BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation

Zhang, Wenqiao; Zhu, Lei; Hallinan, James Thomas Patrick Decourcy; Zhang, Shengyu; Makmur, Andrew; Cai, Qingpeng; Ooi, Beng Chin

doi:10.1109/cvpr52688.2022.02001

Cited by 54 publications

(29 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One adds an unsupervised loss term (i.e., a regularizer) into the loss function so the training model is expected to learn the labeled and unlabeled data at the same time [28]- [31]. Another labels the unlabeled data with pseudo labels and the pseudo-labeled data are then used in training with a supervised loss [32]- [35].…”

Section: Semi-supervised Learning (Ssl)mentioning

confidence: 99%

Dual-Objective Personalized Federated Service System With Partially-Labeled Data Over Wireless Networks

Ching

Chang

Kuo

et al. 2023

IEEE Trans. Serv. Comput.

View full text Add to dashboard Cite

Federated learning (FL) emerges to mitigate the privacy concerns in machine learning-based services and applications, and personalized federated learning (PFL) evolves to alleviate the issue of data heterogeneity. However, FL and PFL usually rest on two assumptions: the users' data is well-labeled, or the personalized goals align with sufficient local data. Unfortunately, the two assumptions may not hold in most cases, where data labeling is costly, or most users have no sufficient local data to satisfy their personalized needs. To this end, we first formulate the problem, DoLP, that studies the issue of insufficient and partially-labeled data on FL-based services. DoLP aims to maximize two service objectives: 1) personalized classification objective and 2) the personalized labeling objective for each user within the constraint of training time over wireless networks. Then, we propose a PFL-based service system DoFed-SPP to solve DoLP. The DoFed-SPP's novelty is two-fold. First, we devise an inference-based first-order approximation metric, similarity ratio, to identify the similarity between users' local data. Second, we design an approximation algorithm to determine the appropriate size and set of users for uploading in each round. Extensive experiments show DoFed-SPP outperforms the state-of-the-art in final accuracy and time-to-accuracy performance on CIFAR10/100 and DBPedia.

show abstract

Section: Semi-supervised Learning (Ssl)mentioning

confidence: 99%

Dual-Objective Personalized Federated Service System With Partially-Labeled Data Over Wireless Networks

Ching

Chang

Kuo

et al. 2023

IEEE Trans. Serv. Comput.

View full text Add to dashboard Cite

show abstract

“…Consistency regularization. It has been extensively used in SSL [3,20,40] to hold similar output distribution when input was perturbed. Since data augmentation [13,36,39] shows huge superiority in supervised learning, recent works have begun to give more attention to data augmentation perturbation and have achieved significant successes.…”

Section: Related Workmentioning

confidence: 99%

Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data

Chen¹,

Tan²,

Zhao³

et al. 2023

Preprint

View full text Add to dashboard Cite

Semi-supervised learning (SSL) has attracted enormous attention due to its vast potential of mitigating the dependence on large labeled datasets. The latest methods (e.g., FixMatch) use a combination of consistency regularization and pseudo-labeling to achieve remarkable successes. However, these methods all suffer from the waste of complicated examples since all pseudo-labels have to be selected by a high threshold to filter out noisy ones. Hence, the examples with ambiguous predictions will not contribute to the training phase. For better leveraging all unlabeled examples, we propose two novel techniques: Entropy Meaning Loss (EML) and Adaptive Negative Learning (ANL). EML incorporates the prediction distribution of non-target classes into the optimization objective to avoid competition with target class, and thus generating more high-confidence predictions for selecting pseudo-label. ANL introduces the additional negative pseudo-label for all unlabeled data to leverage low-confidence examples. It adaptively allocates this label by dynamically evaluating the top-k performance of the model. EML and ANL do not introduce any additional parameter and hyperparameter. We integrate these techniques with FixMatch, and develop a simple yet powerful framework called FullMatch. Extensive experiments on several common SSL benchmarks (CIFAR-10/100, SVHN, STL-10 and ImageNet) demonstrate that FullMatch exceeds FixMatch by a large margin. Integrated with FlexMatch (an advanced FixMatch-based framework), we achieve state-of-the-art performance. Source code is at https://github.com/megvii-research/FullMatch.

show abstract

“…Active learning methods select the data samples that can benefit the model most in each iteration and request humans to label them to push the usage of human efforts to the minimum. To determine which data sample to be labeled by humans, some approaches use probability models and prioritize the data samples with high prediction inconsistency [12,14,26,52], some depend on the vectorized representation from deep learning models [16,34,53], and some calculate the low-rank matrix representation for both labeled and unlabeled data to calculate the informativeness [45].…”

Section: Active Learningmentioning

confidence: 99%

Rapid Image Labeling via Neuro-Symbolic Learning

Wang

Xiang

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

labeling tasks with only 12 to 39 labeled samples. In particular, Rapid significantly outperforms finetuned CV models in two highly specialized tasks. These results demonstrate the effectiveness of Rapid in learning from small data and its capability to generalize among different tasks. Code and our dataset are publicly available at https://github.com/Neural-Symbolic-Image-Labeling/Rapid/ CCS CONCEPTS • Computing methodologies → Machine learning; Computer vision; Knowledge representation and reasoning.

show abstract

BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation

Cited by 54 publications

References 38 publications

Dual-Objective Personalized Federated Service System With Partially-Labeled Data Over Wireless Networks

Dual-Objective Personalized Federated Service System With Partially-Labeled Data Over Wireless Networks

Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data

Rapid Image Labeling via Neuro-Symbolic Learning

Contact Info

Product

Resources

About