Zero-Shot Semantic Segmentation

Benchmarks archive 2025-07-28

4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

3 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

29 shown of 29 papers with code (60 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
  28 May 2019 144 repositories listed Syntology ran 171 of 302 samples · 131 unverified · 112 pointer-only (licence)
  Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available.
• FLAIR: VLM with Fine-grained Language-informed Image Representations
  4 Dec 2024 2 repositories listed Syntology ran 3 of 20 samples · 17 unverified · 20 pointer-only (licence)
  CLIP has shown impressive results in aligning images and texts at scale.
• A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model
  29 Dec 2021 2 repositories listed
  However, semantic segmentation and the CLIP model perform on different visual granularity, that semantic segmentation processes on pixels while CLIP performs on images.
• Context-aware Feature Generation for Zero-shot Semantic Segmentation
  16 Aug 2020 2 repositories listed
  In this paper, we propose a novel context-aware feature generation method for zero-shot segmentation named CaGNet.
• Zero-Shot Semantic Segmentation
  3 Jun 2019 2 repositories listed
  Semantic segmentation models are limited in their ability to scale to large numbers of object classes.
• 3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gap
  16 Apr 2025 1 repository listed
  Existing zero-shot 3D point cloud segmentation methods often struggle with limited transferability from seen classes to unseen classes and from semantic to visual space.
• OpenObj: Open-Vocabulary Object-Level Neural Radiance Fields with Fine-Grained Understanding
  12 Jun 2024 1 repository listed
  In recent years, there has been a surge of interest in open-vocabulary 3D scene reconstruction facilitated by visual language models (VLMs), which showcase remarkable capabilities in open-set retrieval.
• DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut
  5 Jun 2024 1 repository listed Syntology ran 1 of 2 samples · 1 unverified
  Foundation models have emerged as powerful tools across various domains including language, vision, and multimodal tasks.
• Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation
  2 Jun 2024 1 repository listed Syntology ran 6 of 7 samples · 1 unverified
  Our Cascade-CLIP is flexible and can be easily applied to existing zero-shot semantic segmentation methods.
• OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation
  21 Mar 2024 1 repository listed Syntology ran 9 of 10 samples · 1 unverified · 10 pointer-only (licence)
  The recent success of CLIP has demonstrated promising results in zero-shot semantic segmentation by transferring muiltimodal knowledge to pixel-level classification.
• Exploring Regional Clues in CLIP for Zero-Shot Semantic Segmentation
  1 Jan 2024 1 repository listed
  On the other hand overfitting should be mitigated during the training stage.
• Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors
  1 Jan 2024 1 repository listed
  The recent advent of pre-trained vision transformers has unveiled a promising property: their inherent capability to group semantically related visual concepts.
• Spectral Prompt Tuning:Unveiling Unseen Classes for Zero-Shot Semantic Segmentation
  20 Dec 2023 1 repository listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Recently, CLIP has found practical utility in the domain of pixel-level zero-shot segmentation tasks.
• SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference
  4 Dec 2023 1 repository listed Syntology ran 3 of 6 samples · 3 unverified
  Specifically, we replace the traditional self-attention block of CLIP vision encoder's last layer by our CSA module and reuse its pretrained projection matrices of query, key, and value, leading to a training-free…
• An easy zero-shot learning combination: Texture Sensitive Semantic Segmentation IceHrNet and Advanced Style Transfer Learning Strategy
  30 Sep 2023 1 repository listed
  First, we built a river ice semantic segmentation dataset IPC_RI_SEG using a fixed camera and covering the entire ice melting process of the river.
• CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free
  25 Sep 2023 1 repository listed Syntology ran 7 of 7 samples · 0 unverified · 7 pointer-only (licence)
  The emergence of CLIP has opened the way for open-world image perception.
• What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation
  27 Jun 2023 1 repository listed Syntology ran 0 of 3 samples · 3 unverified
  To address this problem, zero-shot semantic segmentation makes use of large self-supervised vision-language models, allowing zero-shot transfer to unseen classes.
• Delving into Shape-aware Zero-shot Semantic Segmentation
  17 Apr 2023 1 repository listed
  Thanks to the impressive progress of large-scale vision-language pretraining, recent recognition models can classify arbitrary objects in a zero-shot and open-set manner, with a surprisingly high accuracy.
• Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network
  3 Apr 2023 1 repository listed
  Recently, the open-vocabulary semantic segmentation problem has attracted increasing attention and the best performing methods are based on two-stream networks: one stream for proposal mask generation and the other for…
• ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Prompts
  28 Jan 2023 1 repository listed
  In particular, we introduce a novel Multiple Prompt Optimal Transport Solver (MPOT), which is designed to learn an optimal mapping between multiple text prompts and visual feature maps of the frozen image encoder hidden…
• Zero-Shot Point Cloud Segmentation by Semantic-Visual Aware Synthesis
  1 Jan 2023 1 repository listed
  Given only the class-level semantic information for unseen objects, we strive to enhance the correspondence, alignment and consistency between the visual and semantic spaces, to synthesise diverse, generic and…
• ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation
  7 Dec 2022 1 repository listed Syntology ran 8 of 9 samples · 1 unverified
  Recently, CLIP has been applied to pixel-level zero-shot learning tasks via a two-stage scheme.
• Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models
  4 Nov 2022 1 repository listed
  Pretrained vision-language models (VLMs) such as CLIP have shown impressive generalization capability in downstream vision tasks with appropriate text prompts.
• Decoupling Zero-Shot Semantic Segmentation
  15 Dec 2021 1 repository listed
  2) a zero-shot classification task on segments.
• Extract Free Dense Labels from CLIP
  2 Dec 2021 1 repository listed
  Contrastive Language-Image Pre-training (CLIP) has made a remarkable breakthrough in open-vocabulary zero-shot image recognition.
• A Closer Look at Self-training for Zero-Label Semantic Segmentation
  21 Apr 2021 1 repository listed
  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.
• From Pixel to Patch: Synthesize Context-aware Features for Zero-shot Semantic Segmentation
  25 Sep 2020 1 repository listed
  Thus, we focus on zero-shot semantic segmentation, which aims to segment unseen objects with only category-level semantic representations provided for unseen categories.
• Learning unbiased zero-shot semantic segmentation networks via transductive transfer
  1 Jul 2020 1 repository listed
  Our method assumes that both the source images with full pixel-level labels and unlabeled target images are available during training.
• Semantic Projection Network for Zero- and Few-Label Semantic Segmentation
  1 Jun 2019 1 repository listed
  In this paper we take this one step further and focus on the challenging task of zero- and few-shot learning of semantic segmentation.

Syntology lines on 10 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.