pith. sign in

arxiv: 1412.7062 · v4 · pith:HA7FR76Pnew · submitted 2014-12-22 · 💻 cs.CV · cs.LG· cs.NE

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

Liang-Chieh Chen , George Papandreou , Iasonas Kokkinos , Kevin Murphy , Alan L. Yuille This is my paper
classification 💻 cs.CV cs.LGcs.NE
keywords dcnnsimagesegmentationdeeplevelresponsessemanticaccuracy
0
0 comments X
read the original abstract

Deep Convolutional Neural Networks (DCNNs) have recently shown state of the art performance in high level vision tasks, such as image classification and object detection. This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification (also called "semantic image segmentation"). We show that responses at the final layer of DCNNs are not sufficiently localized for accurate object segmentation. This is due to the very invariance properties that make DCNNs good for high level tasks. We overcome this poor localization property of deep networks by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF). Qualitatively, our "DeepLab" system is able to localize segment boundaries at a level of accuracy which is beyond previous methods. Quantitatively, our method sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 71.6% IOU accuracy in the test set. We show how these results can be obtained efficiently: Careful network re-purposing and a novel application of the 'hole' algorithm from the wavelet community allow dense computation of neural net responses at 8 frames per second on a modern GPU.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

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

  1. WaveNet: A Generative Model for Raw Audio

    cs.SD 2016-09 accept novelty 9.0

    WaveNet generates realistic raw audio using an autoregressive neural network with dilated convolutions, achieving state-of-the-art naturalness in speech synthesis for English and Mandarin.

  2. VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation

    cs.CV 2026-04 unverdicted novelty 7.0

    VGGT-Segmentor achieves new state-of-the-art cross-view segmentation on Ego-Exo4D with 67.7% and 68.0% average IoU using a geometry-enhanced model and correspondence-free pretraining that beats most supervised baselines.

  3. SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation

    cs.CV 2026-05 unverdicted novelty 6.0

    SegRAG is a training-free retrieval-augmented framework that extracts class-specific point prompts from a filtered DINOv3 feature bank to boost SAM3 semantic segmentation performance on standard and agricultural benchmarks.

  4. SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation

    cs.CV 2026-05 unverdicted novelty 6.0

    SegRAG augments SAM3 with class-specific point prompts retrieved via DINOv3 features and filtered by ICCD, using TSG at inference to improve open-vocabulary segmentation.

  5. VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation

    cs.CV 2026-04 unverdicted novelty 6.0

    VGGT-Segmentor achieves new SOTA cross-view segmentation on Ego-Exo4D (67.7% Ego-to-Exo, 68.0% Exo-to-Ego IoU) via geometry-enhanced features, a three-stage segmentation head, and correspondence-free pretraining.

  6. Learn2Synth: Learning Optimal Data Synthesis Using Hypergradients for Brain Image Segmentation

    cs.CV 2024-11 unverdicted novelty 6.0

    Learn2Synth optimizes data synthesis parameters with hypergradients to train segmentation networks solely on synthetic brain images that generalize to real scans.

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

    cs.CV 2024-02 unverdicted novelty 5.0

    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.

  8. MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification

    cs.CV 2019-07 unverdicted novelty 4.0

    MultiDepth is a multi-task CNN architecture that adds depth-interval classification as an auxiliary task to stabilize and improve regression-based single-image depth estimation on the KITTI dataset.

  9. News Cover Assessment via Multi-task Learning

    cs.CV 2019-07 unverdicted novelty 4.0

    Multi-task network based on modified DeepLabv3+ performs image clarity assessment and semantic segmentation together for news cover evaluation and outperforms single-task baselines on a custom game-content dataset.

  10. A Regularized Convolutional Neural Network for Semantic Image Segmentation

    cs.CV 2019-06 unverdicted novelty 3.0

    Integrating total variation regularization into U-Net and SegNet yields segmentation results with improved spatial regularity and noise robustness on WBC, CamVid, and SUN-RGBD datasets.

  11. Understanding Deep Learning Techniques for Image Segmentation

    cs.CV 2019-07 unverdicted novelty 1.0

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

  12. A review on deep learning techniques for 3D sensed data classification

    cs.CV 2019-07 unverdicted novelty 1.0

    A survey of deep learning architectures for 3D sensed data classification covering RGB-D, multi-view, volumetric and end-to-end methods along with datasets and future directions.