# STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation

arXiv: https://arxiv.org/abs/1509.03150 · HTML: https://mlsanity.com/paper/1509.03150/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2015.

## Built on by (most cited first, 30 of 78)

- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2105.08965/) (2021)
- [Large-scale Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2106.03149/) (2021)
- [Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.14581/) (2021)
- [Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast](https://mlsanity.com/paper/2110.07110/) (2021)
- [Complementary Patch for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.03852/) (2021)
- [Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.01795/) (2021)
- [CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervision](https://mlsanity.com/paper/2203.01475/) (2022)
- [Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.09653/) (2022)
- [Adaptive Early-Learning Correction for Segmentation from Noisy Annotations](https://mlsanity.com/paper/2110.03740/) (2021)
- [X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion](https://mlsanity.com/paper/2212.03863/) (2022)
- [Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2106.04054/) (2021)
- [CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection](https://mlsanity.com/paper/2112.02363/) (2021)
- [EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones](https://mlsanity.com/paper/2211.09703/) (2022)
- [Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation](https://mlsanity.com/paper/2210.17400/) (2022)
- [Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds](https://mlsanity.com/paper/2203.16045/) (2022)
- [Learning to Solve Travelling Salesman Problem with Hardness-adaptive Curriculum](https://mlsanity.com/paper/2204.03236/) (2022)
- [Artificial Intelligence for the Metaverse: A Survey](https://mlsanity.com/paper/2202.10336/) (2022)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.01344/) (2021)
- [WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation](https://mlsanity.com/paper/2304.01184/) (2023)
- [Domain Generalization via Balancing Training Difficulty and Model Capability](https://mlsanity.com/paper/2309.00844/) (2023)
- [Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2206.09554/) (2022)
- [EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training](https://mlsanity.com/paper/2405.08768/) (2024)
- [Multi-Granularity Denoising and Bidirectional Alignment for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2305.05154/) (2023)
- [RealCustom++: Representing Images as Real Textual Word for Real-Time Customization](https://mlsanity.com/paper/2408.09744/) (2024)
- [Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation](https://mlsanity.com/paper/2102.10935/) (2021)
- [Gaussian Dynamic Convolution for Efficient Single-Image Segmentation](https://mlsanity.com/paper/2104.08783/) (2021)
- [Weakly Supervised Semantic Segmentation via Progressive Patch Learning](https://mlsanity.com/paper/2209.07828/) (2022)
- [Progressive Self-Guided Loss for Salient Object Detection](https://mlsanity.com/paper/2101.02412/) (2021)

## Abstract (arXiv)

Recently, significant improvement has been made on semantic object segmentation due to the development of deep convolutional neural networks (DCNNs). Training such a DCNN usually relies on a large number of images with pixel-level segmentation masks, and annotating these images is very costly in terms of both finance and human effort. In this paper, we propose a simple to complex (STC) framework in which only image-level annotations are utilized to learn DCNNs for semantic segmentation. Specifically, we first train an initial segmentation network called Initial-DCNN with the saliency maps of simple images (i.e., those with a single category of major object(s) and clean background). These saliency maps can be automatically obtained by existing bottom-up salient object detection techniques, where no supervision information is needed. Then, a better network called Enhanced-DCNN is learned with supervision from the predicted segmentation masks of simple images based on the Initial-DCNN as well as the image-level annotations. Finally, more pixel-level segmentation masks of complex images (two or more categories of objects with cluttered background), which are inferred by using Enhanced-DCNN and image-level annotations, are utilized as the supervision information to learn the Powerful-DCNN for semantic segmentation. Our method utilizes 40K simple images from Flickr.com and 10K complex images from PASCAL VOC for step-wisely boosting the segmentation network. Extensive experimental results on PASCAL VOC 2012 segmentation benchmark well demonstrate the superiority of the proposed STC framework compared with other state-of-the-arts.