AI Paper Atlas

Research map / Benchmarks / LVIS

LVIS leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on LVIS. Best AP: 42.3 (EfficientSAM-S, CVPR 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

LVIS · AP

10 papers, each with its best reported number for its own method; higher is better.

#AP ↑MethodPaperTopic
142.3EfficientSAM-S
ViT-Small
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
CVPR 2024 · Table 5
Open-set and few-shot detection
241.4SDPT (k=120)
GLIP-L
SDPT: Synchronous Dual Prompt Tuning for Visual-Language Pre-Trained Models
TPAMI 2026 · Table 1
CLIP and zero-shot
340.9OVMR
CenterNet2, Swin-B
OVMR: Open-Vocabulary Recognition with Multi-Modal References
CVPR 2024 · Table 3
CLIP and zero-shot
440CenterMask-FCOS
ResNet-101-FPN
CenterMask: Single Shot Instance Segmentation With Point Representation
CVPR 2020 · Table: Performance of CenterMa
CNN features
532.9Ours
CenterNetV2
Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection
NeurIPS 2022 · LVIS OVD results table
Open-set and few-shot detection
631.6AIMV2
ViT-L
Multimodal Autoregressive Pre-training of Large Vision Encoders
CVPR 2025 · Table 4
CLIP and zero-shot
731.3Lhyper
HyperLearner
Hyperbolic Learning with Synthetic Captions for Open-World Detection
CVPR 2024 · Table 5
Open-set and few-shot detection
830.9MOQAM
ResNet-50
OralXrays-9: Towards Hospital-Scale Panoramic X-ray Anomaly Detection via Personalized Multi-Object Query-Aware Mining
CVPR 2025 · Table 2
Open-set and few-shot detection
928.3GOL + 3DCP
Mask-RCNN ResNet-50
Objaverse: A Universe of Annotated 3D Objects
CVPR 2023 · Table 1
Open-set and few-shot detection
1025.07DLWL
ResNeXt-101-32x8d
DLWL: Improving Detection for Lowshot Classes With Weakly Labelled Data
CVPR 2020 · Table 4
Weakly supervised detection and segmentation

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.