Datasets › LVIS

LVIS

Introduced by Agrim Gupta et al. in LVIS: A Dataset for Large Vocabulary Instance Segmentation archive 2025-07-28

LVIS is a dataset for long tail instance segmentation. It has annotations for over 1000 object categories in 164k images.

Source: LVIS

Benchmarks archive 2025-07-28

All 12 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Syntology 1 newer paper was judged to report on this dataset's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Zero-Shot Object Detection · LVIS v1.0 val (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

First row (archive order)PaperCode
Open Vocabulary Object Detection LVIS v1.0 LaMI-DETR AP novel-LVIS base training 43.4 LaMI-DETR: Open-Vocabulary Detection with Language Model... eternaldolphin/lami-detr 28 Compare
Instance Segmentation LVIS v1.0 val Co-DETR (single-scale) mask AP 60.7 DETRs with Collaborative Hybrid Assignments Training open-mmlab/mmdetection +5 25 Compare
Object Detection LVIS v1.0 val Co-DETR (single-scale) box AP 68.0 DETRs with Collaborative Hybrid Assignments Training open-mmlab/mmdetection +5 15 Compare
Zero-Shot Object Detection LVIS v1.0 minival CP-DETR-Pro(without LVIS data) AP 58.2 CP-DETR: Concept Prompt Guide DETR Toward Stronger... — 11 Compare
Zero-Shot Object Detection LVIS v1.0 val CP-DETR-Pro(without LVIS data) AP 51.6 CP-DETR: Concept Prompt Guide DETR Toward Stronger... — 9 Compare
Few-Shot Object Detection LVIS v1.0 val best_single_model_val AP 47.55 — — 7 Compare
Object Detection LVIS v1.0 minival Co-DETR (single-scale) box AP 72.0 DETRs with Collaborative Hybrid Assignments Training open-mmlab/mmdetection +5 6 Compare
Few-Shot Object Detection LVIS v1.0 test-dev TestConsistency AP 48.58 — — 5 Compare
Novel Object Detection LVIS v1.0 val Cooperative Foundational Models All mAP 19.33 Enhancing Novel Object Detection via Cooperative... rohit901/cooperative-foundational-models 5 Compare
Instance Segmentation LVIS v1.0 test-dev R50-FPN-MaskRCNN-TTA mask AP 41.23 1st Place Solution of LVIS Challenge 2020: A Good Box is... — 1 Compare
Long-tailed Object Detection LVIS v1.0 val R101 Faster R-CNN mAP@0.5:0.95 27.8 Balanced Classification: A Unified Framework for... tianhao-qi/bacl 1 Compare
Object Detection LVIS v1.0 ScaleDet box AP 50.7 ScaleDet: A Scalable Multi-Dataset Object Detector — 1 Compare

Papers archive 2025-07-28

papers with a benchmark row: 58 · with a code link: 52 · where Syntology ran a sample: 28 (25 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (28 of 58 with a benchmark row: 25 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 58 of 58 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 551. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A 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” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (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. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection 1 2 28 Dec 2024 not harvested
Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection 1 1 23 Dec 2024 not harvested
CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection 0 3 13 Dec 2024 not harvested
Fractal Calibration for long-tailed object detection 1 3 15 Oct 2024 not harvested
LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction 1 1 16 Jul 2024 official (archive's flag): 3 ran · 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified
Adaptive Parametric Activation 1 2 11 Jul 2024 not harvested
OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion 1 2 10 Jul 2024 not harvested
OVMR: Open-Vocabulary Recognition with Multi-Modal References 1 1 7 Jun 2024 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (2 pointer-only for licence)
RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection 1 1 30 May 2024 not harvested
OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision 1 2 28 May 2024 official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified (2 pointer-only for licence)
DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data 1 2 16 May 2024 not harvested
Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection 3 6 16 May 2024 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
Retrieval-Augmented Open-Vocabulary Object Detection 1 1 8 Apr 2024 not harvested
YOLO-World: Real-Time Open-Vocabulary Object Detection 3 1 30 Jan 2024 community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified
CLIM: Contrastive Language-Image Mosaic for Region Representation 1 1 18 Dec 2023 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (3 pointer-only for licence)
General Object Foundation Model for Images and Videos at Scale 1 2 14 Dec 2023 official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified (3 pointer-only for licence)
Enhancing Novel Object Detection via Cooperative Foundational Models 1 1 19 Nov 2023 not harvested
CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection 1 1 25 Oct 2023 official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (8 pointer-only for licence)
Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection 1 1 18 Oct 2023 official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (7 pointer-only for licence)
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction 1 1 2 Oct 2023 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (6 pointer-only for licence)
Region-centric Image-Language Pretraining for Open-Vocabulary Detection 2 1 29 Sep 2023 not harvested
Detect Everything with Few Examples 1 1 22 Sep 2023 official (archive's flag): 17 ran · 17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified (1 pointer-only for licence)
Contrastive Feature Masking Open-Vocabulary Vision Transformer 0 1 2 Sep 2023 not harvested
Balanced Classification: A Unified Framework for Long-Tailed Object Detection 1 1 4 Aug 2023 not harvested
Scaling Open-Vocabulary Object Detection 3 2 16 Jun 2023 not harvested
ScaleDet: A Scalable Multi-Dataset Object Detector 0 1 8 Jun 2023 not harvested
Multi-modal Queried Object Detection in the Wild 1 6 30 May 2023 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (4 pointer-only for licence)
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers 2 1 11 May 2023 official (archive's flag): 5 ran · 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified
Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition 1 1 10 Apr 2023 official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (3 pointer-only for licence)
Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection 1 1 10 Mar 2023 not harvested
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection 10 1 9 Mar 2023 official (archive's flag): 1 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result
Aligning Bag of Regions for Open-Vocabulary Object Detection 1 1 27 Feb 2023 not harvested
X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion 2 3 7 Dec 2022 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (3 pointer-only for licence)
DiffusionInst: Diffusion Model for Instance Segmentation 2 4 6 Dec 2022 official: harvested, nothing ran · 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified (7 pointer-only for licence)
DETRs with Collaborative Hybrid Assignments Training 6 3 22 Nov 2022 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information 1 1 17 Nov 2022 not harvested
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale 6 2 14 Nov 2022 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions 3 2 10 Nov 2022 official: harvested, nothing ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified
Learning to Discover and Detect Objects 1 1 19 Oct 2022 official: harvested, nothing ran · 0 ran · 1 unverified
Long-tailed Instance Segmentation using Gumbel Optimized Loss 1 2 22 Jul 2022 not harvested
Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection 1 1 7 Jul 2022 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified
Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization 2 1 22 Jun 2022 official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified
GLIPv2: Unifying Localization and Vision-Language Understanding 1 1 12 Jun 2022 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
Simple Open-Vocabulary Object Detection with Vision Transformers 2 1 12 May 2022 not harvested
Exploring Plain Vision Transformer Backbones for Object Detection 11 4 30 Mar 2022 community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (1 pointer-only for licence)
Detecting Twenty-thousand Classes using Image-level Supervision 1 1 7 Jan 2022 not harvested
RegionCLIP: Region-based Language-Image Pretraining 1 2 16 Dec 2021 not harvested
Grounded Language-Image Pre-training 3 2 7 Dec 2021 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (2 pointer-only for licence)
LVIS Challenge Track Technical Report 1st Place Solution: Distribution Balanced and Boundary Refinement for Large Vocabulary Instance Segmentation 0 1 4 Nov 2021 not harvested
A Unified Objective for Novel Class Discovery 1 1 19 Aug 2021 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result
Exploring Classification Equilibrium in Long-Tailed Object Detection 1 4 17 Aug 2021 official (archive's flag): 2 ran · 2 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; 1 where Syntology's instrument failed) · 0 unverified (1 pointer-only for licence)
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation 4 4 28 Apr 2021 not harvested
Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision 0 1 2 Apr 2021 not harvested
Open-World Semi-Supervised Learning 1 1 6 Feb 2021 not harvested
Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection 2 3 15 Dec 2020 not harvested
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation 5 2 13 Dec 2020 community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
1st Place Solution of LVIS Challenge 2020: A Good Box is not a Guarantee of a Good Mask 0 1 3 Sep 2020 not harvested
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation 1 1 13 Aug 2020 not harvested

Dataset loaders archive 2025-07-28

3 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Custom (CC BY 4.0 + COCO license)

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • LVIS v1.0
  • LVIS v1.0 val
  • LVIS v1.0 test-dev
  • LVIS
  • LVIS v1.0 minival

5 variant names, as the archive lists them.

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