Pith. sign in

REVIEW 5 cited by

EfficientDet: Scalable and Efficient Object Detection

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1911.09070 v7 pith:U5CVWUDX submitted 2019-11-20 cs.CV cs.LGeess.IV

Mingxing Tan , Ruoming Pang , Quoc V. Le This is my paper · ORCID
classification cs.CVcs.LGeess.IV
keywords efficiencyefficientdetfeaturenetworkobjectproposebetterdetection
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency. First, we propose a weighted bi-directional feature pyramid network (BiFPN), which allows easy and fast multiscale feature fusion; Second, we propose a compound scaling method that uniformly scales the resolution, depth, and width for all backbone, feature network, and box/class prediction networks at the same time. Based on these optimizations and better backbones, we have developed a new family of object detectors, called EfficientDet, which consistently achieve much better efficiency than prior art across a wide spectrum of resource constraints. In particular, with single model and single-scale, our EfficientDet-D7 achieves state-of-the-art 55.1 AP on COCO test-dev with 77M parameters and 410B FLOPs, being 4x - 9x smaller and using 13x - 42x fewer FLOPs than previous detectors. Code is available at https://github.com/google/automl/tree/master/efficientdet.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Star-forming clump detection in nearby galaxies using Faster R-CNN and $ugrizy$ imaging data from CLAUDS and HSC-SSP

    astro-ph.IM 2026-07 conditional novelty 6.5 of 10

    A six-band Faster R-CNN with the Zoobot backbone detects star-forming clump candidates in ~700,000 local galaxies, claiming ~90% completeness and ~80% purity for clumps brighter than the surveys' detection limits.

  2. DriveIndia: An Object Detection Dataset for Diverse Indian Traffic Scenes

    cs.CV 2025-07 conditional novelty 6.0 of 10

    DriveIndia is a 66,986-image, 24-class object detection dataset for Indian traffic; the best baseline (YOLOv8) reaches 78.7% mAP50.

  3. Mish: A Self Regularized Non-Monotonic Activation Function

    cs.LG 2019-08 conditional novelty 6.0 of 10

    Mish, a smooth non-monotonic activation function, is proposed and shown to often match or beat ReLU, Swish, and Leaky ReLU on CIFAR-10, ImageNet, and MS-COCO benchmarks.

  4. Bridging the Gap: Physical PCI Device Integration Into SystemC-TLM Virtual Platforms

    cs.SE 2025-05 conditional novelty 5.0 of 10

    Real PCIe devices can be integrated into SystemC-TLM virtual platforms using VFIO, achieving up to 480x speedups on AI inference workloads.

  5. SPACE-SUIT: An Artificial Intelligence Based Chromospheric Feature Extractor and Classifier for SUIT

    astro-ph.SR 2024-12 conditional novelty 5.0 of 10

    A YOLO-based detector, SPACE-SUIT, finds sunspots, plages, filaments, and off-limb structures in SUIT Mg II k images with a validation MAP of 0.874 on mock data.

Pith tools