Co-Training with Active Contrastive Learning and Meta-Pseudo-Labeling on 2D Projections for Deep Semi-Supervised Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910919356841984 |
|---|---|
| author | Aparco-Cardenas, David Gomes, Jancarlo F. Falcão, Alexandre X. de Rezende, Pedro J. |
| author_facet | Aparco-Cardenas, David Gomes, Jancarlo F. Falcão, Alexandre X. de Rezende, Pedro J. |
| contents | A major challenge that prevents the training of DL models is the limited availability of accurately labeled data. This shortcoming is highlighted in areas where data annotation becomes a time-consuming and error-prone task. In this regard, SSL tackles this challenge by capitalizing on scarce labeled and abundant unlabeled data; however, SoTA methods typically depend on pre-trained features and large validation sets to learn effective representations for classification tasks. In addition, the reduced set of labeled data is often randomly sampled, neglecting the selection of more informative samples. Here, we present active-DeepFA, a method that effectively combines CL, teacher-student-based meta-pseudo-labeling and AL to train non-pretrained CNN architectures for image classification in scenarios of scarcity of labeled and abundance of unlabeled data. It integrates DeepFA into a co-training setup that implements two cooperative networks to mitigate confirmation bias from pseudo-labels. The method starts with a reduced set of labeled samples by warming up the networks with supervised CL. Afterward and at regular epoch intervals, label propagation is performed on the 2D projections of the networks' deep features. Next, the most reliable pseudo-labels are exchanged between networks in a cross-training fashion, while the most meaningful samples are annotated and added into the labeled set. The networks independently minimize an objective loss function comprising supervised contrastive, supervised and semi-supervised loss components, enhancing the representations towards image classification. Our approach is evaluated on three challenging biological image datasets using only 5% of labeled samples, improving baselines and outperforming six other SoTA methods. In addition, it reduces annotation effort by achieving comparable results to those of its counterparts with only 3% of labeled data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_18666 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Co-Training with Active Contrastive Learning and Meta-Pseudo-Labeling on 2D Projections for Deep Semi-Supervised Learning Aparco-Cardenas, David Gomes, Jancarlo F. Falcão, Alexandre X. de Rezende, Pedro J. Computer Vision and Pattern Recognition 68T07 I.4.10; I.5.1 A major challenge that prevents the training of DL models is the limited availability of accurately labeled data. This shortcoming is highlighted in areas where data annotation becomes a time-consuming and error-prone task. In this regard, SSL tackles this challenge by capitalizing on scarce labeled and abundant unlabeled data; however, SoTA methods typically depend on pre-trained features and large validation sets to learn effective representations for classification tasks. In addition, the reduced set of labeled data is often randomly sampled, neglecting the selection of more informative samples. Here, we present active-DeepFA, a method that effectively combines CL, teacher-student-based meta-pseudo-labeling and AL to train non-pretrained CNN architectures for image classification in scenarios of scarcity of labeled and abundance of unlabeled data. It integrates DeepFA into a co-training setup that implements two cooperative networks to mitigate confirmation bias from pseudo-labels. The method starts with a reduced set of labeled samples by warming up the networks with supervised CL. Afterward and at regular epoch intervals, label propagation is performed on the 2D projections of the networks' deep features. Next, the most reliable pseudo-labels are exchanged between networks in a cross-training fashion, while the most meaningful samples are annotated and added into the labeled set. The networks independently minimize an objective loss function comprising supervised contrastive, supervised and semi-supervised loss components, enhancing the representations towards image classification. Our approach is evaluated on three challenging biological image datasets using only 5% of labeled samples, improving baselines and outperforming six other SoTA methods. In addition, it reduces annotation effort by achieving comparable results to those of its counterparts with only 3% of labeled data. |
| title | Co-Training with Active Contrastive Learning and Meta-Pseudo-Labeling on 2D Projections for Deep Semi-Supervised Learning |
| topic | Computer Vision and Pattern Recognition 68T07 I.4.10; I.5.1 |
| url | https://arxiv.org/abs/2504.18666 |