Research map / Detection and segmentation / CNN features
Taming Dynamic Clutter: Variance-Driven Adaptive Gain Control for Bio-inspired Small Target Detection
Jiaxiang Li, Shaobing Gao, Qinbing Fu, Meiyi Li, Tiansheng Lu, Minjie Tan
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 AGC plugin | STFeedbackSTMD · Synthetic flicker (Vision Egg) | F1: 0.393 -> 0.953 | Improved |
| add AGC plugin | FeedbackSTMD · Synthetic flicker (Vision Egg) | F1: 0.190 -> 0.755 | Improved |
| add AGC plugin | ESTMD · Synthetic flicker (Vision Egg) | F1: 0.009 -> 0.000 | No clear effect |
| add AGC plugin | DSTMD · RIST (flicker injected) | detection rate: 0.260 -> 0.205 | Hurt |
| add AGC plugin | STFeedbackSTMD · RIST (flicker injected) | F1: 0.032 -> 0.256 | Improved |
| add AGC plugin | STFeedbackSTMD · Infrared (flicker injected) | F1: 0.348 -> 0.724 | Improved |
| add AGC plugin | FeedbackSTMD · Infrared (flicker injected) | F1: 0.293 -> 0.561 | Improved |
| add LPTC ego-motion compensation before AGC (ablation) | AGC · natural scenes | detection sensitivity | Improved |
| increase injected ego-motion bias (ablation) | AGC + STFeedbackSTMD · controlled translation sequence | detection accuracy | Hurt |
| increase flicker size beyond 9x9 pixels (ablation) | AGC · Vision Egg flicker size sweep | detection margin | Hurt |
| use too small lambda (ablation) | AGC · parameter sensitivity | dim target detection | Hurt |
| AGC-augmented STFeedbackSTMD vs deep detectors | STFeedbackSTMD + AGC · Synthetic flicker stress test | F1: 0.2392 -> 0.8610 | Improved |
Closest papers by meaning
- Target-Aware Invertible Encoder with Reconstruction Guidance for Infrared Small Target Detection (CVPR 2026 · similarity 0.80)
- Dynamic Symmetric Point Tracking: Tackling Non-ideal Reference in Analog In-memory Training (ICML 2026 · similarity 0.80)
- Continuous Spatiotemporal Events Decoupling through Spike-based Bayesian Computation (NeurIPS 2024 · similarity 0.79)
- AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection (NeurIPS 2024 · similarity 0.79)
- MOCID: Motion Context and Displacement Information Learning for Moving Infrared Small Target Detection (AAAI 2025 · similarity 0.79)
- RAWild: Toward Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modeling (NeurIPS 2026 · similarity 0.78)
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.
