Pith. sign in

REVIEW 6 cited by

FoveaBox: Beyond Anchor-based Object Detector

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 1904.03797 v2 pith:C5PSLNOL submitted 2019-04-08 cs.CV

Tao Kong , Fuchun Sun , Huaping Liu , Yuning Jiang , Lei Li , Jianbo Shi This is my paper · ORCID
classification cs.CV
keywords objectfoveaboxdetectionperformanceaccurateanchoranchorsbounding
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present FoveaBox, an accurate, flexible, and completely anchor-free framework for object detection. While almost all state-of-the-art object detectors utilize predefined anchors to enumerate possible locations, scales and aspect ratios for the search of the objects, their performance and generalization ability are also limited to the design of anchors. Instead, FoveaBox directly learns the object existing possibility and the bounding box coordinates without anchor reference. This is achieved by: (a) predicting category-sensitive semantic maps for the object existing possibility, and (b) producing category-agnostic bounding box for each position that potentially contains an object. The scales of target boxes are naturally associated with feature pyramid representations. In FoveaBox, an instance is assigned to adjacent feature levels to make the model more accurate.We demonstrate its effectiveness on standard benchmarks and report extensive experimental analysis. Without bells and whistles, FoveaBox achieves state-of-the-art single model performance on the standard COCO and Pascal VOC object detection benchmark. More importantly, FoveaBox avoids all computation and hyper-parameters related to anchor boxes, which are often sensitive to the final detection performance. We believe the simple and effective approach will serve as a solid baseline and help ease future research for object detection. The code has been made publicly available at https://github.com/taokong/FoveaBox .

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. FreeAnchor: Learning to Match Anchors for Visual Object Detection

    cs.CV 2019-09 conditional novelty 8.0 of 10

    FreeAnchor formulates anchor assignment in object detection as maximum likelihood estimation with a bag-based loss, and improves RetinaNet's COCO AP from 35.7 to 38.7 on ResNet-50.

  2. Rethinking Annotation for Object Detection: Is Annotating Small-size Instances Worth Its Cost?

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Detectors trained only on medium/large COCO instances, aided by test-time upscaling, detect small instances about as well as a detector trained on all sizes.

  3. Training-Time-Friendly Network for Real-Time Object Detection

    cs.CV 2019-09 conditional novelty 6.0 of 10

    TTFNet is an object detector that trains much faster than prior real-time detectors while keeping similar accuracy, by using Gaussian-weighted samples around each object center during training.

  4. Residual Objectness for Imbalance Reduction

    cs.CV 2019-08 conditional novelty 6.0 of 10

    Residual Objectness replaces hand-crafted sampling and reweighting with cascaded learned objectness refinements, improving RetinaNet, YOLOv3, and Faster R-CNN by 1.1 to 1.3 AP on COCO.

  5. Revisiting Feature Alignment for One-stage Object Detection

    cs.CV 2019-08 conditional novelty 6.0 of 10

    A one-stage detector that aligns convolutional features to predicted anchor boxes via a RoIConv operator, achieving 44.1 mAP on COCO test-dev.

  6. AFP-Net: Realtime Anchor-Free Polyp Detection in Colonoscopy

    eess.IV 2019-09 conditional novelty 5.0 of 10

    AFP-Net, an anchor-free polyp detector with a context enhancement module and cosine ground-truth projection, achieves 99.36% precision and 96.44% recall on CVC-Clinic, and 52.6 FPS.

Pith tools