Few Shot Object Detection On Ms Coco 10 Shot

评估指标

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
CD-ViTO	35.3	Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector
DE-ViT	34.0	Detect Everything with Few Examples
BIOT	26.3	Balanced ID-OOD tradeoff transfer makes query based detectors good few shot learners	-
RISF (SWIN-Large)	25.5	Re-Scoring Using Image-Language Similarity for Few-Shot Object Detection
DETReg-ft-full DDETR	25	DETReg: Unsupervised Pretraining with Region Priors for Object Detection
imTED+ViT-B	22.5	Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection
hANMCL	22.4	Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning
RISF (Resnet-101)	21.9	Re-Scoring Using Image-Language Similarity for Few-Shot Object Detection
DCFS	19.5	Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation	-
CFA-DeFRCN	19.1	CFA: Constraint-based Finetuning Approach for Generalized Few-Shot Object Detection	-
DAnA-FasterRCNN	18.6	Dual-Awareness Attention for Few-Shot Object Detection
DeFRCN	18.5	DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection
Meta-DETR (Multi-Scale Feature)	17.8	Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
Meta-DETR (Single-Scale Feature)	16.7	Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
FSRN (RetinaNet)	15.8	Towards Discriminative and Transferable One-Stage Few-Shot Object Detectors	-
CME	15.1	Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
imTED+ViT-S	15.0	Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection
FSDetView + PSP	13.4	Few-Shot Object Detection by Attending to Per-Sample-Prototype	-
PnP-FSOD + CT	13.3	Instant Response Few-shot Object Detection with Meta Strategy and Explicit Localization Inference
FSDetView	12.5	Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild

0 of 32 row(s) selected.