ALFA is a late-fusion algorithm that clusters predictions from detectors like SSD and Faster R-CNN using location and score information, yielding lower error than individual detectors or prior fusion methods on PASCAL VOC 2007/2012.
DSSD : Deconvolutional Single Shot Detector
9 Pith papers cite this work, alongside 1,636 external citations. Polarity classification is still indexing.
9
Pith papers citing it
1,636
external citations · Pith
abstract
The main contribution of this paper is an approach for introducing additional context into state-of-the-art general object detection. To achieve this we first combine a state-of-the-art classifier (Residual-101[14]) with a fast detection framework (SSD[18]). We then augment SSD+Residual-101 with deconvolution layers to introduce additional large-scale context in object detection and improve accuracy, especially for small objects, calling our resulting system DSSD for deconvolutional single shot detector. While these two contributions are easily described at a high-level, a naive implementation does not succeed. Instead we show that carefully adding additional stages of learned transformations, specifically a module for feed-forward connections in deconvolution and a new output module, enables this new approach and forms a potential way forward for further detection research. Results are shown on both PASCAL VOC and COCO detection. Our DSSD with $513 \times 513$ input achieves 81.5% mAP on VOC2007 test, 80.0% mAP on VOC2012 test, and 33.2% mAP on COCO, outperforming a state-of-the-art method R-FCN[3] on each dataset.
representative citing papers
A million-box 159-class remote-sensing dataset plus a GSD- and hierarchy-aware detector yields ~5 mAP average gains over fully supervised baselines on nine external benchmarks with no target training.
Presents MMIO benchmark and RTVP method achieving state-of-the-art 42.2% AP in zero-shot industrial defect detection.
SAM-Sode refines explanation maps for tiny bacteria detection by converting them into prompts for the SAM3 model and applying physical and geometric dual constraints to suppress background noise.
Reprojection R-CNN is a two-stage detector for 360° images combining a distortion-aware spherical RPN on ERP with a reprojection network on perspective projections, reporting higher mAP than prior methods on two new synthetic datasets at 178 ms per image.
Develops a multi-task learning based adversarial training approach to improve robustness of object detectors to adversarial attacks, with experiments on PASCAL-VOC and MS-COCO.
Cas-RetinaNet improves RetinaNet by 2 AP on MS COCO by training cascade stages on rising IoU thresholds and adding a Feature Consistency Module to align classification confidence with localization accuracy.
YOLOv3 achieves accuracy comparable to SSD and RetinaNet but runs substantially faster, with 28.2 mAP at 320x320 in 22 ms and 57.9 mAP@50 in 51 ms on Titan X.
Faster RCNN is extended with a track branch and trained end-to-end on concatenated video frames to unify detection and re-identification, reaching 57.79% mAP on the AIC19 vehicle dataset.
citing papers explorer
-
ALFA: Agglomerative Late Fusion Algorithm for Object Detection
ALFA is a late-fusion algorithm that clusters predictions from detectors like SSD and Faster R-CNN using location and score information, yielding lower error than individual detectors or prior fusion methods on PASCAL VOC 2007/2012.
-
LEVIRDet: A Million-Scale 159-Category Dataset and Foundation Model for Universal Remote Sensing Object Detection
A million-box 159-class remote-sensing dataset plus a GSD- and hierarchy-aware detector yields ~5 mAP average gains over fully supervised baselines on nine external benchmarks with no target training.
-
Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline
Presents MMIO benchmark and RTVP method achieving state-of-the-art 42.2% AP in zero-shot industrial defect detection.
-
SAM-Sode: Towards Faithful Explanations for Tiny Bacteria Detection
SAM-Sode refines explanation maps for tiny bacteria detection by converting them into prompts for the SAM3 model and applying physical and geometric dual constraints to suppress background noise.
-
Reprojection R-CNN: A Fast and Accurate Object Detector for 360{\deg} Images
Reprojection R-CNN is a two-stage detector for 360° images combining a distortion-aware spherical RPN on ERP with a reprojection network on perspective projections, reporting higher mAP than prior methods on two new synthetic datasets at 178 ms per image.
-
Towards Adversarially Robust Object Detection
Develops a multi-task learning based adversarial training approach to improve robustness of object detectors to adversarial attacks, with experiments on PASCAL-VOC and MS-COCO.
-
Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection
Cas-RetinaNet improves RetinaNet by 2 AP on MS COCO by training cascade stages on rising IoU thresholds and adding a Feature Consistency Module to align classification confidence with localization accuracy.
-
YOLOv3: An Incremental Improvement
YOLOv3 achieves accuracy comparable to SSD and RetinaNet but runs substantially faster, with 28.2 mAP at 320x320 in 22 ms and 57.9 mAP@50 in 51 ms on Titan X.
-
A unified neural network for object detection, multiple object tracking and vehicle re-identification
Faster RCNN is extended with a track branch and trained end-to-end on concatenated video frames to unify detection and re-identification, reaching 57.79% mAP on the AIC19 vehicle dataset.