Multiple Instance Curriculum Learning for Weakly Supervised Object Detection

11/25/2017
by   Siyang Li, et al.
0

When supervising an object detector with weakly labeled data, most existing approaches are prone to trapping in the discriminative object parts, e.g., finding the face of a cat instead of the full body, due to lacking the supervision on the extent of full objects. To address this challenge, we incorporate object segmentation into the detector training, which guides the model to correctly localize the full objects. We propose the multiple instance curriculum learning (MICL) method, which injects curriculum learning (CL) into the multiple instance learning (MIL) framework. The MICL method starts by automatically picking the easy training examples, where the extent of the segmentation masks agree with detection bounding boxes. The training set is gradually expanded to include harder examples to train strong detectors that handle complex images. The proposed MICL method with segmentation in the loop outperforms the state-of-the-art weakly supervised object detectors by a substantial margin on the PASCAL VOC datasets.

READ FULL TEXT

page 2

page 6

page 8

research
04/11/2019

C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection

Weakly supervised object detection (WSOD) is a challenging task when pro...
research
08/15/2016

Weakly Supervised Object Localization Using Size Estimates

We present a technique for weakly supervised object localization (WSOL),...
research
04/19/2019

Multiple receptive fields and small-object-focusing weakly-supervised segmentation network for fast object detection

Object detection plays an important role in various visual applications....
research
06/14/2019

Utilizing the Instability in Weakly Supervised Object Detection

Weakly supervised object detection (WSOD) focuses on training object det...
research
06/25/2014

Weakly-supervised Discovery of Visual Pattern Configurations

The increasing prominence of weakly labeled data nurtures a growing dema...
research
09/11/2016

Learning Semantic Part-Based Models from Google Images

We propose a technique to train semantic part-based models of object cla...
research
07/13/2018

TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection

This work provides a simple approach to discover tight object bounding b...

Please sign up or login with your details

Forgot password? Click here to reset