Research map / Detection and segmentation / Open-set and few-shot detection
Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use spatially invariant discovery and spatially local object representations instead of SQAIR's holistic discovery | Unsupervised object tracking · Scattered MNIST | MOTA | Helped |
| Train on 1–6 digits rather than covering the full test count range | SILOT · Scattered MNIST videos with up to 12 digits | MOTA | Hurt |
| Use a fully convolutional, spatially invariant discovery module | SILOT · Scattered Shapes, full 96 × 96 videos with up to 35 shapes | MOTA | Helped |
| Use discovery dropout to force reliance on propagation | SILOT · Video object tracking | tracking performance | Helped |
| Use curriculum learning that progressively increases the number of training frames | SILOT · Video object tracking | training stability | Helped |
Closest papers by meaning
- Spatially Invariant Unsupervised Object Detection with Convolutional Neural Networks (AAAI 2019 · similarity 0.91)
- Beyond Local Search: Tracking Objects Everywhere With Instance-Specific Proposals (CVPR 2016 · similarity 0.88)
- Unsupervised Deep Tracking (CVPR 2019 · similarity 0.88)
- Track, Check, Repeat: An EM Approach to Unsupervised Tracking (CVPR 2021 · similarity 0.88)
- Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision (NeurIPS 2025 · similarity 0.87)
- VastTrack: Vast Category Visual Object Tracking (NeurIPS 2024 · 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.