Research map / Detection and segmentation / CNN features
Spatially Invariant Unsupervised Object Detection with Convolutional Neural Networks
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 explicit object-like latent representation from SPAIR instead of plain ConvNet features | LSTM downstream classifier · SET | test accuracy: 50.1 -> 57.9 | Helped |
| replace AIR's recurrent encoder with spatially invariant convolutional encoder (SPAIR) | AIR · scattered MNIST, many digits | Average Precision | Helped |
| add lateral connections between neighboring cells in encoder (ablation) | SPAIR · scattered MNIST 11-15 digits | Average Precision | Helped |
| train on 11-15 digits instead of 6-10 digits | SPAIR · 84x84 scattered MNIST, 1-20 digits | Average Precision | No clear effect |
Closest papers by meaning
- Unsupervised Object Detection with Theoretical Guarantees (NeurIPS 2024 · similarity 0.91)
- Unsupervised Object Localization: Observing the Background To Discover Objects (CVPR 2023 · similarity 0.91)
- Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking (AAAI 2020 · similarity 0.91)
- R-FCN: Object Detection via Region-based Fully Convolutional Networks (NeurIPS 2016 · similarity 0.90)
- ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models (NeurIPS 2019 · similarity 0.90)
- Seeing without Looking: Contextual Rescoring of Object Detections for AP Maximization (CVPR 2020 · 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.