Research map / Detection and segmentation / Weakly supervised detection and segmentation
Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection
Carlo Biffi, Steven McDonagh, Philip Torr, Aleš Leonardis, Sarah Parisot
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add shared encoder between branches (ablation) | OAM detector · VOC07 (10 shots) | mAP (%): 42.1 -> 52.1 | Improved |
| add OAM-generated semi-strong images to second branch training (ablation) | OAM detector · VOC07 (10 shots) | mAP (%): 52.1 -> 58.8 | Improved |
| add online bounding box augmentation (ablation) | OAM detector with shared encoder and OAM · VOC07 (10 shots) | mAP (%): 58.8 -> 59.7 | Improved |
| add bounding box augmentation to first branch (with SE and OAM) (ablation) | OAM first branch · VOC07 (10 shots) | mAP (%): 55.7 -> 59.2 | Improved |
| add shared encoder (first branch with BBA) (ablation) | OAM first branch · VOC07 (10 shots) | mAP (%): 50.2 -> 51.7 | Improved |
| use semi-strong images for bounding box regression (ablation) | OAM second branch · VOC07 | mAP (%) | Hurt |
| replace precomputed proposals with learned RPN | OAM · VOC07 (10 shots) | mAP (%): 59.7 -> 54.6 | Hurt |
| add OAM mixed supervision vs Fast R-CNN | Fast R-CNN · COCO14 (10 shots) | AP@.50: 22.1 -> 31.2 | Improved |
| add OAM vs BCNet | BCNet · VOC07 (10 shots) | mAP (%): 57.1 -> 59.7 | Improved |
| add OAM mixed supervision vs Fast R-CNN at 10% COCO17 | Fast R-CNN · COCO17 (10% data) | AP@.50: 53.7 -> 54.2 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Faster R-CNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 3 of 3 shared results
- EHSOD — EHSOD: CAM-Guided End-to-End Hybrid-Supervised Object Detection with Cascade Refinement (AAAI 2020) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- A Survey of Self-Supervised and Few-Shot Object Detection (TPAMI 2022 · similarity 0.91)
- Label, Verify, Correct: A Simple Few Shot Object Detection Method (CVPR 2022 · similarity 0.91)
- Few-Example Object Detection with Model Communication (TPAMI 2018 · similarity 0.91)
- Co-Student: Collaborating Strong and Weak Students for Sparsely Annotated Object Detection (ECCV 2024 · similarity 0.91)
- Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity (NeurIPS 2021 · similarity 0.90)
- Object Detection Benchmarks are Incomplete: The Role of Label Errors and Annotation Uncertainty (NeurIPS 2026 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
