The reviewed record of science sign in
Pith
Pith Number

pith:32GMPYZP

pith:2021:32GMPYZPDA6GC4M2MVJO7WOGEP
not attested not anchored not stored refs resolved

YOLOX: Exceeding YOLO Series in 2021

Feng Wang, Jian Sun, Songtao Liu, Zeming Li, Zheng Ge

YOLOX turns YOLO detectors anchor-free with a decoupled head and SimOTA assignment to reach higher accuracy at real-time speeds.

arxiv:2107.08430 v2 · 2021-07-18 · cs.CV

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?
Add to your LaTeX paper 
\usepackage{pith}
\pithnumber{32GMPYZPDA6GC4M2MVJO7WOGEP}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
✓ Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

for YOLOX-L with roughly the same amount of parameters as YOLOv4-CSP, YOLOv5-L, we achieve 50.0% AP on COCO at a speed of 68.9 FPS on Tesla V100, exceeding YOLOv5-L by 1.8% AP.

C2weakest assumption

That the reported gains stem primarily from the anchor-free design, decoupled head, and SimOTA rather than from differences in training schedules, data augmentation, or hyperparameter choices versus the YOLOv5 and YOLOv4 baselines.

C3one line summary

YOLOX exceeds prior YOLO models by adopting anchor-free detection, decoupled heads, and SimOTA assignment to reach 50.0% AP on COCO for the large variant.

References

40 extracted · 40 resolved · 4 Pith anchors

[1] YOLOv4: Optimal Speed and Accuracy of Object Detection 2004 · arXiv:2004.10934
[2] End-to- end object detection with transformers 2020
[3] You only look one-level feature 2021
[4] Ota: Optimal transport assignment for object detection 2021
[5] Lla: Loss-aware label assignment for dense pedestrian detection

Formal links

2 machine-checked theorem links

Cited by

65 papers in Pith

LEVIRDet: A Million-Scale 159-Category Dataset and Foundation Model for Universal Remote Sensing Object Detection
Polycepta: Object-Centric Appearance Estimation for Multi-Object Tracking
From Spatial to Spectral: An Efficient, Frequency-Guided Feature Representation Learner for Small Object Detection
Integrated cloud-based architecture for robot-robot and human-robot collaboration using ROS 2--MQTT in Mediterranean Greenhouses
Neural Events: Discrete Asynchronous Autoencoders for Event-Based Vision
Receipt and verification
First computed 2026-07-05T03:03:41.413431Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

de8cc7e32f183c61719a6552efd9c623ddf44e989df98db79dd131d58f012e29

Aliases

arxiv: 2107.08430 · arxiv_version: 2107.08430v2 · doi: 10.48550/arxiv.2107.08430 · pith_short_12: 32GMPYZPDA6G · pith_short_16: 32GMPYZPDA6GC4M2 · pith_short_8: 32GMPYZP
Agent API
Resolver JSON Graph JSON Events JSON Schema Signing key
Verify this Pith Number yourself 
curl -sH 'Accept: application/ld+json' https://pith.science/pith/32GMPYZPDA6GC4M2MVJO7WOGEP \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: de8cc7e32f183c61719a6552efd9c623ddf44e989df98db79dd131d58f012e29
Canonical record JSON 
{
  "metadata": {
    "abstract_canon_sha256": "28db477965163b83d1fc4b948c58e416a5eee1c6cb06987ee4131561b1ef4d81",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2021-07-18T12:55:11Z",
    "title_canon_sha256": "448e0cfa55f7964fea285d0d52fd7c8cb392d9b8f8b2cafca786226b493e7440"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2107.08430",
    "kind": "arxiv",
    "version": 2
  }
}