Papers › Hierarchical Shot Detector
Hierarchical Shot Detector
Jiale Cao, Yanwei Pang, Jungong Han, Xuelong Li
Single shot detector simultaneously predicts object categories and regression offsets of the default boxes. Despite of high efficiency, this structure has some inappropriate designs: (1) The classification result of the default box is improperly assigned to that of the regressed box during inference, (2) Only regression once is not good enough for accurate object detection. To solve the first problem, a novel reg-offset-cls (ROC) module is proposed. It contains three hierarchical steps: box regression, the feature sampling location predication, and the regressed box classification with the features of offset locations. To further solve the second problem, a hierarchical shot detector (HSD) is proposed, which stacks two ROC modules and one feature enhanced module. The second ROC treats the regressed boxes and the feature sampling locations of features in the first ROC as the inputs. Meanwhile, the feature enhanced module injected between two ROCs aims to extract the local and non-local context. Experiments on the MS COCO and PASCAL VOC datasets demonstrate the superiority of proposed HSD. Without the bells or whistles, HSD outperforms all one-stage methods at real-time speed.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Object Detection | COCO test-dev | HSD (Rest101, 768x768, single-scale test) | AP50 | 61.2 | #175 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | HSD (Rest101, 768x768, single-scale test) | AP75 | 46.9 | #175 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | HSD (Rest101, 768x768, single-scale test) | APL | 55.9 | #175 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | HSD (Rest101, 768x768, single-scale test) | APM | 47.3 | #175 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | HSD (Rest101, 768x768, single-scale test) | APS | 22.8 | #175 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | HSD (Rest101, 768x768, single-scale test) | box mAP | 42.3 | #175 of 225 | Archive leaderboard | report |
| Object Detection | PASCAL VOC 2007 | HSD (VGG16, 512x512, single-scale test) | MAP | 83.0% | #4 of 30 | Archive leaderboard | report |
| Object Detection | PASCAL VOC 2007 | HSD (VGG16, 320x320, single-scale test) | MAP | 81.7% | #7 of 30 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections