# CS-R-FCN: Cross-supervised Learning for Large-Scale Object Detection

## TL;DR

This paper introduces CS-R-FCN, a novel cross-supervised learning pipeline that leverages both image-level and bounding-box annotations to improve large-scale object detection performance.

## Contribution

It proposes a new cross-supervised learning framework combining different annotation levels and a semantic aggregation strategy to enhance detection accuracy.

## Key findings

- Significant mAP improvement over previous methods
- Effective utilization of image-level annotations in detection
- Reduced mutual inhibition among categories during learning

## Abstract

Generic object detection is one of the most fundamental problems in computer vision, yet it is difficult to provide all the bounding-box-level annotations aiming at large-scale object detection for thousands of categories. In this paper, we present a novel cross-supervised learning pipeline for large-scale object detection, denoted as CS-R-FCN. First, we propose to utilize the data flow of image-level annotated images in the fully-supervised two-stage object detection framework, leading to cross-supervised learning combining bounding-box-level annotated data and image-level annotated data. Second, we introduce a semantic aggregation strategy utilizing the relationships among the cross-supervised categories to reduce the unreasonable mutual inhibition effects during the feature learning. Experimental results show that the proposed CS-R-FCN improves the mAP by a large margin compared to previous related works.