# Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels

arXiv: https://arxiv.org/abs/2005.08455 · HTML: https://mlsanity.com/paper/2005.08455/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2020.

## Built on by (most cited first, 30 of 35)

- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues](https://mlsanity.com/paper/2402.14762/) (2024)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [A Survey on Long-Tailed Visual Recognition](https://mlsanity.com/paper/2205.13775/) (2022)
- [Detecting Everything in the Open World: Towards Universal Object Detection](https://mlsanity.com/paper/2303.11749/) (2023)
- [On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors](https://mlsanity.com/paper/2103.12474/) (2021)
- [GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models](https://mlsanity.com/paper/2406.14550/) (2024)
- [Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models](https://mlsanity.com/paper/2412.05934/) (2024)
- [SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition](https://mlsanity.com/paper/2401.17857/) (2024)
- [Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Training](https://mlsanity.com/paper/2107.05031/) (2021)
- [Class-Balanced Distillation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2104.05279/) (2021)
- [GAIA: A Transfer Learning System of Object Detection that Fits Your Needs](https://mlsanity.com/paper/2106.11346/) (2021)
- [Balancing Logit Variation for Long-tailed Semantic Segmentation](https://mlsanity.com/paper/2306.02061/) (2023)
- [When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method](https://mlsanity.com/paper/2211.10955/) (2022)
- [Test-time Adaptation with Calibration of Medical Image Classification Nets for Label Distribution Shift](https://mlsanity.com/paper/2207.00769/) (2022)
- [Diaformer: Automatic Diagnosis via Symptoms Sequence Generation](https://mlsanity.com/paper/2112.10433/) (2021)
- [Class-Balanced Active Learning for Image Classification](https://mlsanity.com/paper/2110.04543/) (2021)
- [FindIt: Generalized Localization with Natural Language Queries](https://mlsanity.com/paper/2203.17273/) (2022)
- [Long-tailed Instance Segmentation using Gumbel Optimized Loss](https://mlsanity.com/paper/2207.10936/) (2022)
- [LCReg: Long-Tailed Image Classification with Latent Categories based Recognition](https://mlsanity.com/paper/2309.07186/) (2023)
- [Distilling Long-tailed Datasets](https://mlsanity.com/paper/2408.14506/) (2024)
- [Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentation](https://mlsanity.com/paper/2407.04911/) (2024)
- [MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D Assets](https://mlsanity.com/paper/2404.13923/) (2024)
- [Label Convergence: Defining an Upper Performance Bound in Object Recognition through Contradictory Annotations](https://mlsanity.com/paper/2409.09412/) (2024)
- [Multi-Scenario Combination Based on Multi-Agent Reinforcement Learning to Optimize the Advertising Recommendation System](https://mlsanity.com/paper/2407.02759/) (2024)
- [Class Uncertainty: A Measure to Mitigate Class Imbalance](https://mlsanity.com/paper/2311.14090/) (2023)
- [Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer](https://mlsanity.com/paper/2407.08460/) (2024)
- [Multimodal SuperCon: Classifier for Drivers of Deforestation in Indonesia](https://mlsanity.com/paper/2207.14656/) (2022)
- [HTNav: A Hybrid Navigation Framework with Tiered Structure for Urban Aerial Vision-and-Language Navigation](https://mlsanity.com/paper/2604.08883/) (2026)
- [Soft-labeling Strategies for Rapid Sub-Typing](https://mlsanity.com/paper/2209.12684/) (2022)

## Abstract (arXiv)

Training with more data has always been the most stable and effective way of improving performance in deep learning era. As the largest object detection dataset so far, Open Images brings great opportunities and challenges for object detection in general and sophisticated scenarios. However, owing to its semi-automatic collecting and labeling pipeline to deal with the huge data scale, Open Images dataset suffers from label-related problems that objects may explicitly or implicitly have multiple labels and the label distribution is extremely imbalanced. In this work, we quantitatively analyze these label problems and provide a simple but effective solution. We design a concurrent softmax to handle the multi-label problems in object detection and propose a soft-sampling methods with hybrid training scheduler to deal with the label imbalance. Overall, our method yields a dramatic improvement of 3.34 points, leading to the best single model with 60.90 mAP on the public object detection test set of Open Images. And our ensembling result achieves 67.17 mAP, which is 4.29 points higher than the best result of Open Images public test 2018.