Research map / Label-efficient and robust learning / Recognition and long-tail
Cost-Aware Fine-Grained Recognition for IoTs Based on Sequential Fixations
Hanxiao Wang, Venkatesh Saligrama, Stan Sclaroff, Vitaly Ablavsky
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 a conditioned critic to DDPG (ablation) | foveation actor · CUB/Cars/Dogs (foveated) | accuracy (%): 51.0 -> 57.1 (CUB); average +8.0% | Improved |
| add coaching from a heuristic oracle policy (ablation) | DDPG with conditioned critic · CUB/Cars/Dogs (foveated) | accuracy (%): 57.1 -> 67.0 (CUB); average 19.0% gain over DDPG | Improved |
| use full DDPGC3 training (ablation) | DRIFT · CUB/Cars/Dogs (foveated) | accuracy (%): 67.0 -> 74.4 (CUB); average 25.2% over DDPG | Improved |
| use DRIFT fixations instead of center fixation | IoT foveation · CUB | accuracy (%): 59.3 -> 74.4 | Improved |
| use saliency or attention fixations instead of center fixation | IoT foveation · CUB | accuracy (%): 59.3 -> 37.5 (Saliency), 44.4 (Attention) | Hurt |
| add fallback to full high-acuity image on high entropy (DRIFT_E) | DRIFT · Aircrafts | accuracy (%): 86.7 -> 88.0 | Improved |
| fuse prediction with DRIFT zoomed attention | Inception-V3 · fine-grained standard | accuracy (%): average +1.9% | Improved |
| fuse prediction with DRIFT zoomed attention | ResNet-50 · fine-grained standard | accuracy (%): average +2.1% | Improved |
| use DRIFT boxes instead of center box | localization · CUB hit rate | hit rate (%): 36.2 -> 44.3 | Improved |
| use DRIFT boxes instead of center box | localization · Aircrafts hit rate | hit rate (%): 32.9 -> 50.9 | Improved |
Closest papers by meaning
- On-Device Training Under 256KB Memory (NeurIPS 2022 · similarity 0.84)
- TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge (ICML 2024 · similarity 0.83)
- TransNeXt: Robust Foveal Visual Perception for Vision Transformers (CVPR 2024 · similarity 0.82)
- DiVE-k: DIFFERENTIAL VISUAL REASONING FOR FINE-GRAINED IMAGE RECOGNITION (ICLR 2026 · similarity 0.82)
- Reinforcement Learning as a Parsimonious Alternative to Prediction Cascades: A Case Study on Image Segmentation (AAAI 2024 · similarity 0.82)
- LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision (NeurIPS 2025 · similarity 0.82)
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.
