Self-taught Object Localization with Deep Networks

Abstract

This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i.e., without using any ground-truth bounding boxes for training. The key idea is to analyze the change in the recognition scores when artificially masking out different regions of the image. The masking out of a region that includes the object typically causes a significant drop in recognition score. This idea is embedded into an agglomerative clustering technique that generates self-taught localization hypotheses. Our object localization scheme outperforms existing proposal methods in both precision and recall for small number of subwindow proposals (e.g., on ILSVRC-2012 it produces a relative gain of 23.4% over the state-of-the-art for top-1 hypothesis). Furthermore, our experiments show that the annotations automatically-generated by our method can be used to train object detectors yielding recognition results remarkably close to those obtained by training on manually-annotated bounding boxes.

WACV 2016

References in corpus (4)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Convolutional Feature Masking for Joint Object and Stuff Segmentation
• How good are detection proposals, really?

Cited by in corpus (11)

• Object Detectors Emerge in Deep Scene CNNs
• Learning Deep Features for Discriminative Localization
• Deep Learning Face Attributes in the Wild
• Adversarial Complementary Learning for Weakly Supervised Object Localization
• Webly Supervised Learning of Convolutional Networks
• Unsupervised Category Discovery via Looped Deep Pseudo-Task Optimization Using a Large Scale Radiology Image Database
• Visual Concept Recognition and Localization via Iterative Introspection
• Diverse Sampling for Self-Supervised Learning of Semantic Segmentation
• Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization
• Class Correlation affects Single Object Localization using Pre-trained ConvNets
• Learning Rich Representations For Structured Visual Prediction Tasks