Mixed-supervised segmentation: Confidence maximization helps knowledge distillation

• URL: http://arxiv.org/abs/2109.10902v1
• Date: Tue, 21 Sep 2021 20:06:13 GMT
• Title: Mixed-supervised segmentation: Confidence maximization helps knowledge distillation
• Authors: Bingyuan Liu, Christian Desrosiers, Ismail Ben Ayed, Jose Dolz
• Abstract summary: In this work, we propose a dual-branch architecture for deep neural networks. The upper branch (teacher) receives strong annotations, while the bottom one (student) is driven by limited supervision and guided by the upper branch. We show that the synergy between the entropy and KL divergence yields substantial improvements in performance.
• Score: 24.892332859630518
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite achieving promising results in a breadth of medical image segmentation tasks, deep neural networks require large training datasets with pixel-wise annotations. Obtaining these curated datasets is a cumbersome process which limits the application in scenarios where annotated images are scarce. Mixed supervision is an appealing alternative for mitigating this obstacle, where only a small fraction of the data contains complete pixel-wise annotations and other images have a weaker form of supervision. In this work, we propose a dual-branch architecture, where the upper branch (teacher) receives strong annotations, while the bottom one (student) is driven by limited supervision and guided by the upper branch. Combined with a standard cross-entropy loss over the labeled pixels, our novel formulation integrates two important terms: (i) a Shannon entropy loss defined over the less-supervised images, which encourages confident student predictions in the bottom branch; and (ii) a Kullback-Leibler (KL) divergence term, which transfers the knowledge of the strongly supervised branch to the less-supervised branch and guides the entropy (student-confidence) term to avoid trivial solutions. We show that the synergy between the entropy and KL divergence yields substantial improvements in performance. We also discuss an interesting link between Shannon-entropy minimization and standard pseudo-mask generation, and argue that the former should be preferred over the latter for leveraging information from unlabeled pixels. Quantitative and qualitative results on two publicly available datasets demonstrate that our method significantly outperforms other strategies for semantic segmentation within a mixed-supervision framework, as well as recent semi-supervised approaches. Moreover, we show that the branch trained with reduced supervision and guided by the top branch largely outperforms the latter.

Related papers

• 2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation [92.17700318483745]
  We propose an image-guidance network (IGNet) which builds upon the idea of distilling high level feature information from a domain adapted synthetically trained 2D semantic segmentation network. IGNet achieves state-of-the-art results for weakly-supervised LiDAR semantic segmentation on ScribbleKITTI, boasting up to 98% relative performance to fully supervised training with only 8% labeled points.
  arXiv  Detail & Related papers  (2023-11-27T07:57:29Z)
• Disentangled Representation Learning with Transmitted Information Bottleneck [57.22757813140418]
  We present textbfDisTIB (textbfTransmitted textbfInformation textbfBottleneck for textbfDisd representation learning), a novel objective that navigates the balance between information compression and preservation.
  arXiv  Detail & Related papers  (2023-11-03T03:18:40Z)
• Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation [27.831267434546024]
  We revisit the weak-to-strong consistency framework popularized by FixMatch from semi-supervised classification. We propose an auxiliary feature perturbation stream as a supplement, leading to an expanded perturbation space. Our overall Unified Dual-Stream Perturbations approach (UniMatch) surpasses all existing methods significantly across all evaluation protocols.
  arXiv  Detail & Related papers  (2022-08-21T15:32:43Z)
• Interpolation-based Correlation Reduction Network for Semi-Supervised Graph Learning [49.94816548023729]
  We propose a novel graph contrastive learning method, termed Interpolation-based Correlation Reduction Network (ICRN) In our method, we improve the discriminative capability of the latent feature by enlarging the margin of decision boundaries. By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discnative representation learning.
  arXiv  Detail & Related papers  (2022-06-06T14:26:34Z)
• Flip Learning: Erase to Segment [65.84901344260277]
  Weakly-supervised segmentation (WSS) can help reduce time-consuming and cumbersome manual annotation. We propose a novel and general WSS framework called Flip Learning, which only needs the box annotation. Our proposed approach achieves competitive performance and shows great potential to narrow the gap between fully-supervised and weakly-supervised learning.
  arXiv  Detail & Related papers  (2021-08-02T09:56:10Z)
• Semi-supervised Semantic Segmentation with Directional Context-aware Consistency [66.49995436833667]
  We focus on the semi-supervised segmentation problem where only a small set of labeled data is provided with a much larger collection of totally unlabeled images. A preferred high-level representation should capture the contextual information while not losing self-awareness. We present the Directional Contrastive Loss (DC Loss) to accomplish the consistency in a pixel-to-pixel manner.
  arXiv  Detail & Related papers  (2021-06-27T03:42:40Z)
• Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation [16.560870740946275]
  Explicit Pseudo-pixel Supervision (EPS) learns from pixel-level feedback by combining two weak supervisions. We devise a joint training strategy to fully utilize the complementary relationship between both information. Our method can obtain accurate object boundaries and discard co-occurring pixels, thereby significantly improving the quality of pseudo-masks.
  arXiv  Detail & Related papers  (2021-05-19T07:31:11Z)
• Teach me to segment with mixed supervision: Confident students become masters [27.976487552313113]
  Deep segmentation neural networks require large training datasets with pixel-wise segmentations, which are expensive to obtain in practice. We propose a dual-branch architecture, where the upper branch (teacher) receives strong annotations, while the bottom one (student) is driven by limited supervision and guided by the upper branch. We demonstrate that our method significantly outperforms other strategies to tackle semantic segmentation within a mixed-supervision framework.
  arXiv  Detail & Related papers  (2020-12-15T02:51:36Z)
• Self-paced and self-consistent co-training for semi-supervised image segmentation [23.100800154116627]
  Deep co-training has been proposed as an effective approach for image segmentation when annotated data is scarce. In this paper, we improve existing approaches for semi-supervised segmentation with a self-paced and self-consistent co-training method.
  arXiv  Detail & Related papers  (2020-10-31T17:41:03Z)
• A Weakly-Supervised Semantic Segmentation Approach based on the Centroid Loss: Application to Quality Control and Inspection [6.101839518775968]
  We propose and assess a new weakly-supervised semantic segmentation approach making use of a novel loss function. The performance of the approach is evaluated against datasets from two different industry-related case studies.
  arXiv  Detail & Related papers  (2020-10-26T09:08:21Z)
• Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation [93.83369981759996]
  We propose a self-supervised equivariant attention mechanism (SEAM) to discover additional supervision and narrow the gap. Our method is based on the observation that equivariance is an implicit constraint in fully supervised semantic segmentation. We propose consistency regularization on predicted CAMs from various transformed images to provide self-supervision for network learning.
  arXiv  Detail & Related papers  (2020-04-09T14:57:57Z)

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.