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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add low-rank proposal filtering (ablation) | TLDet (VLDet baseline) · OV-COCO | Novel AP: 32.0 -> 34.2 | Improved |
| add core tensor knowledge distillation (ablation) | TLDet (VLDet baseline) · OV-COCO | Base AP: 50.6 -> 54.4 | Improved |
| add language description enhancement (ablation) | TLDet (VLDet baseline) · OV-COCO | Novel AP: 32.0 -> 33.1 | Improved |
| add language description enhancement (ablation) | TLDet (VLDet baseline) · OV-COCO | Base AP: 50.6 -> 50.4 | No clear effect |
| combine LRPF, CTKD and LDE versus any pair (ablation) | TLDet · OV-COCO | Novel AP: 35.2 -> 36.1 | Improved |
| core tensor KD instead of traditional KD (ablation) | TLDet · OV-COCO | Novel AP50: 33.2 -> 33.8 | Improved |
| static mean fusion instead of cosine-adaptive or KL-consistency fusion in LDE (ablation) | TLDet · OV-COCO | Novel AP50: 35.6 / 35.9 -> 36.1 | No clear effect |
| TLDet versus VLDet baseline on LVIS rare | TLDet · LVIS (Swin-B) | mask AP rare: 26.3 -> 30.1 | Improved |
| TLDet versus DVDet on overall LVIS mask AP | TLDet · LVIS (Swin-B) | mask AP all: 40.2 -> 39.1 | Hurt |
| transfer COCO-trained TLDet to LVIS validation | TLDet · LVIS val | AP50: 10.0 -> 12.3 | Improved |
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.
- CORA — CORA: Adapting CLIP for Open-Vocabulary Detection With Region Prompting and Anchor Pre-Matching (CVPR 2023) · better on 1 of 1 shared result
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
- CAKE: Category Aware Knowledge Extraction for Open-Vocabulary Object Detection (AAAI 2025 · similarity 0.92)
- SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection (CVPR 2024 · similarity 0.91)
- Exploring Region-Word Alignment in Built-in Detector for Open-Vocabulary Object Detection (CVPR 2024 · similarity 0.91)
- ProxyDet: Synthesizing Proxy Novel Classes via Classwise Mixup for Open-Vocabulary Object Detection (AAAI 2024 · similarity 0.90)
- DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection (NeurIPS 2025 · similarity 0.90)
- Open-Det: An Efficient Learning Framework for Open-Ended Detection (ICML 2025 · similarity 0.90)
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.
