Browse State-of-the-Art › Zero-Shot Learning

Zero-Shot Learning

787 papers with code · 33 benchmarks · 43 datasets archive 2025-07-28

Computer VisionMethodology

Zero-shot learning (ZSL) is a model's ability to detect classes never seen during training. The condition is that the classes are not known during supervised learning.

Earlier work in zero-shot learning use attributes in a two-step approach to infer unknown classes. In the computer vision context, more recent advances learn mappings from image feature space to semantic space. Other approaches learn non-linear multimodal embeddings. In the modern NLP context, language models can be evaluated on downstream tasks without fine tuning.

Benchmark datasets for zero-shot learning include aPY, AwA, and CUB, among others.

( Image credit: Prototypical Networks for Few shot Learning in PyTorch )

Further readings:

Description from the archive archive 2025-07-28; Papers-with-Code links inside it are rewritten to this site.

Benchmarks archive 2025-07-28

33 leaderboard tables shown for this task, 33 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. 10 shown of 33 until expanded.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
CUB-200-2011 (14 rows) ZeroDiff Exploring Data Efficiency in Zero-Shot Learning with Diffusion Models — — Compare
MedConceptsQA (13 rows) gpt-4-0125-preview GPT-4 Technical Report code Syntology community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
SUN Attribute (9 rows) ZeroDiff Exploring Data Efficiency in Zero-Shot Learning with Diffusion Models — — Compare
AwA2 (4 rows) ZeroDiff Exploring Data Efficiency in Zero-Shot Learning with Diffusion Models — — Compare
Caltech-101 (2 rows) ZLaP Label Propagation for Zero-shot Classification with Vision-Language Models code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
CIFAR-10 (2 rows) ZLaP* Label Propagation for Zero-shot Classification with Vision-Language Models code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
CIFAR-100 (2 rows) ZLaP* Label Propagation for Zero-shot Classification with Vision-Language Models code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
COCO-MLT (2 rows) ResNet-50 Learning Transferable Visual Models From Natural Language Supervision code Syntology official: no sample here; runs from other or unrecorded repositories · 16 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 4 unverified Compare
DTD (2 rows) ZLaP Label Propagation for Zero-shot Classification with Vision-Language Models code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
FGVC-Aircraft (2 rows) ZLaP Label Propagation for Zero-shot Classification with Vision-Language Models code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
Flowers-102 (2 rows) ZLaP Label Propagation for Zero-shot Classification with Vision-Language Models code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
Food-101 (2 rows) ZLaP* Label Propagation for Zero-shot Classification with Vision-Language Models code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
ImageNet (2 rows) ZLaP Label Propagation for Zero-shot Classification with Vision-Language Models code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
Oxford 102 Flower (2 rows) SPOT Synthetic Sample Selection for Generalized Zero-Shot Learning — — Compare
Oxford-IIIT Pets (2 rows) ZLaP Label Propagation for Zero-shot Classification with Vision-Language Models code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
Stanford Cars (2 rows) ZLaP* Label Propagation for Zero-shot Classification with Vision-Language Models code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
SUN397 (2 rows) ZLaP* Label Propagation for Zero-shot Classification with Vision-Language Models code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
UCF101 (2 rows) ZLaP Label Propagation for Zero-shot Classification with Vision-Language Models code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
VOC-MLT (2 rows) CLIP(ResNet-50) Learning Transferable Visual Models From Natural Language Supervision code Syntology official: no sample here; runs from other or unrecorded repositories · 16 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 4 unverified Compare
aPY - 0-Shot (1 row) ZSL-KG Zero-Shot Learning with Common Sense Knowledge Graphs code — Compare
CUB-200 - 0-Shot Learning (1 row) zsl_ADA A Generative Framework for Zero-Shot Learning with Adversarial... code — Compare
EuroSAT (1 row) ZLaP* Label Propagation for Zero-shot Classification with Vision-Language Models code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
GDSCv2 (1 row) MSDA Zero-shot Learning of Drug Response Prediction for Preclinical... code — Compare
How2QA (1 row) SeViLA — — — Compare
ImageNet_CN (1 row) M²-Encoder M2-Encoder: Advancing Bilingual Image-Text Understanding by... code — Compare
iVQA (1 row) FrozenBiLM Zero-Shot Video Question Answering via Frozen Bidirectional Language Models code Syntology official: harvested, nothing ran · 14 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 20 unverified Compare
LSMDC (1 row) FrozenBiLM Zero-Shot Video Question Answering via Frozen Bidirectional Language Models code Syntology official: harvested, nothing ran · 14 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 20 unverified Compare
MIT-States (1 row) CZSL LOCL: Learning Object-Attribute Composition using Localization code — Compare
MSRVTT-QA (1 row) HiTeA HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training — — Compare
MSVD-QA (1 row) HiTeA HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training — — Compare
PASCAL Context (1 row) ZS3Net Zero-Shot Semantic Segmentation code — Compare
SNIPS (1 row) ZSL-KG Zero-Shot Learning with Common Sense Knowledge Graphs code — Compare
TVQA (1 row) VideoChat2 MVBench: A Comprehensive Multi-modal Video Understanding Benchmark code Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified Compare

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. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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

43 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 43 until expanded.

Subtasks archive 2025-07-28

7 subtasks in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 1,864 · with a code link: 787 · where Syntology ran a sample: 245 (196 with a run with no instrument failure, 49 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (245 of 1,864 tagged: 196 with a run with no instrument failure, 49 where every run was a failure of Syntology's instrument)

Page 1 of 19: papers 1 to 100 of 1,864, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 63 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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections