paper-with-me

Papers

Self-taught Object Localization with Deep Networks

2014-09-13 · Loris Bazzani, Alessandro Bergamo, Dragomir Anguelov, Lorenzo Torresani

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.

📄 PDF Abstract BibTeX arXiv:1409.3964

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringObjectObject Localization

Similar Papers 제목 키워드 기반

Deep Self-Taught Learning for Weakly Supervised Object Localization

2017-04-18 · CVPR 2017 7 · Zequn Jie, Yunchao Wei, Xiaojie Jin, Jiashi Feng 외

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 loca…

ObjectObject LocalizationWeakly Supervised Object DetectionWeakly-Supervised Object Localization

Self-Taught Cross-Domain Few-Shot Learning with Weakly Supervised Object Localization and Task-Decomposition

2021-09-03 · Xiyao Liu, Zhong Ji, Yanwei Pang, Zhongfei Zhang

The domain shift between the source and target domain is the main challenge in Cross-Domain Few-Shot Learning (CD-FSL). However, the target domain is absolutely unknown during the training on the source domain, which res…

Cross-Domain Few-Shotcross-domain few-shot learningFew-Shot LearningObject Localization+1

Learning Bound for Parameter Transfer Learning

2016-10-27 · NeurIPS 2016 12 · Wataru Kumagai

We consider a transfer-learning problem by using the parameter transfer approach, where a suitable parameter of feature mapping is learned through one task and applied to another objective task. Then, we introduce the no…

Transfer Learning

Evolving Self-taught Neural Networks: The Baldwin Effect and the Emergence of Intelligence

2019-04-04 · Nam Le

The so-called Baldwin Effect generally says how learning, as a form of ontogenetic adaptation, can influence the process of phylogenetic adaptation, or evolution. This idea has also been taken into computation in which e…

Deep Self-taught Learning for Remote Sensing Image Classification

2017-10-19 · Anika Bettge, Ribana Roscher, Susanne Wenzel

This paper addresses the land cover classification task for remote sensing images by deep self-taught learning. Our self-taught learning approach learns suitable feature representations of the input data using sparse rep…

ClassificationDictionary LearningGeneral Classificationimage-classification+3