AI Paper Atlas

Research map / Benchmarks / COD10K

COD10K leaderboard

37 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on COD10K. Best MAE: 0.014 (CODiff (1 step), 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.

COD10K · MAE

22 papers, each with its best reported number for its own method; lower is better.

12 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

COD10K · S-measure

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

7 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

COD10K · Sα

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

1 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

COD10K · weighted F-measure

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

#weighted F-measure ↑MethodPaperTopic
10.852CODiff (1 step)
DINOv2-ViT-B14 (frozen)
CODiff: One-Step Diffusion Model for Camouflaged Object Detection
ICML 2026 · Table 1
CNN features
20.808MM-SAMMulti-modal Segment Anything Model for Camouflaged Scene Segmentation
ICCV 2025 · Table 1
Open-set and few-shot detection
30.804ESCNet
PVTv2-b4
ESCNet:Edge-Semantic Collaborative Network for Camouflaged Object Detection
ICCV 2025 · Table 1
CNN features
40.735FSPNet
ViT
Feature Shrinkage Pyramid for Camouflaged Object Detection With Transformers
CVPR 2023 · Table 1
CNN features
50.68SINetConcealed Object Detection
TPAMI 2021 · Table 2
Open-set and few-shot detection
60.65Ours (point-supervised)
PVT
Just a Hint: Point-Supervised Camouflaged Object Detection
ECCV 2024 · Table 1
Weakly supervised detection and segmentation
70.635DualUCOD
DINOv2
Unsupervised Camouflaged Object Detection with Dual-Eigenvector Spectral Pseudo-Labeling and Contrastive Refinement
ICML 2026 · Table 1
Open-set and few-shot detection
80.6RISE (unsupervised)
DINOv2-ViT-L14
Beyond Single Images: Retrieval Self-Augmented Unsupervised Camouflaged Object Detection
ICCV 2025 · Table 1
Weakly supervised detection and segmentation
90.576Ours (CRNet)
ResNet-50
Weakly-Supervised Camouflaged Object Detection with Scribble Annotations
AAAI 2023 · Table 1
Weakly supervised detection and segmentation
100.5628EReCu
DINO ViT-S/8
EReCu: Pseudo-label Evolution Fusion and Refinement with Multi-Cue Learning for Unsupervised Camouflage Detection
CVPR 2026 · Table 1
Weakly supervised detection and segmentation

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