# A Closer Look at Self-training for Zero-Label Semantic Segmentation

arXiv: https://arxiv.org/abs/2104.11692 · HTML: https://mlsanity.com/paper/2104.11692/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 50 references that are in the map.
- First posted on arXiv 21 Apr 2021.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [One-Shot Learning for Semantic Segmentation](https://mlsanity.com/paper/1709.03410/) (2017)
- [ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1604.05144/) (2016)
- [What's the Point: Semantic Segmentation with Point Supervision](https://mlsanity.com/paper/1506.02106/) (2015)
- [Label Propagation for Deep Semi-supervised Learning](https://mlsanity.com/paper/1904.04717/) (2019)
- [Feature Generating Networks for Zero-Shot Learning](https://mlsanity.com/paper/1712.00981/) (2017)
- [Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/1906.00817/) (2019)
- [Modeling the Background for Incremental Learning in Semantic Segmentation](https://mlsanity.com/paper/2002.00718/) (2020)
- [PseudoSeg: Designing Pseudo Labels for Semantic Segmentation](https://mlsanity.com/paper/2010.09713/) (2020)
- [Label-Embedding for Image Classification](https://mlsanity.com/paper/1503.08677/) (2015)
- [FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference](https://mlsanity.com/paper/1902.10421/) (2019)
- [Semi-Supervised Semantic Segmentation with High- and Low-level Consistency](https://mlsanity.com/paper/1908.05724/) (2019)
- [Latent Embeddings for Zero-shot Classification](https://mlsanity.com/paper/1603.08895/) (2016)
- [Context-aware Feature Generation for Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2008.06893/) (2020)

## Built on by (most cited first, 30 of 57)

- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model](https://mlsanity.com/paper/2112.14757/) (2021)
- [Decoupling Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2112.07910/) (2021)
- [ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2212.03588/) (2022)
- [Towards Open Vocabulary Learning: A Survey](https://mlsanity.com/paper/2306.15880/) (2023)
- [DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models](https://mlsanity.com/paper/2303.11681/) (2023)
- [DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models](https://mlsanity.com/paper/2308.06160/) (2023)
- [ReCo: Retrieve and Co-segment for Zero-shot Transfer](https://mlsanity.com/paper/2206.07045/) (2022)
- [Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision](https://mlsanity.com/paper/2301.09121/) (2023)
- [CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation](https://mlsanity.com/paper/2312.12359/) (2023)
- [FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation](https://mlsanity.com/paper/2303.17225/) (2023)
- [Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling](https://mlsanity.com/paper/2111.12698/) (2021)
- [Perceptual Grouping in Contrastive Vision-Language Models](https://mlsanity.com/paper/2210.09996/) (2022)
- [Open-vocabulary Object Segmentation with Diffusion Models](https://mlsanity.com/paper/2301.05221/) (2023)
- [SATR: Zero-Shot Semantic Segmentation of 3D Shapes](https://mlsanity.com/paper/2304.04909/) (2023)
- [Learning Mask-aware CLIP Representations for Zero-Shot Segmentation](https://mlsanity.com/paper/2310.00240/) (2023)
- [CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free](https://mlsanity.com/paper/2309.14289/) (2023)
- [DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model](https://mlsanity.com/paper/2306.01736/) (2023)
- [Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentation](https://mlsanity.com/paper/2306.11087/) (2023)
- [MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis](https://mlsanity.com/paper/2407.13675/) (2024)
- [See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data](https://mlsanity.com/paper/2307.10782/) (2023)
- [COSMOS: Cross-Modality Unsupervised Domain Adaptation for 3D Medical Image Segmentation based on Target-aware Domain Translation and Iterative Self-Training](https://mlsanity.com/paper/2203.16557/) (2022)
- [Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Picking](https://mlsanity.com/paper/2204.07049/) (2022)
- [Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2406.00670/) (2024)
- [ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Prompts](https://mlsanity.com/paper/2301.12171/) (2023)
- [Delving into Shape-aware Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2304.08491/) (2023)
- [Semantic-Promoted Debiasing and Background Disambiguation for Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2305.13173/) (2023)
- [PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation](https://mlsanity.com/paper/2406.06679/) (2024)
- [IFSeg: Image-free Semantic Segmentation via Vision-Language Model](https://mlsanity.com/paper/2303.14396/) (2023)
- [Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models](https://mlsanity.com/paper/2311.17095/) (2023)

## Abstract (arXiv)

Being able to segment unseen classes not observed during training is an important technical challenge in deep learning, because of its potential to reduce the expensive annotation required for semantic segmentation. Prior zero-label semantic segmentation works approach this task by learning visual-semantic embeddings or generative models. However, they are prone to overfitting on the seen classes because there is no training signal for them. In this paper, we study the challenging generalized zero-label semantic segmentation task where the model has to segment both seen and unseen classes at test time. We assume that pixels of unseen classes could be present in the training images but without being annotated. Our idea is to capture the latent information on unseen classes by supervising the model with self-produced pseudo-labels for unlabeled pixels. We propose a consistency regularizer to filter out noisy pseudo-labels by taking the intersections of the pseudo-labels generated from different augmentations of the same image. Our framework generates pseudo-labels and then retrain the model with human-annotated and pseudo-labelled data. This procedure is repeated for several iterations. As a result, our approach achieves the new state-of-the-art on PascalVOC12 and COCO-stuff datasets in the challenging generalized zero-label semantic segmentation setting, surpassing other existing methods addressing this task with more complex strategies.