Selective Spatio-Temporal Fruit Inspector (S$^2$FI): A Mamba-based Framework for Rotational Fruit Quality Assessment
We propose the Selective Spatio-Temporal Fruit Inspector (S$^2$FI) architecture, which combines a 3D convolutional encoder with a Mamba-based backbone.It efficiently extracts spatiotemporal features, adaptively weighs informative frames during fruit rotation, and models long-range dependencies with linear complexity, reducing motion blur and occlusion.
ProofPaper ↗
Key points
- The global fruit and vegetable industry confronts severe post-harvest sorting challenges for small and medium-scale growers.
- To bridge this gap between expensive equipment and inefficient manual work, this study develops a low-cost, high-efficiency, lightweight fruit sorting system driven by deep learning, suitable for small and medium growers.
- We also built a conveyor-based fruit quality video dataset with 6,460 samples.
- Experiments on the held-out test set show that our method achieves the best trade-off among accuracy, efficiency, and practicality, outperforming the compared baselines on the test set, achieving an excellent balance of accuracy, speed, and practicality for real-world sorting.
Sources (1)
- [1]Selective Spatio-Temporal Fruit Inspector (S$^2$FI): A Mamba-based Framework for Rotational Fruit Quality AssessmentarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 01:53 AM
We propose the Selective Spatio-Temporal Fruit Inspector (S$^2$FI) architecture, which combines a 3D convolutional encoder with a Mamba-based backbone.It efficiently extracts spatiotemporal features, adaptively weighs informative frames during fruit rotation, and models long-range dependencies with linear complexity, reducing motion blur and occlusion.
The global fruit and vegetable industry confronts severe post-harvest sorting challenges for small and medium-scale growers.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 9, 2026Time Delay System for Sequence Modeling
- Oct 8, 2026Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based Validation
- Oct 8, 2026SACQ: Structured Decoding with Memory-Conditioned Refinement for Long-Horizon Forecasting
- Oct 7, 2026CMP-IRRT*: A Perception-Assisted Height-Adaptive Planner for Quadruped Robots
- Oct 7, 2026HAN-Mamba: Hierarchical Selective State Space Networks for Multi-Scale Financial Volatility Forecasting
- Oct 7, 2026FedSSMCoOp: SSM Encoders for light-weight Federated Prompt Learning for Few-shot Classification