Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
read the original abstract
Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information. In this work, we propose to combine the advantages from both methods. Specifically, our proposed model, DeepLabv3+, extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries. We further explore the Xception model and apply the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network. We demonstrate the effectiveness of the proposed model on PASCAL VOC 2012 and Cityscapes datasets, achieving the test set performance of 89.0\% and 82.1\% without any post-processing. Our paper is accompanied with a publicly available reference implementation of the proposed models in Tensorflow at \url{https://github.com/tensorflow/models/tree/master/research/deeplab}.
This paper has not been read by Pith yet.
Forward citations
Cited by 12 Pith papers
-
Contour Refinement using Discrete Diffusion in Low Data Regime
A CNN-based discrete diffusion method refines sparse contours from segmentation masks using simplified denoising steps and minimal post-processing, outperforming baselines on small medical and environmental datasets w...
-
U4D: Unsupervised 4D Dynamic Scene Understanding
Unsupervised joint semantic instance segmentation, 4D reconstruction, and scene flow from multi-view video of multi-person dynamic scenes, with reported ~40% gains over prior methods.
-
OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization
OmniISR unifies centralized, federated, and hybrid learning by injecting mutual-information supervision and negative-entropy regularization at multiple hidden layers, with supporting convergence and drift bounds.
-
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.
-
SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation
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.
-
Can We Go Beyond Visual Features? Neural Tissue Relation Modeling for Relational Graph Analysis in Non-Melanoma Skin Histology
NTRM combines CNNs with tissue-level graph neural networks to model inter-tissue relationships, delivering 4.9% to 31.25% higher Dice scores than prior methods on a non-melanoma skin cancer histology segmentation benchmark.
-
Flow matching for Sentinel-2 super-resolution: implementation, application, and implications
Flow matching achieves single-step pixel accuracy and 20-step perceptual quality for Sentinel-2 super-resolution, outperforming diffusion and Real-ESRGAN while enabling large-scale 2.5 m land-cover products.
-
From Noisy Historical Maps to Time-Series Oil Palm Mapping Without Annotation in Malaysia and Indonesia (2020-2024)
A U-Net optimized with Determinant-based Mutual Information produces 10m oil palm maps for Malaysia and Indonesia 2020-2024 from noisy historical labels and Sentinel-2 data, reporting 60-71% accuracy against verified ...
-
MORPH-U: Multi-Objective Resilient Motion Planning for V2X-Enabled Autonomous Driving in High-Uncertainty Environments via Simulation
MORPH-U integrates V2X data into autonomous vehicle planning with Hybrid-A* replanning, multi-objective Pareto optimization, and a Byzantine-inspired gate to improve safety against message delays, drops, and forgery i...
-
Improving Semantic Segmentation via Dilated Affinity
Dilated affinity is jointly predicted with segmentation labels to strengthen features and support efficient label propagation refinement on benchmark datasets.
-
SAN: Scale-Aware Network for Semantic Segmentation of High-Resolution Aerial Images
SANet adds a re-sampling-based scale-aware module to semantic segmentation networks to better handle inconsistent object scales in aerial images.
-
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.