Research map / Detection and segmentation / Open-set and few-shot detection
Unifying Visual Perception by Dispersible Points Learning
Jianming Liang, Guanglu Song, Biao Leng, Yu Liu
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 UniHead instead of extra blocks (ablation) | ResNet-50 · ImageNet-1k val | top-1 accuracy: 79.0 -> 79.5 | Improved |
| add extra blocks to Swin-B (ablation) | Swin-B · ImageNet-1k val | top-1 accuracy: 83.5 -> 83.6 | No clear effect |
| add UniHead (ablation) | Swin-B · ImageNet-1k val | top-1 accuracy: 83.5 -> 83.9 | Improved |
| add task token (ablation) | UniHead Faster RCNN · COCO val detection | AP: 41.6 -> 41.8 | Improved |
| add task token (ablation) | UniHead Faster RCNN · COCO val keypoints | AP: 50.4 -> 50.7 | Improved |
| add task-specific bias initialization (ablation) | UniHead · COCO val detection | AP: 40.9 -> 41.6 | Improved |
| add task-specific bias initialization (ablation) | UniHead · COCO val keypoints | AP: 57.0 -> 57.9 | Improved |
| increase point number K from 8 to 16 (ablation) | UniHead · COCO val detection | AP: 40.8 -> 41.8 | Improved |
| increase point number K from 16 to 32 (ablation) | UniHead · COCO val detection | AP: 41.8 -> 41.5 | Hurt |
| increase transformer blocks from 1+1 to 4+4 (ablation) | UniHead · COCO val detection | AP: 41.6 -> 42.0 | Improved |
| add head disentanglement (ablation) | Faster RCNN · COCO val detection | AP: 38.8 -> 39.3 | Improved |
| add multi-head self attention (ablation) | Faster RCNN with head disentanglement · COCO val detection | AP: 39.3 -> 39.9 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- Faster RCNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 5 of 5 shared results
- FCOS — FCOS: Fully Convolutional One-Stage Object Detection (ICCV 2019) · better on 1 of 1 shared result
- Cascade RCNN — Cascade R-CNN: Delving Into High Quality Object Detection (CVPR 2018) · 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
- Perception Encoder: The best visual embeddings are not at the output of the network (NeurIPS 2025 · similarity 0.88)
- UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface (NeurIPS 2025 · similarity 0.87)
- UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling (NeurIPS 2024 · similarity 0.87)
- Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials (NeurIPS 2025 · similarity 0.87)
- DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers (CVPR 2025 · similarity 0.86)
- VITRIX-UniViTAR: Unified Vision Transformer with Native Resolution (NeurIPS 2025 · similarity 0.86)
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.
