AI Paper Atlas

Research map / Benchmarks / OV-COCO

OV-COCO leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on OV-COCO. Best AP50 novel: 52.4 (OSSD+DINOv2, ICML 2026).

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.

OV-COCO · AP50 novel

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

#AP50 novel ↑MethodPaperTopic
152.4OSSD+DINOv2
ViT-L/14
Object-level Semantic and Spatial Distillation for Open Vocabulary Detection
ICML 2026 · Table 1
Open-set and few-shot detection
250.2F-ViT+DeCLIP (ViT-L/14)Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception
TPAMI 2026 · Table 3
Open-set and few-shot detection
349.8F-ViT+SynCLIP
ViT-L/14
SynCLIP: Synonym-Coherent Language-Image Pretraining for Robust Open-Vocabulary Dense Perception
CVPR 2026 · Table 1a
CLIP and zero-shot
448.1R-SC-CLIPSelf
ViT-L/14
Refining CLIP's Spatial Awareness: A Visual-Centric Perspective
ICLR 2025 · Table: Results on open-vocabul
CLIP and zero-shot
547.8MSPL
RN50x4
CoT-PL: Chain-of-Thought Pseudo-Labeling for Open-Vocabulary Object Detection
ECCV 2026 · Table 1
Open-set and few-shot detection
647.6ESSA-OVD
ViT-L/14
Explicit Semantic–Spatial Alignment for Open-Vocabulary Object Detection
ECCV 2026 · Table 1a
Open-set and few-shot detection
747.5DeCLIP + NoOVD
ViT-L/14
NoOVD: Novel Category Discovery and Embedding for Open-Vocabulary Object Detection
CVPR 2026 · Table 2
Open-set and few-shot detection
844.3F-ViT+CLIPSelf
EVA-CLIP ViT-L/14
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
ICLR 2024 · Table: Results on open-vocabul
Open-set and few-shot detection
937.2F-ViT + ATAS
EVA-CLIP ViT-B
ATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction
ICCV 2025 · Table 3
Open-set and few-shot detection
1036.9BARON* + CLIM
RN50
CLIM: Contrastive Language-Image Mosaic for Region Representation
AAAI 2024 · Table 1
Open-set and few-shot detection
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

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