DeepAI AI Chat
Log In Sign Up

OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation

by   Alexandre Ramé, et al.

Object detectors tend to perform poorly in new or open domains, and require exhaustive yet costly annotations from fully labeled datasets. We aim at benefiting from several datasets with different categories but without additional labelling, not only to increase the number of categories detected, but also to take advantage from transfer learning and to enhance domain independence. Our dataset merging procedure starts with training several initial Faster R-CNN on the different datasets while considering the complementary datasets' images for domain adaptation. Similarly to self-training methods, the predictions of these initial detectors mitigate the missing annotations on the complementary datasets. The final OMNIA Faster R-CNN is trained with all categories on the union of the datasets enriched by predictions. The joint training handles unsafe targets with a new classification loss called SoftSig in a softly supervised way. Experimental results show that in the case of fashion detection for images in the wild, merging Modanet with COCO increases the final performance from 45.5 to 57.4 shift on Cityscapes enables to beat the state-of-the-art by 5.3 points. We hope that our methodology could unlock object detection for real-world applications without immense datasets.


page 1

page 4

page 6


Cross-Supervised Object Detection

After learning a new object category from image-level annotations (with ...

Cross-Ssupervised Object Detection

After learning a new object category from image-level annotations (with ...

Mixed Supervised Object Detection with Robust Objectness Transfer

In this paper, we consider the problem of leveraging existing fully labe...

SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation

In autonomous driving, a LiDAR-based object detector should perform reli...

Object Detection with a Unified Label Space from Multiple Datasets

Given multiple datasets with different label spaces, the goal of this wo...

Background Adaptive Faster R-CNN for Semi-Supervised Convolutional Object Detection of Threats in X-Ray Images

Recently, progress has been made in the supervised training of Convoluti...

Analysing object detectors from the perspective of co-occurring object categories

The accuracy of state-of-the-art Faster R-CNN and YOLO object detectors ...

Code Repositories



view repo