Data to 7 Oct 2026

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

arXiv 1503.01640 ↗First posted 5 Mar 2015cs.CVcited by 238

Not on the map. Why?

Abstract (arXiv)

Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate supervision demands expensive labeling effort and limits the performance of deep networks that usually benefit from more training data. In this paper, we propose a method that achieves competitive accuracy but only requires easily obtained bounding box annotations. The basic idea is to iterate between automatically generating region proposals and training convolutional networks. These two steps gradually recover segmentation masks for improving the networks, and vise versa. Our method, called BoxSup, produces competitive results supervised by boxes only, on par with strong baselines fully supervised by masks under the same setting. By leveraging a large amount of bounding boxes, BoxSup further unleashes the power of deep convolutional networks and yields state-of-the-art results on PASCAL VOC 2012 and PASCAL-CONTEXT.

Key facts. Cited by 238 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Mar 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 70; 2022: 61; 2023: 47; 2024: 36; 2025: 15; 2026: 8.

238 papers.

Sort:

By area:

2021A Survey on Deep Semi-supervised Learningcited by 250
2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 163
2022CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentationcited by 118
2022ReCo: Retrieve and Co-segment for Zero-shot Transfercited by 115
2021Semi-supervised Semantic Segmentation with Directional Context-aware Consistencycited by 112
2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 104
2021Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentationcited by 101
2021Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentationcited by 95
2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
2021Complementary Patch for Weakly Supervised Semantic Segmentationcited by 75
2022Class Re-Activation Maps for Weakly-Supervised Semantic Segmentationcited by 75

38 more

2022Cross Language Image Matching for Weakly Supervised Semantic Segmentationcited by 72
2021Context Decoupling Augmentation for Weakly Supervised Semantic Segmentationcited by 69
2022Scribble-Supervised LiDAR Semantic Segmentationcited by 69
2022Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentationcited by 64
2021Adaptive Early-Learning Correction for Segmentation from Noisy Annotationscited by 61
2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
2022L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentationcited by 57
2022Discovering Object Masks with Transformers for Unsupervised Semantic Segmentationcited by 54
2022Unsupervised Semantic Segmentation with Self-supervised Object-centric Representationscited by 54
2021Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentationcited by 53
2021Pseudo-mask Matters in Weakly-supervised Semantic Segmentationcited by 48
2021Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentationcited by 47
2022A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Predictioncited by 46
2021Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learningcited by 43
2021Multi-Layer Pseudo-Supervision for Histopathology Tissue Semantic Segmentation using Patch-level Classification Labelscited by 43
2021Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentationcited by 41
2023CLIP in Medical Imaging: A Surveycited by 40
2021Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervisioncited by 39
2021Incremental Learning in Semantic Segmentation from Image Labelscited by 39
2021Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentationcited by 37
2022Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentationcited by 37
2023Referring Image Segmentation Using Text Supervisioncited by 35
2021Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervisioncited by 31
2021All you need are a few pixels: semantic segmentation with PixelPickcited by 30
2023DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Modelcited by 30
2021Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentationcited by 29
2021Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentationcited by 28
2023Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentationcited by 27
2021Unsupervised Foreground Extraction via Deep Region Competitioncited by 26
2022TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentationcited by 26
2022Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentationcited by 26
2023Semantic Image Segmentation: Two Decades of Researchcited by 26
2021Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinementcited by 25
2021Semantic Segmentation In-the-Wild Without Seeing Any Segmentation Examplescited by 24
2022SATS: Self-Attention Transfer for Continual Semantic Segmentationcited by 24
2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
2021Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentationcited by 22
2022FedMix: Mixed Supervised Federated Learning for Medical Image Segmentationcited by 22

50 most cited of 238 All 238 (JSON)