Data to 7 Oct 2026

Zero-Shot Semantic Segmentation

arXiv 1906.00817 ↗First posted 3 Jun 2019cs.CVcited by 245

Not on the map. Why?

Cited by 36 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Semantic segmentation models are limited in their ability to scale to large numbers of object classes. In this paper, we introduce the new task of zero-shot semantic segmentation: learning pixel-wise classifiers for never-seen object categories with zero training examples. To this end, we present a novel architecture, ZS3Net, combining a deep visual segmentation model with an approach to generate visual representations from semantic word embeddings. By this way, ZS3Net addresses pixel classification tasks where both seen and unseen categories are faced at test time (so called "generalized" zero-shot classification). Performance is further improved by a self-training step that relies on automatic pseudo-labeling of pixels from unseen classes. On the two standard segmentation datasets, Pascal-VOC and Pascal-Context, we propose zero-shot benchmarks and set competitive baselines. For complex scenes as ones in the Pascal-Context dataset, we extend our approach by using a graph-context encoding to fully leverage spatial context priors coming from class-wise segmentation maps.

Key facts. Cited by 245 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 27; 2022: 31; 2023: 79; 2024: 52; 2025: 38; 2026: 18.

245 papers.

Sort:

By area:

2022Language-driven Semantic Segmentationcited by 711
2021Extract Free Dense Labels from CLIPcited by 580
2022Open-Vocabulary Semantic Segmentation with Mask-adapted CLIPcited by 560
2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 529
2021Image Segmentation Using Text and Image Promptscited by 509
2021Scaling Open-Vocabulary Image Segmentation with Image-Level Labelscited by 471
2023Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Modelscited by 371
2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 361
2023Side Adapter Network for Open-Vocabulary Semantic Segmentationcited by 296
2022GLIPv2: Unifying Localization and Vision-Language Understandingcited by 275
2021A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Modelcited by 223

38 more

2023CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentationcited by 215
2023Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIPcited by 199
2021Decoupling Zero-Shot Semantic Segmentationcited by 198
2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
2022ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentationcited by 178
2022PLA: Language-Driven Open-Vocabulary 3D Scene Understandingcited by 176
2023Towards Open Vocabulary Learning: A Surveycited by 165
2022SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentationcited by 162
2023DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Modelscited by 162
2023Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusioncited by 131
2023DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Modelscited by 122
2022ReCo: Retrieve and Co-segment for Zero-shot Transfercited by 115
2022Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learningcited by 115
2023Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervisioncited by 99
2023SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentationcited by 95
2023FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentationcited by 94
2023CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentationcited by 94
2023CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIPcited by 89
2023Grounding Everything: Emerging Localization Properties in Vision-Language Transformerscited by 89
2021Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labelingcited by 84
2022Perceptual Grouping in Contrastive Vision-Language Modelscited by 82
2023Open-vocabulary Object Segmentation with Diffusion Modelscited by 82
2023CLIP as RNN: Segment Countless Visual Concepts without Training Endeavorcited by 69
2022Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embeddingcited by 67
2023SILC: Improving Vision Language Pretraining with Self-Distillationcited by 66
2023Diffusion Models for Open-Vocabulary Segmentationcited by 63
2023SATR: Zero-Shot Semantic Segmentation of 3D Shapescited by 62
2023A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Futurecited by 59
2021A Closer Look at Self-training for Zero-Label Semantic Segmentationcited by 57
2023Learning Mask-aware CLIP Representations for Zero-Shot Segmentationcited by 57
2021Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Cloudscited by 55
2023Towards Label-free Scene Understanding by Vision Foundation Modelscited by 54
2021Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentationcited by 53
2023Hierarchical Open-vocabulary Universal Image Segmentationcited by 53
2024POP-3D: Open-Vocabulary 3D Occupancy Prediction from Imagescited by 52
2023Open-Vocabulary Segmentation with Semantic-Assisted Calibrationcited by 49
2024Better Call SAL: Towards Learning to Segment Anything in Lidarcited by 47
2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46

50 most cited of 245 All 245 (JSON)