SM+: Refined Scale Match for Tiny Person Detection

by   Nan Jiang, et al.

Detecting tiny objects ( e.g., less than 20 x 20 pixels) in large-scale images is an important yet open problem. Modern CNN-based detectors are challenged by the scale mismatch between the dataset for network pre-training and the target dataset for detector training. In this paper, we investigate the scale alignment between pre-training and target datasets, and propose a new refined Scale Match method (termed SM+) for tiny person detection. SM+ improves the scale match from image level to instance level, and effectively promotes the similarity between pre-training and target dataset. Moreover, considering SM+ possibly destroys the image structure, a new probabilistic structure inpainting (PSI) method is proposed for the background processing. Experiments conducted across various detectors show that SM+ noticeably improves the performance on TinyPerson, and outperforms the state-of-the-art detectors with a significant margin.


Efficient Conditional Pre-training for Transfer Learning

Almost all the state-of-the-art neural networks for computer vision task...

Scale Match for Tiny Person Detection

Visual object detection has achieved unprecedented ad-vance with the ris...

Stitcher: Feedback-driven Data Provider for Object Detection

Object detectors commonly vary quality according to scales, where the pe...

BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training

Multiple datasets and open challenges for object detection have been int...

Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos

We introduce an approach for pre-training egocentric video models using ...

PLIP: Language-Image Pre-training for Person Representation Learning

Pre-training has emerged as an effective technique for learning powerful...

BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision

We present a novel bird's-eye-view (BEV) detector with perspective super...

Please sign up or login with your details

Forgot password? Click here to reset