# Unsupervised Hard Example Mining from Videos for Improved Object Detection

arXiv: https://arxiv.org/abs/1808.04285 · HTML: https://mlsanity.com/paper/1808.04285/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2018.

## Built on by (most cited first, 30 of 30)

- [Contrastive Learning for Neural Topic Model](https://mlsanity.com/paper/2110.12764/) (2021)
- [Robust Contrastive Learning Using Negative Samples with Diminished Semantics](https://mlsanity.com/paper/2110.14189/) (2021)
- [Geometric Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16694/) (2021)
- [Instance-specific and Model-adaptive Supervision for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2211.11335/) (2022)
- [Exploring the Coordination of Frequency and Attention in Masked Image Modeling](https://mlsanity.com/paper/2211.15362/) (2022)
- [Semi-supervised 3D Object Detection via Temporal Graph Neural Networks](https://mlsanity.com/paper/2202.00182/) (2022)
- [Learning to Better Segment Objects from Unseen Classes with Unlabeled Videos](https://mlsanity.com/paper/2104.12276/) (2021)
- [Semi-Automatic Annotation For Visual Object Tracking](https://mlsanity.com/paper/2101.06977/) (2021)
- [Effective Pseudo-Labeling based on Heatmap for Unsupervised Domain Adaptation in Cell Detection](https://mlsanity.com/paper/2303.05269/) (2023)
- [GaitMPL: Gait Recognition with Memory-Augmented Progressive Learning](https://mlsanity.com/paper/2306.04650/) (2023)
- [Multi-Object Tracking with Hallucinated and Unlabeled Videos](https://mlsanity.com/paper/2108.08836/) (2021)
- [Investigating the Zone of Proximal Development of Language Models for In-Context Learning](https://mlsanity.com/paper/2502.06990/) (2025)
- [Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning](https://mlsanity.com/paper/2309.03598/) (2023)
- [Globally Correlation-Aware Hard Negative Generation](https://mlsanity.com/paper/2411.13145/) (2024)
- [Active learning using weakly supervised signals for quality inspection](https://mlsanity.com/paper/2104.02973/) (2021)
- [Hard Negative Sampling via Regularized Optimal Transport for Contrastive Representation Learning](https://mlsanity.com/paper/2111.03169/) (2021)
- [An Artificial Intelligence Dataset for Solar Energy Locations in India](https://mlsanity.com/paper/2202.01340/) (2022)
- [Improved Hard Example Mining Approach for Single Shot Object Detectors](https://mlsanity.com/paper/2202.13080/) (2022)
- [RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation](https://mlsanity.com/paper/2504.17502/) (2025)
- [Cell Detection in Domain Shift Problem Using Pseudo-Cell-Position Heatmap](https://mlsanity.com/paper/2107.08653/) (2021)
- [Self-supervised Video Representation Learning with Cascade Positive Retrieval](https://mlsanity.com/paper/2201.07989/) (2022)
- [Global Renewables Watch: A Temporal Dataset of Solar and Wind Energy Derived from Satellite Imagery](https://mlsanity.com/paper/2503.14860/) (2025)
- [Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining](https://mlsanity.com/paper/2505.06557/) (2025)
- [DrasCLR: A Self-supervised Framework of Learning Disease-related and Anatomy-specific Representation for 3D Medical Images](https://mlsanity.com/paper/2302.10390/) (2023)
- [Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions](https://mlsanity.com/paper/2508.08352/) (2025)
- [Holistic Fine-grained GGS Characterization: From Detection to Unbalanced Classification](https://mlsanity.com/paper/2202.00087/) (2022)
- [N-RPN: Hard Example Learning for Region Proposal Networks](https://mlsanity.com/paper/2208.01916/) (2022)
- [Perceive, Excavate and Purify: A Novel Object Mining Framework for Instance Segmentation](https://mlsanity.com/paper/2304.08826/) (2023)
- [Conditional Online Learning for Keyword Spotting](https://mlsanity.com/paper/2305.13332/) (2023)
- [Distractor-Aware Video Object Segmentation](https://mlsanity.com/paper/2608.11835/) (2026)

## Abstract (arXiv)

Important gains have recently been obtained in object detection by using training objectives that focus on em hard negative examples, i.e., negative examples that are currently rated as positive or ambiguous by the detector. These examples can strongly influence parameters when the network is trained to correct them. Unfortunately, they are often sparse in the training data, and are expensive to obtain. In this work, we show how large numbers of hard negatives can be obtained em automatically by analyzing the output of a trained detector on video sequences. In particular, detections that are em isolated in time, i.e., that have no associated preceding or following detections, are likely to be hard negatives. We describe simple procedures for mining large numbers of such hard negatives (and also hard em positives) from unlabeled video data. Our experiments show that retraining detectors on these automatically obtained examples often significantly improves performance. We present experiments on multiple architectures and multiple data sets, including face detection, pedestrian detection and other object categories.