Scale Match for Tiny Person Detection

by   Xuehui Yu, et al.

Visual object detection has achieved unprecedented ad-vance with the rise of deep convolutional neural networks.However, detecting tiny objects (for example tiny per-sons less than 20 pixels) in large-scale images remainsnot well investigated. The extremely small objects raisea grand challenge about feature representation while themassive and complex backgrounds aggregate the risk offalse alarms. In this paper, we introduce a new benchmark,referred to as TinyPerson, opening up a promising directionfor tiny object detection in a long distance and with mas-sive backgrounds. We experimentally find that the scale mis-match between the dataset for network pre-training and thedataset for detector learning could deteriorate the featurerepresentation and the detectors. Accordingly, we proposea simple yet effective Scale Match approach to align theobject scales between the two datasets for favorable tiny-object representation. Experiments show the significantperformance gain of our proposed approach over state-of-the-art detectors, and the challenging aspects of TinyPersonrelated to real-world scenarios. The TinyPerson benchmarkand the code for our approach will be publicly available( evaluation rules of AP have updated in benchmark after this paper accepted, So this paper use old rules. we will keep old rules of AP in benchmark, but we recommand the new and we will use the new in latter research.)


page 1

page 3

page 5


SWA Object Detection

Do you want to improve 1.0 AP for your object detector without any infer...

USB: Universal-Scale Object Detection Benchmark

Benchmarks, such as COCO, play a crucial role in object detection. Howev...

SM+: Refined Scale Match for Tiny Person Detection

Detecting tiny objects ( e.g., less than 20 x 20 pixels) in large-scale ...

Fewer is More: Efficient Object Detection in Large Aerial Images

Current mainstream object detection methods for large aerial images usua...

Empirical Upper Bound, Error Diagnosis and Invariance Analysis of Modern Object Detectors

Object detection remains as one of the most notorious open problems in c...

SRN: Side-output Residual Network for Object Symmetry Detection in the Wild

In this paper, we establish a baseline for object symmetry detection in ...

Logit Normalization for Long-tail Object Detection

Real-world data exhibiting skewed distributions pose a serious challenge...

Please sign up or login with your details

Forgot password? Click here to reset