T10:04:25Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.