AI Paper Atlas

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

Tensor Decomposition and Language Description for Open-Vocabulary Object Detection

Qiuyu Liang, Yongqiang Zhang

AAAI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 1 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 low-rank proposal filtering (ablation)TLDet (VLDet baseline) · OV-COCONovel AP: 32.0 -> 34.2Improved
add core tensor knowledge distillation (ablation)TLDet (VLDet baseline) · OV-COCOBase AP: 50.6 -> 54.4Improved
add language description enhancement (ablation)TLDet (VLDet baseline) · OV-COCONovel AP: 32.0 -> 33.1Improved
add language description enhancement (ablation)TLDet (VLDet baseline) · OV-COCOBase AP: 50.6 -> 50.4No clear effect
combine LRPF, CTKD and LDE versus any pair (ablation)TLDet · OV-COCONovel AP: 35.2 -> 36.1Improved
core tensor KD instead of traditional KD (ablation)TLDet · OV-COCONovel AP50: 33.2 -> 33.8Improved
static mean fusion instead of cosine-adaptive or KL-consistency fusion in LDE (ablation)TLDet · OV-COCONovel AP50: 35.6 / 35.9 -> 36.1No clear effect
TLDet versus VLDet baseline on LVIS rareTLDet · LVIS (Swin-B)mask AP rare: 26.3 -> 30.1Improved
TLDet versus DVDet on overall LVIS mask APTLDet · LVIS (Swin-B)mask AP all: 40.2 -> 39.1Hurt
transfer COCO-trained TLDet to LVIS validationTLDet · LVIS valAP50: 10.0 -> 12.3Improved

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