DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First, we highlight convolution with upsampled filters, or 'atrous convolution', as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively enlarge the field of view of filters to incorporate larger context without increasing the number of parameters or the amount of computation. Second, we propose atrous spatial pyramid pooling (ASPP) to robustly segment objects at multiple scales. ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales. Third, we improve the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. The commonly deployed combination of max-pooling and downsampling in DCNNs achieves invariance but has a toll on localization accuracy. We overcome this by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF), which is shown both qualitatively and quantitatively to improve localization performance. Our proposed "DeepLab" system sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 79.7 percent mIOU in the test set, and advances the results on three other datasets: PASCAL-Context, PASCAL-Person-Part, and Cityscapes. All of our code is made publicly available online.

Last synced 2026-08-22 14:19 UTC

• A Spatial Prior-Guided Feature Enhancement and Multi-Branch Complementary Learning Framework for Small Ship Detection in SAR Images

  Remote Sensing 2026 · 0 citations

• FreqFusion-Net: frequency-aware adaptive multimodal fusion for building extraction in complex terrain via transfer learning

  Geocarto International 2026 · 0 citations

• CRFTrans: A recursive vision transformer reformulating the mean-field inference in conditional random field for medical image segmentation

  Neural Networks 2026 · 0 citations

• BCL-YOLO: A YOLO-Based Model for Medical Image Detection

  Applied Artificial Intelligence Research 2026 · 0 citations

• AC-UKAN: An enhanced U-KAN framework integrating modulated deformable convolution and mixed pooling

  Biomedical Signal Processing and Control 2026 · 0 citations

• Depth Adaption SegNet for RGB-T Segmentation

  Applied Sciences 2026 · 0 citations

• RL-Axial: Learning When to Compute Global Context for Multimodal Segmentation

  Cognitive Computation 2026 · 0 citations

• EFMSANet: an edge-fused multi-scale attention network for building extraction from remote sensing images

  International Journal of Remote Sensing 2026 · 0 citations

• An automated machine-vision method for coarse aggregate gradation measurement using attention-based instance segmentation

  Engineering Applications of Artificial Intelligence 2026 · 0 citations

• PipeDet: Pipe Detection in the Complex Structured Environment of Aeroengine Outer Profile

  ACM Transactions on Multimedia Computing Communications and Applications 2026 · 0 citations

• Boundary-Aware Semantic Segmentation Method for Identification of Maceral Components of Deep Coal Reservoir

  SPE Asia Pacific Oil & Gas Conference and Exhibition (APOGCE) 2026 · 0 citations

• FRA-YOLO: Frequency-guided receptive-field adaptation for occluded ship detection in complex nearshore backgrounds

  Ocean Engineering 2026 · 0 citations

• A Lightweight Coastal Litter Segmentation Network with Feature Gating and Multiscale Context for UAV Imagery

  Remote Sensing 2026 · 0 citations

• Lightweight sea-ice segmentation for resource-constrained polar navigation applications

  Ocean Engineering 2026 · 0 citations

• HSMTL-Net: A Multi-Task Learning Framework for Human Segmentation with Integrated Regression and Classification Modules

  Unspecified venue · 0 citations

• An Improved ResU-Net for Thermally Grown Oxide Layer Segmentation in Thermal Barrier Coatings

  SAE technical papers on CD-ROM/SAE technical paper series 2026 · 0 citations

• Detection of Road Surface Ice and Snow Cover Using the HPC-D Segmentation Algorithm Combined with the SCI Illumination Enhancement Model

  Applied System Innovation 2026 · 0 citations