# Deep Self-Taught Learning for Weakly Supervised Object Localization

arXiv: https://arxiv.org/abs/1704.05188 · HTML: https://mlsanity.com/paper/1704.05188/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2017.

## Built on by (most cited first, 27 of 27)

- [Localizing Objects with Self-Supervised Transformers and no Labels](https://mlsanity.com/paper/2109.14279/) (2021)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Adaptive Early-Learning Correction for Segmentation from Noisy Annotations](https://mlsanity.com/paper/2110.03740/) (2021)
- [Points as Queries: Weakly Semi-supervised Object Detection by Points](https://mlsanity.com/paper/2104.07434/) (2021)
- [ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues](https://mlsanity.com/paper/2201.06696/) (2022)
- [A Survey of Self-Supervised and Few-Shot Object Detection](https://mlsanity.com/paper/2110.14711/) (2021)
- [Self-supervised object detection from audio-visual correspondence](https://mlsanity.com/paper/2104.06401/) (2021)
- [Omni-DETR: Omni-Supervised Object Detection with Transformers](https://mlsanity.com/paper/2203.16089/) (2022)
- [Group R-CNN for Weakly Semi-supervised Object Detection with Points](https://mlsanity.com/paper/2205.05920/) (2022)
- [What Can Human Sketches Do for Object Detection?](https://mlsanity.com/paper/2303.15149/) (2023)
- [Active Learning Strategies for Weakly-supervised Object Detection](https://mlsanity.com/paper/2207.12112/) (2022)
- [Self-learning for weakly supervised Gleason grading of local patterns](https://mlsanity.com/paper/2105.10420/) (2021)
- [WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition](https://mlsanity.com/paper/2402.14812/) (2024)
- [Scaling Novel Object Detection with Weakly Supervised Detection Transformers](https://mlsanity.com/paper/2207.05205/) (2022)
- [Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey](https://mlsanity.com/paper/2105.12694/) (2021)
- [Weakly Supervised Keypoint Discovery](https://mlsanity.com/paper/2109.13423/) (2021)
- [Weakly-Supervised 3D Scene Graph Generation via Visual-Linguistic Assisted Pseudo-labeling](https://mlsanity.com/paper/2404.02527/) (2024)
- [Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection](https://mlsanity.com/paper/2308.05991/) (2023)
- [Weakly Supervised Volumetric Segmentation via Self-taught Shape Denoising Model](https://mlsanity.com/paper/2104.13082/) (2021)
- [Self-Supervised Object Detection via Generative Image Synthesis](https://mlsanity.com/paper/2110.09848/) (2021)
- [Graph Convolution Neural Network For Weakly Supervised Abnormality Localization In Long Capsule Endoscopy Videos](https://mlsanity.com/paper/2110.09110/) (2021)
- [Learning a Weight Map for Weakly-Supervised Localization](https://mlsanity.com/paper/2111.14131/) (2021)
- [Few-shot Visual Relationship Co-localization](https://mlsanity.com/paper/2108.11618/) (2021)
- [Discovery-and-Selection: Towards Optimal Multiple Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/2110.09060/) (2021)
- [MuRAL: Multi-Scale Region-based Active Learning for Object Detection](https://mlsanity.com/paper/2303.16637/) (2023)
- [HUWSOD: Holistic Self-training for Unified Weakly Supervised Object Detection](https://mlsanity.com/paper/2406.19394/) (2024)
- [Self-supervised cross-modality learning for uncertainty-aware object detection and recognition in applications which lack pre-labelled training data](https://mlsanity.com/paper/2411.03082/) (2024)

## Abstract (arXiv)

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.