Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection

01/09/2018
by   Yuxing Tang, et al.
0

Deep CNN-based object detection systems have achieved remarkable success on several large-scale object detection benchmarks. However, training such detectors requires a large number of labeled bounding boxes, which are more difficult to obtain than image-level annotations. Previous work addresses this issue by transforming image-level classifiers into object detectors. This is done by modeling the differences between the two on categories with both image-level and bounding box annotations, and transferring this information to convert classifiers to detectors for categories without bounding box annotations. We improve this previous work by incorporating knowledge about object similarities from visual and semantic domains during the transfer process. The intuition behind our proposed method is that visually and semantically similar categories should exhibit more common transferable properties than dissimilar categories, e.g. a better detector would result by transforming the differences between a dog classifier and a dog detector onto the cat class, than would by transforming from the violin class. Experimental results on the challenging ILSVRC2013 detection dataset demonstrate that each of our proposed object similarity based knowledge transfer methods outperforms the baseline methods. We found strong evidence that visual similarity and semantic relatedness are complementary for the task, and when combined notably improve detection, achieving state-of-the-art detection performance in a semi-supervised setting.

READ FULL TEXT

page 2

page 3

page 6

page 9

page 10

page 12

page 14

research
05/30/2019

Hierarchical Structure and Joint Training for Large Scale Semi-supervised Object Detection

Generic object detection is one of the most fundamental and important pr...
research
04/03/2018

Transferring Common-Sense Knowledge for Object Detection

We propose the idea of transferring common-sense knowledge from source c...
research
07/18/2014

LSDA: Large Scale Detection Through Adaptation

A major challenge in scaling object detection is the difficulty of obtai...
research
01/17/2021

Improving Apparel Detection with Category Grouping and Multi-grained Branches

Training an accurate object detector is expensive and time-consuming. On...
research
12/01/2018

NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection

The labeling cost of large number of bounding boxes is one of the main c...
research
10/20/2021

Noisy Annotation Refinement for Object Detection

Supervised training of object detectors requires well-annotated large-sc...
research
10/10/2015

Spatial Semantic Regularisation for Large Scale Object Detection

Large scale object detection with thousands of classes introduces the pr...

Please sign up or login with your details

Forgot password? Click here to reset