Stitcher: Feedback-driven Data Provider for Object Detection

by   Yukang Chen, et al.

Object detectors commonly vary quality according to scales, where the performance on small objects is the least satisfying. In this paper, we investigate this phenomenon and discover that: in the majority of training iterations, small objects contribute barely to the total loss, causing poor performance with imbalanced optimization. Inspired by this finding, we present Stitcher, a feedback-driven data provider, which aims to train object detectors in a balanced way. In Stitcher, images are resized into smaller components and then stitched into the same size to regular images. Stitched images contain inevitable smaller objects, which would be beneficial with our core idea, to exploit the loss statistics as feedback to guide next-iteration update. Experiments have been conducted on various detectors, backbones, training periods, datasets, and even on instance segmentation. Stitcher steadily improves performance by a large margin in all settings, especially for small objects, with nearly no additional computation in both training and testing stages.


page 3

page 4

page 5


Synthesizing Training Data for Object Detection in Indoor Scenes

Detection of objects in cluttered indoor environments is one of the key ...

SM+: Refined Scale Match for Tiny Person Detection

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

A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

Object frequencies in daily scenes follow a long-tailed distribution. Ma...

Self-supervisory Signals for Object Discovery and Detection

In robotic applications, we often face the challenge of discovering new ...

Inverting and Understanding Object Detectors

As a core problem in computer vision, the performance of object detectio...

Classification Calibration for Long-tail Instance Segmentation

Remarkable progress has been made in object instance detection and segme...

Enhanced Training of Query-Based Object Detection via Selective Query Recollection

This paper investigates a phenomenon where query-based object detectors ...

Please sign up or login with your details

Forgot password? Click here to reset