Research map / Detection and segmentation / CNN features
SALISA: Saliency-Based Input Sampling for Efficient Video Object Detection
Babak Ehteshami Bejnordi, Amirhossein Habibian, Fatih Porikli, Amir Ghodrati
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 saliency-based input resampling | EfficientDet-D0 · UA-DETRAC | mAP: 51.3 -> 54.2 | Improved |
| add saliency-based input resampling | EfficientDet-D2 · UA-DETRAC | mAP: 59.4 -> 61.2 | Improved |
| add saliency-based input resampling | EfficientDet-D2 · ImageNet-VID | mAP: 72.5 -> 74.5 | Improved |
| add saliency-based input resampling | EfficientDet-D1 · UA-DETRAC small objects | small-object mAP: 8.4 -> 14.9 | Improved |
| add saliency-based input resampling | EfficientDet-D1 · UA-DETRAC medium objects | mAP: 54.8 -> 58.2 | Improved |
| add saliency-based input resampling | EfficientDet-D3 · UA-DETRAC large objects | mAP: 78.5 -> 78.0 | No clear effect |
| add the regularization loss to the TPS-STN resampler (ablation) | SALISA with EfficientDet-D1 · UA-DETRAC | mAP: 57.6 -> 61.4 | Improved |
| use SALISA resampler instead of learning to zoom (ablation) | SALISA with EfficientDet-D1 · UA-DETRAC | mAP: 47.7 -> 61.4 | Improved |
| increase TPS control points from 256 to 1024 (ablation) | SALISA with EfficientDet-D0 · UA-DETRAC | mAP: 54.2 -> 45.7 | Hurt |
| lower area threshold alpha from 2.0 to 0.5 (ablation) | SALISA with EfficientDet-D1 · UA-DETRAC small objects | small-object mAP: 13.1 -> 14.9 | Improved |
| lower alpha from 0.5 to 0.1 (ablation) | SALISA with EfficientDet-D1 · UA-DETRAC small objects | small-object mAP: 14.9 -> 13.4 | Hurt |
| lower saliency threshold tau from 0.5 to 0.3 (ablation) | SALISA with EfficientDet-D0 · ImageNet-VID | mAP: 70.2 -> 70.4 | No clear effect |
Closest papers by meaning
- Towards High-Resolution Salient Object Detection (ICCV 2019 · similarity 0.89)
- Cascaded Partial Decoder for Fast and Accurate Salient Object Detection (CVPR 2019 · similarity 0.88)
- An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection (CVPR 2019 · similarity 0.88)
- Disentangled High Quality Salient Object Detection (ICCV 2021 · similarity 0.88)
- DVSOD: RGB-D Video Salient Object Detection (NeurIPS 2023 · similarity 0.88)
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · similarity 0.88)
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.
