FSC147

Overview edit

Variants: FSC147

Associated Benchmarks

This dataset is used in 1 benchmark:

• Object Counting - Metrics: MAE(test), MAE(val), RMSE(test), RMSE(val)

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation (2024) -
• GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting (2024) -
• CountGD: Multi-Modal Open-World Counting (2024) -
• Learning Spatial Similarity Distribution for Few-shot Object Counting (2024) -
• DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting (2024) -
• OmniCount: Multi-label Object Counting with Semantic-Geometric Priors (2024) -
• Semantic Generative Augmentations for Few-Shot Counting (2023) -
• Open-world Text-specified Object Counting (2023) -
• Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting (2023) -
• A Low-Shot Object Counting Network With Iterative Prototype Adaptation (2022) -
• CounTR: Transformer-based Generalised Visual Counting (2022) -
• Few-shot Object Counting and Detection (2022) -
• Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision (2022) -
• Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting (2022) -
• Few-shot Object Counting with Similarity-Aware Feature Enhancement (2022) -
• Object Counting: You Only Need to Look at One (2021) -
• Learning To Count Everything (2021) -