AI Paper Atlas

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

"PartImageNet: A Large, High-Quality Dataset of Parts"

Ju He, Shuo Yang, Shaokang Yang, Adam Kortylewski, Xiaoding Yuan, Jie-Neng Chen, Shuai Liu, Cheng Yang, Qihang Yu, Alan Yuille

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 105 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
add part-annotation deep supervision at stage 2 (ablation)Deeplab v3+ · PartImageNet object segmentationmIoU (val): 74.04 -> 74.21No clear effect
add part-annotation deep supervision at stage 3 (ablation)Deeplab v3+ · PartImageNet object segmentationmIoU (test): 71.79 -> 72.26Improved
add part-annotation deep supervision at stage 4 (ablation)Deeplab v3+ · PartImageNet object segmentationmIoU (val): 74.04 -> 75.67Improved
add part-annotation deep supervision at stage 4 (ablation)Deeplab v3+ · PartImageNet object segmentationmIoU (test): 71.79 -> 72.84Improved
add object masks as deep supervision at stage 4 (ablation)Deeplab v3+ · PartImageNet object segmentationmIoU (val): 74.04 -> 72.45Hurt
supervise parts with cross entropy instead of none (ablation)Deeplab v3+ stage 4 · PartImageNet object segmentationmIoU (val): 74.04 -> 73.88Hurt
use binary cross entropy instead of cross entropy for part deep supervision (ablation)Deeplab v3+ stage 4 · PartImageNet object segmentationmIoU (val): 73.88 -> 75.67Improved
initialize part dictionaries with part annotations (ablation)COMPAS · PartImageNet few-shot 5-way 1-shotaccuracy: 67.1 -> 68.0Improved
initialize part dictionaries with part annotations (ablation)COMPAS · PartImageNet few-shot 5-way 5-shotaccuracy: 82.3 -> 82.9Improved
use annotated part regions instead of random regions (ablation)DeepEMD · PartImageNet few-shot 5-way 1-shotaccuracy: 67.3 -> 68.5Improved
use annotated part regions instead of random regions (ablation)DeepEMD · PartImageNet few-shot 5-way 5-shotaccuracy: 82.7 -> 83.6Improved

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