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.

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

30 shown of 58 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 551. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples 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 ran 3 of 4 samples (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 ran 4 of 7 samples (3 unverified)
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 ran 9 of 11 samples (2 unverified)
Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection 3 6 16 May 2024 ran 1 of 2 samples (1 unverified)
DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data 1 2 16 May 2024 not harvested
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 ran 0 of 3 samples (3 unverified)
CLIM: Contrastive Language-Image Mosaic for Region Representation 1 1 18 Dec 2023 ran 1 of 3 samples (2 unverified; 3 pointer-only for licence)
General Object Foundation Model for Images and Videos at Scale 1 2 14 Dec 2023 ran 8 of 13 samples (5 unverified)
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 ran 6 of 8 samples (2 unverified; 8 pointer-only for licence)
Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection 1 1 18 Oct 2023 ran 5 of 7 samples (2 unverified; 7 pointer-only for licence)
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction 1 1 2 Oct 2023 ran 2 of 6 samples (4 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 ran 15 of 20 samples (5 unverified)
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 ran 3 of 4 samples (1 unverified)
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers 2 1 11 May 2023 ran 5 of 8 samples (3 unverified)
Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition 1 1 10 Apr 2023 ran 5 of 7 samples (2 unverified)
Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection 1 1 10 Mar 2023 not harvested

The full list of 58 is in the JSON twin.

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