TFCounter:Polishing Gems for Training-Free Object Counting
Object counting is a challenging task with broad application prospects in security surveillance, traffic management, and disease diagnosis. Existing object counting methods face a tri-fold challenge: achieving superior performance, maintaining high generalizability, and minimizing annotation costs. We develop a novel training-free class-agnostic object counter, TFCounter, which is prompt-context-aware via the cascade of the essential elements in large-scale foundation models. This approach employs an iterative counting framework with a dual prompt system to recognize a broader spectrum of objects varying in shape, appearance, and size. Besides, it introduces an innovative context-aware similarity module incorporating background context to enhance accuracy within messy scenes. To demonstrate cross-domain generalizability, we collect a novel counting dataset named BIKE-1000, including exclusive 1000 images of shared bicycles from Meituan. Extensive experiments on FSC-147, CARPK, and BIKE-1000 datasets demonstrate that TFCounter outperforms existing leading training-free methods and exhibits competitive results compared to trained counterparts.
Code (0)
등록된 구현이 없습니다.
Tasks
ManagementObjectObject CountingTraining-free Object CountingSimilar Papers 제목 키워드 기반
Generative Evolutionary Meta-Solver (GEMS): Scalable Surrogate-Free Multi-Agent Reinforcement Learning
Scalable multi-agent reinforcement learning (MARL) remains a central challenge for AI. Existing population-based methods, like Policy-Space Response Oracles, PSRO, require storing explicit policy populations and construc…
Multi-agent Reinforcement LearningGEMSS: A Variational Bayesian Method for Discovering Multiple Sparse Solutions in Classification and Regression Problems
High-dimensional, underdetermined and highly correlated systems are common in data science practice, especially when analyzing physical measurements. In such settings, feature selection poses a fundamental challenge beca…
Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised Object Detection
Exploiting pseudo labels (e.g., categories and bounding boxes) of unannotated objects produced by a teacher detector have underpinned much of recent progress in semi-supervised object detection (SSOD). However, due to th…
object-detectionObject DetectionPseudo LabelSemi-Supervised Object DetectionIntegrating splice-isoform expression into genome-scale models characterizes breast cancer metabolism
Motivation: Despite being often perceived as the main contributors to cell fate and physiology, genes alone cannot predict cellular phenotype. During the process of gene expression, 95% of human genes can code for multip…
Progressive Feature Polishing Network for Salient Object Detection
Feature matters for salient object detection. Existing methods mainly focus on designing a sophisticated structure to incorporate multi-level features and filter out cluttered features. We present Progressive Feature Pol…
Objectobject-detectionObject DetectionRGB Salient Object Detection+1