Startseite Neuigkeiten Neueste Forschungsarbeiten Tutorials Datensätze Wiki SOTA LLM-Modelle GPU-Rangliste Veranstaltungen

Deutsch

Object Counting On Fsc147

Metriken

MAE(test)

MAE(val)

RMSE(test)

RMSE(val)

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	MAE(test)	MAE(val)	RMSE(test)	RMSE(val)	Paper Title	Repository
GeCo	7.91	9.52	54.28	43.00	A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
RCC	17.12	17.49	104.53	58.81	Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision
SAFECount	14.32	15.28	85.54	47.20	Few-shot Object Counting with Similarity-Aware Feature Enhancement
Counting-DETR	16.79	-	123.56	-	Few-shot Object Counting and Detection
GCA-SUN	14.00	16.06	92.19	53.04	GCA-SUN: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting	-
CounTR	11.95	13.13	91.23	49.83	CounTR: Transformer-based Generalised Visual Counting
SemAug-SAFECount	12.74	12.59	89.90	44.95	Semantic Generative Augmentations for Few-Shot Counting
DAVE	8.66	8.91	32.36	28.08	DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting
Omnicount (Open vocabulary, multi-label, without training)	18.63	-	112	-	OmniCount: Multi-label Object Counting with Semantic-Geometric Priors	-
FamNet	22.08	23.75	99.54	69.07	Learning To Count Everything
CACViT	9.13	10.63	48.96	37.95	Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting
SemAug-CounTR	11.32	12.31	77.50	41.65	Semantic Generative Augmentations for Few-Shot Counting
CountGD	5.74	7.1	24.09	26.08	CountGD: Multi-Modal Open-World Counting	-
LaoNet	15.78	17.11	97.15	56.81	Object Counting: You Only Need to Look at One	-
CounTX (uses text descriptions instead of visual exemplars)	15.88	17.10	106.29	65.61	Open-world Text-specified Object Counting
SSD	9.58	9.73	64.13	29.72	Learning Spatial Similarity Distribution for Few-shot Object Counting
SPDCN	13.51	14.59	96.80	49.97	Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic Counting
LOCA	10.79	10.24	56.97	32.56	A Low-Shot Object Counting Network With Iterative Prototype Adaptation
BMNet+	14.62	15.74	91.83	58.53	Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting

0 of 19 row(s) selected.