Papers › Deep Self-Taught Learning for Weakly Supervised Object Localization

Deep Self-Taught Learning for Weakly Supervised Object Localization

18 Apr 2017CVPR 2017 7arXiv:1704.05188archive 2025-07-28

Zequn Jie, Yunchao Wei, Xiaojie Jin, Jiashi Feng, Wei Liu

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.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ObjectObject LocalizationWeakly Supervised Object DetectionWeakly-Supervised Object Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Weakly Supervised Object Detection PASCAL VOC 2007 Deep Self-Taught Learning MAP 43.7 #32 of 41 Archive leaderboard report
Weakly Supervised Object Detection PASCAL VOC 2012 test Deep Self-Taught Learning MAP 38.3 #26 of 32 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections