Robust Mutual Learning for Semi-supervised Semantic Segmentation
- URL: http://arxiv.org/abs/2106.00609v1
- Date: Tue, 1 Jun 2021 16:22:01 GMT
- Title: Robust Mutual Learning for Semi-supervised Semantic Segmentation
- Authors: Pan Zhang, Bo Zhang, Ting Zhang, Dong Chen, Fang Wen
- Abstract summary: We propose robust mutual learning that improves the prior approach in two aspects.
We show that strong data augmentations, model noises and heterogeneous network architectures are essential to alleviate the model coupling.
The proposed robust mutual learning demonstrates state-of-the-art performance on semantic segmentation in low-data regime.
- Score: 23.54885398483688
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent semi-supervised learning (SSL) methods are commonly based on pseudo
labeling. Since the SSL performance is greatly influenced by the quality of
pseudo labels, mutual learning has been proposed to effectively suppress the
noises in the pseudo supervision. In this work, we propose robust mutual
learning that improves the prior approach in two aspects. First, the vanilla
mutual learners suffer from the coupling issue that models may converge to
learn homogeneous knowledge. We resolve this issue by introducing mean teachers
to generate mutual supervisions so that there is no direct interaction between
the two students. We also show that strong data augmentations, model noises and
heterogeneous network architectures are essential to alleviate the model
coupling. Second, we notice that mutual learning fails to leverage the
network's own ability for pseudo label refinement. Therefore, we introduce
self-rectification that leverages the internal knowledge and explicitly
rectifies the pseudo labels before the mutual teaching. Such self-rectification
and mutual teaching collaboratively improve the pseudo label accuracy
throughout the learning. The proposed robust mutual learning demonstrates
state-of-the-art performance on semantic segmentation in low-data regime.
Related papers
- Self-Supervised Representation Learning with Spatial-Temporal Consistency for Sign Language Recognition [96.62264528407863]
We propose a self-supervised contrastive learning framework to excavate rich context via spatial-temporal consistency.
Inspired by the complementary property of motion and joint modalities, we first introduce first-order motion information into sign language modeling.
Our method is evaluated with extensive experiments on four public benchmarks, and achieves new state-of-the-art performance with a notable margin.
arXiv Detail & Related papers (2024-06-15T04:50:19Z) - A Probabilistic Model Behind Self-Supervised Learning [53.64989127914936]
In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels.
We present a generative latent variable model for self-supervised learning.
We show that several families of discriminative SSL, including contrastive methods, induce a comparable distribution over representations.
arXiv Detail & Related papers (2024-02-02T13:31:17Z) - Active Self-Supervised Learning: A Few Low-Cost Relationships Are All
You Need [34.013568381942775]
Self-Supervised Learning (SSL) has emerged as the solution of choice to learn transferable representations from unlabeled data.
In this work, we formalize and generalize this principle through Positive Active Learning (PAL) where an oracle queries semantic relationships between samples.
First, it unveils a theoretically grounded learning framework beyond SSL, based on similarity graphs, that can be extended to tackle supervised and semi-supervised learning depending on the employed oracle.
Second, it provides a consistent algorithm to embed a priori knowledge, e.g. some observed labels, into any SSL losses without any change in the training pipeline.
arXiv Detail & Related papers (2023-03-27T14:44:39Z) - Distantly-Supervised Named Entity Recognition with Adaptive Teacher
Learning and Fine-grained Student Ensemble [56.705249154629264]
Self-training teacher-student frameworks are proposed to improve the robustness of NER models.
In this paper, we propose an adaptive teacher learning comprised of two teacher-student networks.
Fine-grained student ensemble updates each fragment of the teacher model with a temporal moving average of the corresponding fragment of the student, which enhances consistent predictions on each model fragment against noise.
arXiv Detail & Related papers (2022-12-13T12:14:09Z) - On Higher Adversarial Susceptibility of Contrastive Self-Supervised
Learning [104.00264962878956]
Contrastive self-supervised learning (CSL) has managed to match or surpass the performance of supervised learning in image and video classification.
It is still largely unknown if the nature of the representation induced by the two learning paradigms is similar.
We identify the uniform distribution of data representation over a unit hypersphere in the CSL representation space as the key contributor to this phenomenon.
We devise strategies that are simple, yet effective in improving model robustness with CSL training.
arXiv Detail & Related papers (2022-07-22T03:49:50Z) - Weakly Supervised Semantic Segmentation via Alternative Self-Dual
Teaching [82.71578668091914]
This paper establishes a compact learning framework that embeds the classification and mask-refinement components into a unified deep model.
We propose a novel alternative self-dual teaching (ASDT) mechanism to encourage high-quality knowledge interaction.
arXiv Detail & Related papers (2021-12-17T11:56:56Z) - Co-learning: Learning from Noisy Labels with Self-supervision [28.266156561454327]
Self-supervised learning works in the absence of labels and thus eliminates the negative impact of noisy labels.
Motivated by co-training with both supervised learning view and self-supervised learning view, we propose a simple yet effective method called Co-learning for learning with noisy labels.
arXiv Detail & Related papers (2021-08-05T06:20:51Z) - ReSSL: Relational Self-Supervised Learning with Weak Augmentation [68.47096022526927]
Self-supervised learning has achieved great success in learning visual representations without data annotations.
We introduce a novel relational SSL paradigm that learns representations by modeling the relationship between different instances.
Our proposed ReSSL significantly outperforms the previous state-of-the-art algorithms in terms of both performance and training efficiency.
arXiv Detail & Related papers (2021-07-20T06:53:07Z) - Bidirectional Mapping Coupled GAN for Generalized Zero-Shot Learning [7.22073260315824]
Bidirectional mapping-based generalized zero-shot learning (GZSL) methods rely on the quality of synthesized features to recognize seen and unseen data.
We learn a joint distribution of seen-unseen domains and preserving domain distinction is crucial for these methods.
In this work, we utilize the available unseen class semantics alongside seen class semantics and learn joint distribution through a strong visual-semantic coupling.
arXiv Detail & Related papers (2020-12-30T06:11:29Z) - Noisy Concurrent Training for Efficient Learning under Label Noise [13.041607703862724]
Deep neural networks (DNNs) fail to learn effectively under label noise and have been shown to memorize random labels which affect their performance.
We consider learning in isolation, using one-hot encoded labels as the sole source of supervision, and a lack of regularization to discourage memorization as the major shortcomings of the standard training procedure.
We propose Noisy Concurrent Training (NCT) which leverages collaborative learning to use the consensus between two models as an additional source of supervision.
arXiv Detail & Related papers (2020-09-17T14:22:17Z)
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.