Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation

• URL: http://arxiv.org/abs/2211.16701v1
• Date: Wed, 30 Nov 2022 02:47:25 GMT
• Title: Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation
• Authors: Siqi Fan, Fenghua Zhu, Zunlei Feng, Yisheng Lv, Mingli Song, Fei-Yue Wang
• Abstract summary: We propose a novel learning approach, called Conservative-Progressive Collaborative Learning (CPCL), among which two predictive networks are trained in parallel. One network seeks common ground via intersection supervision and is supervised by the high-quality labels to ensure a more reliable supervision. The other network reserves differences via union supervision and is supervised by all the pseudo labels to keep exploring with curiosity.
• Score: 50.51992191965432
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pseudo supervision is regarded as the core idea in semi-supervised learning for semantic segmentation, and there is always a tradeoff between utilizing only the high-quality pseudo labels and leveraging all the pseudo labels. Addressing that, we propose a novel learning approach, called Conservative-Progressive Collaborative Learning (CPCL), among which two predictive networks are trained in parallel, and the pseudo supervision is implemented based on both the agreement and disagreement of the two predictions. One network seeks common ground via intersection supervision and is supervised by the high-quality labels to ensure a more reliable supervision, while the other network reserves differences via union supervision and is supervised by all the pseudo labels to keep exploring with curiosity. Thus, the collaboration of conservative evolution and progressive exploration can be achieved. To reduce the influences of the suspicious pseudo labels, the loss is dynamic re-weighted according to the prediction confidence. Extensive experiments demonstrate that CPCL achieves state-of-the-art performance for semi-supervised semantic segmentation.

Related papers

• LEAF: Unveiling Two Sides of the Same Coin in Semi-supervised Facial Expression Recognition [56.22672276092373]
  Semi-supervised learning has emerged as a promising approach to tackle the challenge of label scarcity in facial expression recognition. We propose a unified framework termed hierarchicaL dEcoupling And Fusing to coordinate expression-relevant representations and pseudo-labels. We show that LEAF outperforms state-of-the-art semi-supervised FER methods, effectively leveraging both labeled and unlabeled data.
  arXiv  Detail & Related papers  (2024-04-23T13:43:33Z)
• An Evidential-enhanced Tri-Branch Consistency Learning Method for Semi-supervised Medical Image Segmentation [8.507454166954139]
  We introduce an Evidential Tri-Branch Consistency learning framework (ETC-Net) for semi-supervised medical image segmentation. ETC-Net employs three branches: an evidential conservative branch, an evidential progressive branch, and an evidential fusion branch. We also integrate uncertainty estimation from the evidential learning into cross-supervised training, mitigating the negative impact of erroneous supervision signals.
  arXiv  Detail & Related papers  (2024-04-10T14:25:23Z)
• DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation [6.775785126617824]
  We propose a dual student framework with trustworthy progressive learning (DuPL) Experiment results demonstrate the superiority of the proposed DuPL over the recent state-of-the-art alternatives on PASCAL VOC 2012 and MS datasets.
  arXiv  Detail & Related papers  (2024-03-17T12:14:34Z)
• Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning [57.67629402360924]
  We introduce the Partially Supervised Reinforcement Learning (PSRL) framework. At the heart of PSRL is the fusion of both supervised and unsupervised learning. We show that PSRL offers a potent balance, enhancing model interpretability while preserving, and often significantly outperforming, the performance benchmarks set by traditional methods.
  arXiv  Detail & Related papers  (2024-02-14T16:23:23Z)
• Causal Unsupervised Semantic Segmentation [60.178274138753174]
  Unsupervised semantic segmentation aims to achieve high-quality semantic grouping without human-labeled annotations. We propose a novel framework, CAusal Unsupervised Semantic sEgmentation (CAUSE), which leverages insights from causal inference.
  arXiv  Detail & Related papers  (2023-10-11T10:54:44Z)
• Towards Distribution-Agnostic Generalized Category Discovery [51.52673017664908]
  Data imbalance and open-ended distribution are intrinsic characteristics of the real visual world. We propose a Self-Balanced Co-Advice contrastive framework (BaCon) BaCon consists of a contrastive-learning branch and a pseudo-labeling branch, working collaboratively to provide interactive supervision to resolve the DA-GCD task.
  arXiv  Detail & Related papers  (2023-10-02T17:39:58Z)
• ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization [26.542718087103665]
  We present a novel semi-supervised learning framework that intelligently leverages the consistency regularization between the model's predictions from two strongly-augmented views of an image, weighted by a confidence of pseudo-label, dubbed ConMatch. We conduct experiments to demonstrate the effectiveness of our ConMatch over the latest methods and provide extensive ablation studies.
  arXiv  Detail & Related papers  (2022-08-18T04:37:50Z)
• Weakly-supervised Action Localization via Hierarchical Mining [76.00021423700497]
  Weakly-supervised action localization aims to localize and classify action instances in the given videos temporally with only video-level categorical labels. We propose a hierarchical mining strategy under video-level and snippet-level manners, i.e., hierarchical supervision and hierarchical consistency mining. We show that HiM-Net outperforms existing methods on THUMOS14 and ActivityNet1.3 datasets with large margins by hierarchically mining the supervision and consistency.
  arXiv  Detail & Related papers  (2022-06-22T12:19:09Z)

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.