WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection

09/11/2019
by   Zhaoyang Zeng, et al.
0

We study on weakly-supervised object detection (WSOD) which plays a vital role in relieving human involvement from object-level annotations. Predominant works integrate region proposal mechanisms with convolutional neural networks (CNN). Although CNN is proficient in extracting discriminative local features, grand challenges still exist to measure the likelihood of a bounding box containing a complete object (i.e., "objectness"). In this paper, we propose a novel WSOD framework with Objectness Distillation (i.e., WSOD^2) by designing a tailored training mechanism for weakly-supervised object detection. Multiple regression targets are specifically determined by jointly considering bottom-up (BU) and top-down (TD) objectness from low-level measurement and CNN confidences with an adaptive linear combination. As bounding box regression can facilitate a region proposal learning to approach its regression target with high objectness during training, deep objectness representation learned from bottom-up evidences can be gradually distilled into CNN by optimization. We explore different adaptive training curves for BU/TD objectness, and show that the proposed WSOD^2 can achieve state-of-the-art results.

READ FULL TEXT

page 1

page 3

page 8

research
11/26/2019

WSOD with PSNet and Box Regression

Weakly supervised object detection(WSOD) task uses only image-level anno...
research
11/14/2017

Interpretable R-CNN

This paper presents a method of learning qualitatively interpretable mod...
research
05/22/2020

KL-Divergence-Based Region Proposal Network for Object Detection

The learning of the region proposal in object detection using the deep n...
research
06/25/2015

AttentionNet: Aggregating Weak Directions for Accurate Object Detection

We present a novel detection method using a deep convolutional neural ne...
research
06/23/2020

SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection

Based on the framework of multiple instance learning (MIL), tremendous w...
research
01/26/2018

Weakly Supervised Object Detection with Pointwise Mutual Information

In this work a novel approach for weakly supervised object detection tha...
research
04/14/2022

Spatial Likelihood Voting with Self-Knowledge Distillation for Weakly Supervised Object Detection

Weakly supervised object detection (WSOD), which is an effective way to ...

Please sign up or login with your details

Forgot password? Click here to reset