COCO-Stuff

COCO-Stuff augments all 164K images of the popular COCO dataset with pixel-level stuff annotations. These annotations can be used for scene understanding tasks like semantic segmentation, object detection and image captioning.

Papers using COCO-Stuff (11)

Segnext: Rethinking Convolutional Attention Design For Semantic Segmentation2022 · 483 citesOpen-vocabulary Semantic Segmentation With Mask-adapted CLIP2022 · 396 citesSeaformer++: Squeeze-enhanced Axial Transformer For Mobile Visual Recognition2023 · 82 citesRtformer: Efficient Design For Real-time Semantic Segmentation With Transformer2022 · 76 citesIn Defense Of Lazy Visual Grounding For Open-vocabulary Semantic Segmentation2024 · 15 citesExample-guided Image Synthesis Across Arbitrary Scenes Using Masked Spatial-channel Attention And Self-supervision2020 · 4 citesExample-guided Scene Image Synthesis Using Masked Spatial-channel Attention And Patch-based Self-supervision2019 · 3 citesLow-Resolution Self-Attention for Semantic Segmentation2023 · 2 citesARTA: Adaptive Mixed-resolution Token Allocation For Efficient Dense Feature Extraction2026Cross-domain Semantic Segmentation With Large Language Model-assisted Descriptor Generation2025Context-Aware Automatic Occlusion Removal2019