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.
hub
Semantic image segmentation with deep convolutional nets and fully connected CRF s
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
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.
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
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.
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.
Learn2Synth optimizes data synthesis parameters with hypergradients to train segmentation networks solely on synthetic brain images that generalize to real scans.
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.
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.
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.
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.
A 2019 survey that categorizes and intuitively explains major deep learning techniques for image segmentation, progressing from classical methods to modern neural architectures.
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.
citing papers explorer
-
WaveNet: A Generative Model for Raw Audio
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.
-
SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation
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.
-
VGGT-Segmentor: Geometry-Enhanced Cross-View Segmentation
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.
-
Learn2Synth: Learning Optimal Data Synthesis Using Hypergradients for Brain Image Segmentation
Learn2Synth optimizes data synthesis parameters with hypergradients to train segmentation networks solely on synthetic brain images that generalize to real scans.
-
Attention-Mamba: A Mamba-Enhanced Multi-Scale Parallel Inference Network for Medical Image Segmentation
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.
-
MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification
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.
-
News Cover Assessment via Multi-task Learning
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.
-
A Regularized Convolutional Neural Network for Semantic Image Segmentation
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.
-
Understanding Deep Learning Techniques for Image Segmentation
A 2019 survey that categorizes and intuitively explains major deep learning techniques for image segmentation, progressing from classical methods to modern neural architectures.
-
A review on deep learning techniques for 3D sensed data classification
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.