# Coarse-to-fine Semantic Segmentation from Image-level Labels

arXiv: https://arxiv.org/abs/1812.10885 · HTML: https://mlsanity.com/paper/1812.10885/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2018.

## Built on by (most cited first, 28 of 28)

- [TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment](https://mlsanity.com/paper/2308.03060/) (2023)
- [Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes](https://mlsanity.com/paper/2101.06085/) (2021)
- [Wide-Depth-Range 6D Object Pose Estimation in Space](https://mlsanity.com/paper/2104.00337/) (2021)
- [Fully Transformer Networks for Semantic Image Segmentation](https://mlsanity.com/paper/2106.04108/) (2021)
- [Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval](https://mlsanity.com/paper/2308.06748/) (2023)
- [CycleSegNet: Object Co-segmentation with Cycle Refinement and Region Correspondence](https://mlsanity.com/paper/2101.01308/) (2021)
- [Few-Shot Segmentation with Global and Local Contrastive Learning](https://mlsanity.com/paper/2108.05293/) (2021)
- [Spatial Structure Constraints for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2401.11122/) (2024)
- [Multi-Granularity Denoising and Bidirectional Alignment for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2305.05154/) (2023)
- [HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation](https://mlsanity.com/paper/2111.02333/) (2021)
- [Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2407.02768/) (2024)
- [Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays](https://mlsanity.com/paper/2207.04394/) (2022)
- [CRCNet: Few-shot Segmentation with Cross-Reference and Region-Global Conditional Networks](https://mlsanity.com/paper/2208.10761/) (2022)
- [Applications of Deep Learning in Fish Habitat Monitoring: A Tutorial and Survey](https://mlsanity.com/paper/2206.05394/) (2022)
- [DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation](https://mlsanity.com/paper/2406.03702/) (2024)
- [Surface-SOS: Self-Supervised Object Segmentation via Neural Surface Representation](https://mlsanity.com/paper/2501.09947/) (2025)
- [Semi-Supervised Confidence-Level-based Contrastive Discrimination for Class-Imbalanced Semantic Segmentation](https://mlsanity.com/paper/2211.15066/) (2022)
- [Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.05463/) (2021)
- [TSGB: Target-Selective Gradient Backprop for Probing CNN Visual Saliency](https://mlsanity.com/paper/2110.05182/) (2021)
- [Boosting Medical Image-based Cancer Detection via Text-guided Supervision from Reports](https://mlsanity.com/paper/2405.14230/) (2024)
- [Free-Mask: A Novel Paradigm of Integration Between the Segmentation Diffusion Model and Image Editing](https://mlsanity.com/paper/2411.01819/) (2024)
- [Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning](https://mlsanity.com/paper/2503.00515/) (2025)
- [AASeg: Attention Aware Network for Real Time Semantic Segmentation](https://mlsanity.com/paper/2108.04349/) (2021)
- [VS-CAM: Vertex Semantic Class Activation Mapping to Interpret Vision Graph Neural Network](https://mlsanity.com/paper/2209.09104/) (2022)
- [A Robust Morphological Approach for Semantic Segmentation of Very High Resolution Images](https://mlsanity.com/paper/2208.01254/) (2022)
- [Semi-supervised segmentation of land cover images using nonlinear canonical correlation analysis with multiple features and t-SNE](https://mlsanity.com/paper/2401.12164/) (2024)
- [Speeding up the annotation process in semantic segmentation industrial applications](https://mlsanity.com/paper/2606.19934/) (2026)
- [Widest-Path Reachability Fields for Connectivity-Preserving Slender Structure Segmentation](https://mlsanity.com/paper/2607.07123/) (2026)

## Abstract (arXiv)

Deep neural network-based semantic segmentation generally requires large-scale cost extensive annotations for training to obtain better performance. To avoid pixel-wise segmentation annotations which are needed for most methods, recently some researchers attempted to use object-level labels (e.g. bounding boxes) or image-level labels (e.g. image categories). In this paper, we propose a novel recursive coarse-to-fine semantic segmentation framework based on only image-level category labels. For each image, an initial coarse mask is first generated by a convolutional neural network-based unsupervised foreground segmentation model and then is enhanced by a graph model. The enhanced coarse mask is fed to a fully convolutional neural network to be recursively refined. Unlike existing image-level label-based semantic segmentation methods which require to label all categories for images contain multiple types of objects, our framework only needs one label for each image and can handle images contains multi-category objects. With only trained on ImageNet, our framework achieves comparable performance on PASCAL VOC dataset as other image-level label-based state-of-the-arts of semantic segmentation. Furthermore, our framework can be easily extended to foreground object segmentation task and achieves comparable performance with the state-of-the-art supervised methods on the Internet Object dataset.