HyperAI

Object Counting On Fsc147

Metrics

MAE(test)
MAE(val)
RMSE(test)
RMSE(val)

Results

Performance results of various models on this benchmark

Model Name
MAE(test)
MAE(val)
RMSE(test)
RMSE(val)
Paper TitleRepository
GeCo7.919.5254.2843.00A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
RCC17.1217.49104.5358.81Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision
SAFECount14.3215.2885.5447.20Few-shot Object Counting with Similarity-Aware Feature Enhancement
Counting-DETR16.79-123.56-Few-shot Object Counting and Detection
GCA-SUN14.0016.0692.1953.04GCA-SUN: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting-
CounTR11.9513.1391.2349.83CounTR: Transformer-based Generalised Visual Counting
SemAug-SAFECount12.7412.5989.9044.95Semantic Generative Augmentations for Few-Shot Counting
DAVE8.668.9132.3628.08DAVE -- 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-
FamNet22.0823.7599.5469.07Learning To Count Everything
CACViT9.1310.6348.9637.95Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting
SemAug-CounTR11.3212.3177.5041.65Semantic Generative Augmentations for Few-Shot Counting
CountGD5.747.124.0926.08CountGD: Multi-Modal Open-World Counting-
LaoNet15.7817.1197.1556.81Object Counting: You Only Need to Look at One-
CounTX (uses text descriptions instead of visual exemplars)15.8817.10106.2965.61Open-world Text-specified Object Counting
SSD9.589.7364.1329.72Learning Spatial Similarity Distribution for Few-shot Object Counting
SPDCN13.5114.5996.8049.97Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic Counting
LOCA10.7910.2456.9732.56A Low-Shot Object Counting Network With Iterative Prototype Adaptation
BMNet+14.6215.7491.8358.53Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting
0 of 19 row(s) selected.