Freaks City

Detection Pipeline Overview Anchor-driven detection frameworks operate through a standardized sequence. First, a dense grid of reference regions is synthesized across the input tensor. Second, a classifier evaluates each reference region for target presence. Third, a regressor adjusts the coordinates of positive regions to align with ground-tru ...

Object detection models frequantly generate multiple bounding boxes for a single object. To isolate the most accurate localization, a post-processing step is required to filter redundant proposals. Non-Maximum Suppression (NMS) is the standard technique employed to select the optimal box while suppressing overlapping candidates. Core Algorithm ...

In object detection, accurately determining how well a predicted bounding box aligns with the ground truth is essential. This alignment is quantified using the Intersection over Union (IoU), a metric derived from set theory. IoU measures the overlap between two regions by dividing the area of their intersection by the area of their union: $$ \t ...

Introduction to MMDetection MMDetection is an open-source object detection toolbox developed by SenseTime and The Chinese University of Hong Kong. Built on PyTorch, it implements a wide array of object detection algorithms, encapsulating dataset construction, model architecture, and training strategies into modular components. This modular desi ...