Deep Self-Taught Learning for Weakly Supervised Object Localization

04/18/2017
by   Zequn Jie, et al.
0

Most existing weakly supervised localization (WSL) approaches learn detectors by finding positive bounding boxes based on features learned with image-level supervision. However, those features do not contain spatial location related information and usually provide poor-quality positive samples for training a detector. To overcome this issue, we propose a deep self-taught learning approach, which makes the detector learn the object-level features reliable for acquiring tight positive samples and afterwards re-train itself based on them. Consequently, the detector progressively improves its detection ability and localizes more informative positive samples. To implement such self-taught learning, we propose a seed sample acquisition method via image-to-object transferring and dense subgraph discovery to find reliable positive samples for initializing the detector. An online supportive sample harvesting scheme is further proposed to dynamically select the most confident tight positive samples and train the detector in a mutual boosting way. To prevent the detector from being trapped in poor optima due to overfitting, we propose a new relative improvement of predicted CNN scores for guiding the self-taught learning process. Extensive experiments on PASCAL 2007 and 2012 show that our approach outperforms the state-of-the-arts, strongly validating its effectiveness.

READ FULL TEXT

page 1

page 3

page 4

page 8

research
04/25/2018

Zigzag Learning for Weakly Supervised Object Detection

This paper addresses weakly supervised object detection with only image-...
research
05/29/2017

Ensemble of Part Detectors for Simultaneous Classification and Localization

Part-based representation has been proven to be effective for a variety ...
research
06/14/2019

Utilizing the Instability in Weakly Supervised Object Detection

Weakly supervised object detection (WSOD) focuses on training object det...
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...
research
04/01/2021

Two-phase weakly supervised object detection with pseudo ground truth mining

Weakly Supervised Object Detection (WSOD), aiming to train detectors wit...
research
11/22/2016

Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model

In this paper, a self-learning approach is proposed towards solving scen...
research
11/12/2016

Online Generative-Discriminative Model for Object Detection in Video: An Unsupervised Learning Framework

Traditional single-view object detection methods often perform worse und...

Please sign up or login with your details

Forgot password? Click here to reset