TFCounter:Polishing Gems for Training-Free Object Counting

arXiv:2405.02301v1 Announce Type: new
Abstract: 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 …

abstract annotation application arxiv challenge class context costs counter cs.cv diagnosis disease disease diagnosis face free management novel object performance prompt prospects security surveillance traffic traffic management training type via