AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Pix2seq: A Language Modeling Framework for Object Detection

Ting Chen, Saurabh Saxena, Lala Li, David J. Fleet, Geoffrey Hinton

ICLR 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 128 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Pretrain Pix2Seq on Objects365 before COCO fine-tuningPix2Seq · COCO 2017 valAP: 45.0 -> 50.0Improved
Increase fine-tuning image size from 640×640 to 1333×1333Objects365-pretrained Pix2Seq, R50 · COCO 2017 valAP: 39.1 -> 42.6Improved
Add sequence augmentation during fine-tuning (ablation)Pix2Seq pretrained on Objects365 · COCO 2017 valAR@100: 55.4 -> 61.6Improved
Add sequence augmentation during fine-tuning (ablation)Pix2Seq pretrained on Objects365 · COCO 2017 valAP: 43.7 -> 44.5Improved
Add sequence augmentation during pretraining as well as fine-tuning (ablation)Pix2Seq pretrained on Objects365 · COCO 2017 valAR@100: 61.6 -> 61.7No clear effect
Use deterministic object ordering instead of random ordering (ablation)Pix2Seq sequence construction · COCOAPHurt
Use fewer than 500 coordinate quantization bins (ablation)Pix2Seq sequence construction · COCO, images with longest side 640 pixelsAPHurt
Use nucleus sampling instead of argmax sampling at inference (ablation)Pix2Seq · COCOAPImproved
Remove sequence augmentation and delay EOS sampling (ablation)Pix2Seq trained from scratch on COCO · COCOARHurt

Later papers that compared with this method

2 later accepted papers report Pix2Seq as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy