Pith. sign in

REVIEW 9 cited by

Fast-SCNN: Fast Semantic Segmentation Network

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 1902.04502 v1 pith:4V7WEXNO submitted 2019-02-12 cs.CV

Rudra P K Poudel , Stephan Liwicki , Roberto Cipolla This is my paper · ORCID
classification cs.CV
keywords segmentationnetworkresolutioncomputationfastsemanticcityscapesdata
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The encoder-decoder framework is state-of-the-art for offline semantic image segmentation. Since the rise in autonomous systems, real-time computation is increasingly desirable. In this paper, we introduce fast segmentation convolutional neural network (Fast-SCNN), an above real-time semantic segmentation model on high resolution image data (1024x2048px) suited to efficient computation on embedded devices with low memory. Building on existing two-branch methods for fast segmentation, we introduce our `learning to downsample' module which computes low-level features for multiple resolution branches simultaneously. Our network combines spatial detail at high resolution with deep features extracted at lower resolution, yielding an accuracy of 68.0% mean intersection over union at 123.5 frames per second on Cityscapes. We also show that large scale pre-training is unnecessary. We thoroughly validate our metric in experiments with ImageNet pre-training and the coarse labeled data of Cityscapes. Finally, we show even faster computation with competitive results on subsampled inputs, without any network modifications.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

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

  1. FUME: Fused Unified Multi-Gas Emission Network for Livestock Rumen Acidosis Detection

    cs.CV 2026-01 conditional novelty 6.0 of 10

    FUME classifies rumen acidosis from CO2/CH4 optical gas images with 98.8% accuracy and 81% mIoU, using 1.28M parameters.

  2. Intra-class Patch Swap for Self-Distillation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    An intra-class patch swap augmentation plus instance-to-instance KL distillation lets a single network train itself and beat several teacher-based and self-distillation baselines on image tasks.

  3. Self-Healing Visual Recovery for Autonomous Ground Vehicles Using Camera-Only Visual Odometry

    cs.RO 2026-07 conditional novelty 5.0 of 10

    Camera-only UGVs recover from line loss in 86.6% of Webots episodes (median 3.26 s) via spin-search then VO breadcrumb return, embedding MAPE-K at 20 Hz on CPU.

  4. GABI: Geometry-Aware Boundary Integration for Spacecraft Segmentation

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    GABI augments a convolutional backbone with an auxiliary distance-field prediction head to improve spacecraft segmentation accuracy and generalization under variable illumination while remaining lightweight.

  5. Analysis of the Dick Effect for AI-based Dynamic Gravimeter

    physics.atom-ph 2025-08 unverdicted novelty 5.0 of 10

    A 0.12 s accelerometer dead time in an atom-interferometer dynamic gravimeter introduces roughly 8 mGal of measurement noise, which the paper attributes to high-frequency aliasing and analyzes with a derived frequency...

  6. Attention-Mamba: A Mamba-Enhanced Multi-Scale Parallel Inference Network for Medical Image Segmentation

    cs.CV 2024-02 unverdicted novelty 5.0 of 10

    Attention-Mamba uses parallel branches, Recursive Alignment Module, and Mamba-enhanced attention to report highest segmentation accuracy on Synapse, ACDC, ISIC-2018, and PH2 with 14.05M parameters and 8.94 GFLOPs.

  7. GasTwinFormer: A Hybrid Vision Transformer for Livestock Methane Emission Segmentation and Dietary Classification in Optical Gas Imaging

    cs.CV 2025-08 conditional novelty 4.0 of 10

    GasTwinFormer, a hybrid of two existing attention mechanisms, segments cattle methane plumes in thermal video at 74.47% mIoU and contributes a new 11,694-frame OGI beef cattle dataset.

  8. CarboFormer: A Lightweight Semantic Segmentation Architecture for Efficient Carbon Dioxide Detection Using Optical Gas Imaging

    cs.CV 2025-05 conditional novelty 4.0 of 10

    CarboFormer, a 5.07M-parameter transformer-based model, segments CO2 plumes in optical gas images with up to 92.98% mIoU at 84.68 FPS.

  9. A Novel Downsampling Strategy Based on Information Complementarity for Medical Image Segmentation

    cs.CV 2025-07 reject novelty 3.0 of 10

    A downsampling layer that adds min-pooling and max-pooling outputs yields small, inconsistent Dice gains in medical image segmentation, with no code or significance testing.

Pith tools