Boosting Unsupervised Segmentation Learning

• URL: http://arxiv.org/abs/2404.03392v3
• Date: Thu, 28 Nov 2024 13:51:19 GMT
• Title: Boosting Unsupervised Segmentation Learning
• Authors: Alp Eren Sari, Francesco Locatello, Paolo Favaro,
• Abstract summary: We present two practical improvement techniques for unsupervised segmentation learning.<n>First, we leverage image post-processing techniques such as guided filtering to refine the output masks.<n>Second, we introduce a multi-scale consistency criterion, based on a teacher-student training scheme.
• Score: 37.63303434543399
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present two practical improvement techniques for unsupervised segmentation learning. These techniques address limitations in the resolution and accuracy of predicted segmentation maps of recent state-of-the-art methods. Firstly, we leverage image post-processing techniques such as guided filtering to refine the output masks, improving accuracy while avoiding substantial computational costs. Secondly, we introduce a multi-scale consistency criterion, based on a teacher-student training scheme. This criterion matches segmentation masks predicted from regions of the input image extracted at different resolutions to each other. Experimental results on several benchmarks used in unsupervised segmentation learning demonstrate the effectiveness of our proposed techniques.

Related papers

• Selective Masking based Self-Supervised Learning for Image Semantic Segmentation [3.2190659800523562]
  We show that our proposed selective masking method outperforms the traditional random masking method and supervised ImageNet pretraining on downstream segmentation accuracy.<n>Our proposed Selective Masking Image Reconstruction method provides an effective and practical solution to improve end-to-end semantic segmentation.
  arXiv  Detail & Related papers  (2025-12-07T20:21:26Z)
• Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection [54.21851618853518]
  We present a concise yet effective approach called Patch Generation-to-Selection to enhance CLIP's training efficiency. Our approach, CLIP-PGS, sets new state-of-the-art results in zero-shot classification and retrieval tasks.
  arXiv  Detail & Related papers  (2025-03-21T12:10:38Z)
• DiverseNet: Decision Diversified Semi-supervised Semantic Segmentation Networks for Remote Sensing Imagery [17.690698736544626]
  We propose DiverseNet which explores multi-head and multi-model semi-supervised learning algorithms by simultaneously enhancing precision and diversity during training. The two proposed methods in the DiverseNet family, namely DiverseHead and DiverseModel, both achieve the better semantic segmentation performance in four widely utilised remote sensing imagery data sets.
  arXiv  Detail & Related papers  (2023-11-22T22:20:10Z)
• Leveraging Uncertainty for Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images [25.429124017422385]
  Deep weakly supervised methods allow image classification and ROI segmentation for interpretability. These methods lack mechanisms for modeling explicitly non-discriminative regions which raises false-positive rates. We propose novel regularization terms, which enable the model to seek both non-discriminative and discriminative regions.
  arXiv  Detail & Related papers  (2022-05-12T02:18:23Z)
• Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation [13.828282295918628]
  We propose a novel unsupervised pre-training framework that avoids the drawback of contrastive learning. Experimental results on two benchmark medical segmentation datasets reveal our method's effectiveness when few annotated images are available.
  arXiv  Detail & Related papers  (2022-02-04T20:18:00Z)
• DeepfakeUCL: Deepfake Detection via Unsupervised Contrastive Learning [20.94569893388119]
  We design a novel deepfake detection method via unsupervised contrastive learning. We show that our method enables comparable detection performance to state-of-the-art supervised techniques.
  arXiv  Detail & Related papers  (2021-04-23T09:48:10Z)
• Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition [102.75463782627791]
  We take steps toward answering the question by exposing failures of existing semantic segmentation methods in the open visual world. Inspired by previous research on model falsification, we start from an arbitrarily large image set, and automatically sample a small image set by MAximizing the Discrepancy (MAD) between two segmentation methods. The selected images have the greatest potential in falsifying either (or both) of the two methods. A segmentation method, whose failures are more difficult to be exposed in the MAD competition, is considered better.
  arXiv  Detail & Related papers  (2021-02-27T16:06:25Z)
• Contrastive Rendering for Ultrasound Image Segmentation [59.23915581079123]
  The lack of sharp boundaries in US images remains an inherent challenge for segmentation. We propose a novel and effective framework to improve boundary estimation in US images. Our proposed method outperforms state-of-the-art methods and has the potential to be used in clinical practice.
  arXiv  Detail & Related papers  (2020-10-10T07:14:03Z)
• Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentation [54.49894381464853]
  We propose to leverage both labeled and unlabeled data for instance segmentation with improved accuracy by knowledge distillation. We propose a novel Mask-guided Mean Teacher framework with Perturbation-sensitive Sample Mining. Experiments show that the proposed method improves the performance significantly compared with the supervised method learned from labeled data only.
  arXiv  Detail & Related papers  (2020-07-21T13:27:09Z)
• ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning [4.205692673448206]
  We propose a novel data augmentation mechanism called ClassMix, which generates augmentations by mixing unlabelled samples. We evaluate this augmentation technique on two common semi-supervised semantic segmentation benchmarks, showing that it attains state-of-the-art results.
  arXiv  Detail & Related papers  (2020-07-15T18:21:17Z)
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments [57.33699905852397]
  We propose an online algorithm, SwAV, that takes advantage of contrastive methods without requiring to compute pairwise comparisons. Our method simultaneously clusters the data while enforcing consistency between cluster assignments. Our method can be trained with large and small batches and can scale to unlimited amounts of data.
  arXiv  Detail & Related papers  (2020-06-17T14:00:42Z)
• MetricUNet: Synergistic Image- and Voxel-Level Learning for Precise CT Prostate Segmentation via Online Sampling [66.01558025094333]
  We propose a two-stage framework, with the first stage to quickly localize the prostate region and the second stage to precisely segment the prostate. We introduce a novel online metric learning module through voxel-wise sampling in the multi-task network. Our method can effectively learn more representative voxel-level features compared with the conventional learning methods with cross-entropy or Dice loss.
  arXiv  Detail & Related papers  (2020-05-15T10:37:02Z)
• Attentive Semantic Exploring for Manipulated Face Detection [12.635690519021555]
  We find that segmenting images into semantic fragments could be effective, as discriminative defects and distortions are closely related to such fragments. We propose a novel manipulated face detection method based on Multilevel Facial Semantic and Cascade Attention Mechanism.
  arXiv  Detail & Related papers  (2020-05-06T17:08:56Z)

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.