AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification

Miaoge Li, Dongsheng Wang, Xinyang Liu, Zequn Zeng, Ruiying Lu, Bo Chen, Mingyuan Zhou

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 26 citations (OpenAlex)

Read the paper

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 layer-wise conditional transport loss between patch set and label set (ablation)PatchCT · MS-COCOmAP: 84.7 -> 88.3Improved
add layer-wise conditional transport loss (ablation)PatchCT · Pascal VOC 2007 testmAP: 94.9 -> 97.1Improved
add layer-wise conditional transport loss (ablation)PatchCT · NUS-WIDEmAP: 65.8 -> 68.1Improved
use the prompt 'A photo of {label}' instead of the bare label name (ablation)PatchCT · MS-COCOmAP: 88.0 -> 88.3Improved
use the prompt template instead of label name only (ablation)PatchCT · Pascal VOC 2007 testmAP: 96.7 -> 97.1Improved
vary top-k patch count from 50 to 250 (ablation)PatchCT · Pascal VOC 2007 testmAP: 96.8 to 97.2No clear effect
start the CT alignment at an early layer (l_s < 6) rather than latePatchCT · MS-COCO and Pascal VOC 2007mAPImproved
start the CT alignment from layer 1PatchCT · MS-COCO and Pascal VOC 2007mAPHurt
replace cross-attention alignment with CT alignment (PatchCT vs M3TR)multi-label classifier · MS-COCOmAP: 87.5 -> 88.3Improved
PatchCT vs MlTr-1 on NUS-WIDE overall F1PatchCT · NUS-WIDE (ALL)OF1: 75.8 -> 74.7Mixed

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