pith. sign in

arxiv: 1701.06659 · v1 · pith:EEDRWCGSnew · submitted 2017-01-23 · 💻 cs.CV

DSSD : Deconvolutional Single Shot Detector

Cheng-Yang Fu , Wei Liu , Ananth Ranga , Ambrish Tyagi , Alexander C. Berg This is my paper
classification 💻 cs.CV
keywords detectionadditionaldssdstate-of-the-artapproachcococontextdeconvolution
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ALFA: Agglomerative Late Fusion Algorithm for Object Detection

    cs.CV 2019-07 unverdicted novelty 7.0

    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...

  2. SAM-Sode: Towards Faithful Explanations for Tiny Bacteria Detection

    cs.CV 2026-05 unverdicted novelty 6.0

    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.

  3. Reprojection R-CNN: A Fast and Accurate Object Detector for 360{\deg} Images

    cs.CV 2019-07 unverdicted novelty 6.0

    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 s...

  4. Towards Adversarially Robust Object Detection

    cs.CV 2019-07 unverdicted novelty 5.0

    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.

  5. Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection

    cs.CV 2019-07 unverdicted novelty 5.0

    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.

  6. YOLOv3: An Incremental Improvement

    cs.CV 2018-04 accept novelty 4.0

    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.

  7. A unified neural network for object detection, multiple object tracking and vehicle re-identification

    cs.CV 2019-07 unverdicted novelty 3.0

    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.