# Self Paced Deep Learning for Weakly Supervised Object Detection

arXiv: https://arxiv.org/abs/1605.07651 · HTML: https://mlsanity.com/paper/1605.07651/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2016.

## Built on by (most cited first, 25 of 25)

- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations](https://mlsanity.com/paper/2303.06242/) (2023)
- [Generalized Binary Search Network for Highly-Efficient Multi-View Stereo](https://mlsanity.com/paper/2112.02338/) (2021)
- [Deep Anomaly Discovery From Unlabeled Videos via Normality Advantage and Self-Paced Refinement](https://mlsanity.com/paper/2108.01975/) (2021)
- [MonoGRNet: A General Framework for Monocular 3D Object Detection](https://mlsanity.com/paper/2104.08797/) (2021)
- [Self-learning for weakly supervised Gleason grading of local patterns](https://mlsanity.com/paper/2105.10420/) (2021)
- [Are we certain it's anomalous?](https://mlsanity.com/paper/2211.09224/) (2022)
- [Intent-based Prompt Calibration: Enhancing prompt optimization with synthetic boundary cases](https://mlsanity.com/paper/2402.03099/) (2024)
- [Self-paced ensemble learning for speech and audio classification](https://mlsanity.com/paper/2103.11988/) (2021)
- [Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation](https://mlsanity.com/paper/2402.17316/) (2024)
- [When Do Curricula Work in Federated Learning?](https://mlsanity.com/paper/2212.12712/) (2022)
- [Curriculum-Based Augmented Fourier Domain Adaptation for Robust Medical Image Segmentation](https://mlsanity.com/paper/2306.03511/) (2023)
- [CLIP: Train Faster with Less Data](https://mlsanity.com/paper/2212.01452/) (2022)
- [Learning 3D Perception from Others' Predictions](https://mlsanity.com/paper/2410.02646/) (2024)
- [Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement](https://mlsanity.com/paper/2106.05554/) (2021)
- [Gyro-based Neural Single Image Deblurring](https://mlsanity.com/paper/2404.00916/) (2024)
- [Accelerating the Training of Video Super-Resolution Models](https://mlsanity.com/paper/2205.05069/) (2022)
- [Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud?](https://mlsanity.com/paper/2403.02818/) (2024)
- [Towards Accurate Localization by Instance Search](https://mlsanity.com/paper/2107.05005/) (2021)
- [Weakly Supervised Visual-Auditory Fixation Prediction with Multigranularity Perception](https://mlsanity.com/paper/2112.13697/) (2021)
- [Curriculum for Crowd Counting -- Is it Worthy?](https://mlsanity.com/paper/2401.07586/) (2024)
- [Does YOLO Really Need to See Every Training Image in Every Epoch?](https://mlsanity.com/paper/2603.17684/) (2026)
- [Credit spread approximation and improvement using random forest regression](https://mlsanity.com/paper/2106.07358/) (2021)
- [ABRA: Teleporting Fine-Tuned Knowledge Across Domains for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2603.12409/) (2026)

## Abstract (arXiv)

In a weakly-supervised scenario object detectors need to be trained using image-level annotation alone. Since bounding-box-level ground truth is not available, most of the solutions proposed so far are based on an iterative, Multiple Instance Learning framework in which the current classifier is used to select the highest-confidence boxes in each image, which are treated as pseudo-ground truth in the next training iteration. However, the errors of an immature classifier can make the process drift, usually introducing many of false positives in the training dataset. To alleviate this problem, we propose in this paper a training protocol based on the self-paced learning paradigm. The main idea is to iteratively select a subset of images and boxes that are the most reliable, and use them for training. While in the past few years similar strategies have been adopted for SVMs and other classifiers, we are the first showing that a self-paced approach can be used with deep-network-based classifiers in an end-to-end training pipeline. The method we propose is built on the fully-supervised Fast-RCNN architecture and can be applied to similar architectures which represent the input image as a bag of boxes. We show state-of-the-art results on Pascal VOC 2007, Pascal VOC 2010 and ILSVRC 2013. On ILSVRC 2013 our results based on a low-capacity AlexNet network outperform even those weakly-supervised approaches which are based on much higher-capacity networks.