AI Paper Atlas

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

Unsupervised Pre-Training With Language-Vision Prompts for Low-Data Instance Segmentation

Dingwen Zhang, Hao Li, Diqi He, Nian Liu, Lechao Cheng, Jingdong Wang, Junwei Han

TPAMI 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary 3D and world perception · 44 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 auxiliary kernel supervision loss (ablation)UPLVP K-Net · COCO 10%mask AP: 25.3 -> 25.4Improved
add cosine-similarity prompt-kernel matching vs no prompting (ablation)UPLVP K-Net · COCO 10%mask AP: 25.2 -> 25.4Improved
random prompt assignment instead of no prompt (ablation)UPLVP K-Net · COCO 10%mask AP: -0.1 mAPHurt
cosine similarity instead of sequential assignment (ablation)UPLVP K-Net · COCO 10%mask AP: 25.3 -> 25.4Improved
use 80 CLIP category labels instead of saliency 0/1 labels (ablation)UPLVP K-Net · COCO 10%mask AP: 24.2 -> 25.4Improved
add prompting to K-Net with UPSP pseudo labels (ablation)K-Net · COCO 10%mask AP: 21.7 -> 23.5Improved
add prompting to K-Net with random proposals (ablation)K-Net · COCO 10%mask AP: 0.8 -> 10.0Improved
add prompting with FreeSOLO pseudo labels (ablation)K-Net · COCO 10%mask AP: 23.3 -> 24.0Improved
UPLVP pre-training instead of ImageNet supervisedK-Net · COCO 5%mask AP: 14.8 -> 22.2Improved
UPLVP instead of UPSP (add category knowledge)K-Net · COCO 5%mask AP: 19.9 -> 22.2Improved
UPLVP vs FreeSOLO pre-trainingK-Net · COCO 10%mask AP: 25.6 -> 25.4No clear effect
UPLVP vs Mask R-CNN on small objectsK-Net · CityscapesAP_S: 8.3 -> 7.3Hurt

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