Pith. sign in

REVIEW 7 cited by

AutoAssign: Differentiable Label Assignment for Dense 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 2007.03496 v3 pith:NX2JGVNZ submitted 2020-07-07 cs.CV

Benjin Zhu , Jianfeng Wang , Zhengkai Jiang , Fuhang Zong , Songtao Liu , Zeming Li , Jian Sun This is my paper · ORCID
classification cs.CV
keywords weightingadjustautoassignobjectachievesadaptassignmentbest
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Determining positive/negative samples for object detection is known as label assignment. Here we present an anchor-free detector named AutoAssign. It requires little human knowledge and achieves appearance-aware through a fully differentiable weighting mechanism. During training, to both satisfy the prior distribution of data and adapt to category characteristics, we present Center Weighting to adjust the category-specific prior distributions. To adapt to object appearances, Confidence Weighting is proposed to adjust the specific assign strategy of each instance. The two weighting modules are then combined to generate positive and negative weights to adjust each location's confidence. Extensive experiments on the MS COCO show that our method steadily surpasses other best sampling strategies by large margins with various backbones. Moreover, our best model achieves 52.1% AP, outperforming all existing one-stage detectors. Besides, experiments on other datasets, e.g., PASCAL VOC, Objects365, and WiderFace, demonstrate the broad applicability of AutoAssign.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection

    cs.CV 2025-08 conditional novelty 6.0 of 10

    DenoDet V2 reaches 56.71 mAP on SARDet-100K, the best reported result, by using band-wise phase-amplitude token exchange to denoise DFT features, while using roughly half the parameters of DenoDet V1.

  2. Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A new benchmark for oriented tiny object detection with the smallest object sizes to date, plus a dynamic coarse-to-fine training scheme that improves accuracy across eight datasets.

  3. Physics-Informed Super-Resolution of Atmospheric Data

    cs.LG 2026-07 reject novelty 5.0 of 10

    Adding multi-scale hydrostatic-primitive-equation losses to atmospheric super-resolution models improves reported physical-consistency scores and some reconstruction/event-detection metrics, but the metric and constra...

  4. Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection

    cs.CV 2025-04 conditional novelty 5.0 of 10

    PLUSNet combines Fourier-based feature purification, multi-criteria label assignment, and a frequency-decoupled head to improve small object detection by about 3 AP on SODA-D.

  5. SAR-NAS: Lightweight SAR Object Detection with Neural Architecture Search

    cs.CV 2025-09 conditional novelty 4.0 of 10

    Applying a one-shot evolutionary NAS to YOLOv10 channel widths yields SAR-NAS-S and SAR-NAS-N, which modestly improve mAP on SARDet-100K over YOLOv10 baselines while cutting parameters and FLOPs.

  6. CEM-FBGTinyDet: Context-Enhanced Foreground Balance with Gradient Tuning for tiny Objects

    cs.CV 2025-06 reject novelty 4.0 of 10

    A tiny-object detector with high-to-low level feature fusion and a sigmoid-weighted L1/L2 loss reports +1.3 AP on AI-TOD, but the loss gradient claims are contradicted by the paper's own equations.

  7. A Simple Detector with Frame Dynamics is a Strong Tracker

    cs.CV 2025-05 conditional novelty 4.0 of 10

    Adding frame difference or optical flow channels to a YOLO-based detector, plus a trajectory-constrained false-positive filter, produces top-ranked infrared UAV tracking without a Siamese or transformer tracking head.

Pith tools