Pith. sign in

REVIEW 8 cited by

Capsules for Object Segmentation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1804.04241 v1 pith:PWJRR7S5 submitted 2018-04-11 stat.ML cs.AIcs.CVcs.LG

Rodney LaLonde , Ulas Bagci This is my paper · ORCID
classification stat.MLcs.AIcs.CVcs.LG
keywords capsulecapsulesinputnetworkssegcapssegmentationconvolutionalobject
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Convolutional neural networks (CNNs) have shown remarkable results over the last several years for a wide range of computer vision tasks. A new architecture recently introduced by Sabour et al., referred to as a capsule networks with dynamic routing, has shown great initial results for digit recognition and small image classification. The success of capsule networks lies in their ability to preserve more information about the input by replacing max-pooling layers with convolutional strides and dynamic routing, allowing for preservation of part-whole relationships in the data. This preservation of the input is demonstrated by reconstructing the input from the output capsule vectors. Our work expands the use of capsule networks to the task of object segmentation for the first time in the literature. We extend the idea of convolutional capsules with locally-connected routing and propose the concept of deconvolutional capsules. Further, we extend the masked reconstruction to reconstruct the positive input class. The proposed convolutional-deconvolutional capsule network, called SegCaps, shows strong results for the task of object segmentation with substantial decrease in parameter space. As an example application, we applied the proposed SegCaps to segment pathological lungs from low dose CT scans and compared its accuracy and efficiency with other U-Net-based architectures. SegCaps is able to handle large image sizes (512 x 512) as opposed to baseline capsules (typically less than 32 x 32). The proposed SegCaps reduced the number of parameters of U-Net architecture by 95.4% while still providing a better segmentation accuracy.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. The Convergence of Dynamic Routing between Capsules

    cs.LG 2025-01 conditional novelty 6.0 of 10

    Dynamic routing between capsules is exactly nonlinear gradient descent on the concave objective Ψ(C) = -Σ_j (||U_j C(:,j)|| - arctan ||U_j C(:,j)||), whose value decreases at every routing iteration.

  2. Recognizing Image Objects by Relational Analysis Using Heterogeneous Superpixels and Deep Convolutional Features

    cs.CV 2019-08 conditional novelty 6.0 of 10

    A capsule network operating on superpixel-pooled VGG-16 features can classify images with about 89% accuracy on a small four-class dataset and provides part-whole explanations without segmentation labels.

  3. Quantum Feature-Empowered Deep Classification for Fast Mangrove Mapping

    quant-ph 2025-01 conditional novelty 5.0 of 10

    A dual-branch CNN plus quantum-circuit network, QEDNet, improves mangrove mapping accuracy on three Sentinel-2 test scenes over conventional deep networks while using fewer parameters.

  4. Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsules

    cs.CV 2019-08 conditional novelty 5.0 of 10

    Point2SpatialCapsule replaces max-pooling aggregation with NetVLAD-style clustering plus dynamic capsule routing, achieving 93.4% accuracy on ModelNet40 classification.

  5. Weakly Supervised Segmentation by A Deep Geodesic Prior

    stat.ML 2019-08 conditional novelty 5.0 of 10

    A geodesic-map autoencoder prior added to the segmentation loss improves cardiac MRI segmentation Dice by 4.4% on clean labels and by 4.6% to 6.3% on two levels of synthetic label noise.

  6. Federated Learning for Large Models in Medical Imaging: A Comprehensive Review

    cs.CR 2025-08 conditional novelty 4.0 of 10

    A survey of federated learning for medical imaging covers CT/MRI reconstruction and downstream diagnosis and segmentation, emphasizing non-IID data and privacy.

  7. Conditional diffusion model with spatial attention and latent embedding for medical image segmentation

    eess.IV 2025-02 conditional novelty 4.0 of 10

    A conditional diffusion model with a per-timestep discriminator, spatial attention, and latent embedding reports state-of-the-art accuracy on three medical segmentation datasets using only 2 to 4 diffusion steps.

  8. Understanding Deep Learning Techniques for Image Segmentation

    cs.CV 2019-07 unverdicted novelty 1.0 of 10

    A 2019 survey that categorizes and intuitively explains major deep learning techniques for image segmentation, progressing from classical methods to modern neural architectures.

Pith tools