mlsanityData to 14 Oct 2026

GAIA: A Transfer Learning System of Object Detection that Fits Your Needs

arXiv 2106.11346 ↗First posted 21 Jun 2021cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Transfer learning with pre-training on large-scale datasets has played an increasingly significant role in computer vision and natural language processing recently. However, as there exist numerous application scenarios that have distinctive demands such as certain latency constraints and specialized data distributions, it is prohibitively expensive to take advantage of large-scale pre-training for per-task requirements. In this paper, we focus on the area of object detection and present a transfer learning system named GAIA, which could automatically and efficiently give birth to customized solutions according to heterogeneous downstream needs. GAIA is capable of providing powerful pre-trained weights, selecting models that conform to downstream demands such as latency constraints and specified data domains, and collecting relevant data for practitioners who have very few datapoints for their tasks. With GAIA, we achieve promising results on COCO, Objects365, Open Images, Caltech, CityPersons, and UODB which is a collection of datasets including KITTI, VOC, WiderFace, DOTA, Clipart, Comic, and more. Taking COCO as an example, GAIA is able to efficiently produce models covering a wide range of latency from 16ms to 53ms, and yields AP from 38.2 to 46.5 without whistles and bells. To benefit every practitioner in the community of object detection, GAIA is released at https://github.com/GAIA-vision.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 55 of its 70 references that are in the map. First posted on arXiv 21 Jun 2021.

Builds on

55 of 70 references.

References · 55

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  7. 2017Mask R-CNNcited by 7,277
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  10. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  11. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  12. 2015Fast R-CNNcited by 2,933
38 more
  1. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  2. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  3. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  4. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  5. 2017Deformable Convolutional Networkscited by 1,488
  6. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  7. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  8. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  9. 2016Deep Networks with Stochastic Depthcited by 979
  10. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
  11. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
  12. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  13. 2019Big Transfer (BiT): General Visual Representation Learningcited by 769
  14. 2017Focal Loss for Dense Object Detectioncited by 752
  15. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  16. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 623
  17. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 605
  18. 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 544
  19. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 443
  20. 2018Rethinking ImageNet Pre-trainingcited by 377
  21. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  22. 2015WIDER FACE: A Face Detection Benchmarkcited by 298
  23. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 291
  24. 2016Designing Neural Network Architectures using Reinforcement Learningcited by 279
  25. 2019Libra R-CNN: Towards Balanced Learning for Object Detectioncited by 255
  26. 2019Billion-scale semi-supervised learning for image classificationcited by 232
  27. 2019Universally Slimmable Networks and Improved Training Techniquescited by 221
  28. 2018Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptationcited by 218
  29. 2020BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Modelscited by 188
  30. 2018Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learningcited by 174
  31. 2017CityPersons: A Diverse Dataset for Pedestrian Detectioncited by 172
  32. 2020Unsupervised Domain Clusters in Pretrained Language Modelscited by 160
  33. 2017Receptive Field Block Net for Accurate and Fast Object Detectioncited by 141
  34. 2019Towards Universal Object Detection by Domain Attentioncited by 89
  35. 2019DetNAS: Backbone Search for Object Detectioncited by 81
  36. 2020Object Detection with a Unified Label Space from Multiple Datasetscited by 65
  37. 2017Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-scale Lesion Databasecited by 42
  38. 2020Large-Scale Object Detection in the Wild from Imbalanced Multi-Labelscited by 35

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 4; 2023: 7; 2024: 11; 2025: 1; 2026: 2.

27 papers.

Sort:

By area:

  1. 2024MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialoguescited by 250
  2. 2024GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Modelscited by 43
  3. 2024Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Modelscited by 33
  4. 2024SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decompositioncited by 30
  5. 2022Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical Worldcited by 22
  6. 2023Diffusion-Based Hierarchical Multi-Label Object Detection to Analyze Panoramic Dental X-rayscited by 18
  7. 2021HyperSegNAS: Bridging One-Shot Neural Architecture Search with 3D Medical Image Segmentation using HyperNetcited by 14
  8. 2021A Curriculum-style Self-training Approach for Source-Free Semantic Segmentationcited by 11
  9. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  10. 2024Online Learning of Multiple Tasks and Their Relationships : Testing on Spam Email Data and EEG Signals Recorded in Construction Fieldscited by 8
  11. 2025Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansioncited by 8
  12. 2022DATA: Domain-Aware and Task-Aware Self-supervised Learningcited by 5
15 more
  1. 2022Universal Object Detection with Large Vision Modelcited by 5
  2. 2023DetOFA: Efficient Training of Once-for-All Networks for Object Detection Using Path Filtercited by 5
  3. 2023Simple Transferability Estimation for Regression Taskscited by 5
  4. 2024Multi-Scenario Combination Based on Multi-Agent Reinforcement Learning to Optimize the Advertising Recommendation Systemcited by 5
  5. 2023StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptationcited by 4
  6. 2023Decomposition Ascribed Synergistic Learning for Unified Image Restorationcited by 3
  7. 2026HTNav: A Hybrid Navigation Framework with Tiered Structure for Urban Aerial Vision-and-Language Navigationcited by 2
  8. 2022GPPF: A General Perception Pre-training Framework via Sparsely Activated Multi-Task Learningcited by 1
  9. 2024CST: Calibration Side-Tuning for Parameter and Memory Efficient Transfer Learningcited by 1
  10. 2024Feature Corrective Transfer Learning: End-to-End Solutions to Object Detection in Non-Ideal Visual Conditionscited by 1
  11. 2024Real-Time Summarization of Twittercited by 1
  12. 2023Adaptability of Computer Vision at the Tactical Edge: Addressing Environmental Uncertaintycited by 0
  13. 2024Analyzing Multi-Head Attention on Trojan BERT Modelscited by 0
  14. 2024Twin Trigger Generative Networks for Backdoor Attacks against Object Detectioncited by 0
  15. 2026A Self-Supervised Approach for Enhanced Feature Representations in Object Detection Taskscited by 0