Mixed-supervised segmentation: Confidence maximization helps knowledge distillation
release_k4c4hrqlefbi7mx72rjsokbkli
by
Bingyuan Liu, Christian Desrosiers, Ismail Ben Ayed, Jose Dolz
2022
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 applicability in scenarios. Mixed supervision is an
appealing alternative for mitigating this obstacle. 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 KL
divergence term, which transfers the knowledge (i.e., predictions) 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. We evaluate the effectiveness of the proposed formulation through a
series of quantitative and qualitative experiments using two publicly available
datasets. Results demonstrate that our method significantly outperforms other
strategies for semantic segmentation within a mixed-supervision framework, as
well as recent semi-supervised approaches. Our code is publicly available:
https://github.com/by-liu/ConfKD.
In text/plain
format
Archived Files and Locations
application/pdf 2.9 MB
file_5wczul53c5hprczytiovxgwiwa
|
arxiv.org (repository) web.archive.org (webarchive) |
2109.10902v4
access all versions, variants, and formats of this works (eg, pre-prints)