mlsanityData to 14 Oct 2026

GOOD: Exploring Geometric Cues for Detecting Objects in an Open World

arXiv 2212.11720 ↗First posted 22 Dec 2022cs.CV cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

We address the task of open-world class-agnostic object detection, i.e., detecting every object in an image by learning from a limited number of base object classes. State-of-the-art RGB-based models suffer from overfitting the training classes and often fail at detecting novel-looking objects. This is because RGB-based models primarily rely on appearance similarity to detect novel objects and are also prone to overfitting short-cut cues such as textures and discriminative parts. To address these shortcomings of RGB-based object detectors, we propose incorporating geometric cues such as depth and normals, predicted by general-purpose monocular estimators. Specifically, we use the geometric cues to train an object proposal network for pseudo-labeling unannotated novel objects in the training set. Our resulting Geometry-guided Open-world Object Detector (GOOD) significantly improves detection recall for novel object categories and already performs well with only a few training classes. Using a single "person" class for training on the COCO dataset, GOOD surpasses SOTA methods by 5.0% AR@100, a relative improvement of 24%.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 32 of its 48 references that are in the map. First posted on arXiv 22 Dec 2022.

Builds on

32 of 48 references.

References · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  5. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  6. 2021Vision Transformers for Dense Predictioncited by 1,803
  7. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  8. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  9. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  10. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  11. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  12. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
20 more
  1. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  2. 2015Holistically-Nested Edge Detectioncited by 592
  3. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  4. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  5. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  6. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 316
  7. 2022Simple Open-Vocabulary Object Detection with Vision Transformerscited by 305
  8. 2021Towards Open World Object Detectioncited by 297
  9. 20223D Common Corruptions and Data Augmentationcited by 119
  10. 2021Counterfactual Generative Networkscited by 111
  11. 2021Learning Open-World Object Proposals without Learning to Classifycited by 109
  12. 2020Robust Learning Through Cross-Task Consistencycited by 105
  13. 2021Class-agnostic Object Detection with Multi-modal Transformercited by 85
  14. 2021Opening up Open-World Trackingcited by 50
  15. 2022Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinitycited by 41
  16. 2021Learning to Detect Every Thing in an Open Worldcited by 37
  17. 2020Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigationcited by 32
  18. 2020Class-agnostic Object Detectioncited by 17
  19. 2022Extending One-Stage Detection with Open-World Proposalscited by 9
  20. 2021Self-Initiated Open World Learning for Autonomous AI Agentscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 3; 2025: 1; 2026: 1.

10 papers.

  1. 2023AG3D: Learning to Generate 3D Avatars from 2D Image Collectionscited by 55
  2. 2023Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Reviewcited by 25
  3. 2024Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectivescited by 23
  4. 2023Exploring Transformers for Open-world Instance Segmentationcited by 5
  5. 2023Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depthcited by 4
  6. 2023OpenInst: A Simple Query-Based Method for Open-World Instance Segmentationcited by 4
  7. 2024O1O: Grouping of Known Classes to Identify Unknown Objects as Odd-One-Outcited by 1
  8. 2025v-CLR: View-Consistent Learning for Open-World Instance Segmentationcited by 1
  9. 2024Multimodal-Enhanced Objectness Learner for Corner Case Detection in Autonomous Drivingcited by 0
  10. 2026Background-Free Objectness Learning for Class-Agnostic Detectioncited by 0