This is the first cross-inductive-bias comparison in knowledge distillation for vision involving a recurrent xLSTM-based teacher: same-family distillation (ViT → DeiT, 88.81%) achieves 1.74 pp higher accuracy than cross-family (ViL → DeiT, 87.07%), yet both deliver equivalent on-device efficiency.
Small surface defects on industrial components are characterized by small scale, low contrast, weak texture, and strong background interference. To improve deployment efficiency while preserving detection accuracy, this study proposes KDSP-DEA-YOLO based on the DEA-YOLOv8n teacher model. A heterogeneous lightweight stu...
Automated galaxy morphology classification now rests on parameter-heavy convolutional backbones, whose cost becomes a design constraint as survey volumes grow. This paper compares three lightweight architectures (MobileNetV2, EfficientNetB0, and MobileViT-Extra Small (XS)) against a ResNet50 baseline on the Galaxy10 Da...
Xiang-Yu Liao· Applied and Computational En...· 0 citations
Generative world models can provide visual rollouts for embodied planning, yet their feasibility on edge devices depends not only on the learned model but also on how the execution runtime represents its operations. We introduce a cache-aware lowering that expresses supported causal Conv3D calls as batched spatial Conv...
Jia-Ming Zhang, Wu Yang, Shu-Han Tao et al.· 0 citations
The deployment of Convolutional Neural Networks (CNNs) for mechanical fault diagnosis at the edge is often limited by the parameter explosion in fully connected layers when processing high-dimensional spectral features, such as the Fast Fourier Transform (FFT). This paper investigates the feasibility of low-latency inf...
L. Carvalho, Luiz Guilherme Ito, J. R. Azambuja· Symposium on Integrated Circ...· 0 citations
Feed-forward 3D reconstruction models have achieved impressive performance by scaling model and dataset size, but their cost excludes most research groups and precludes edge deployment. Additionally, generating 3D supervision without sensors still relies on slow, unreliable Structure-from-Motion, as the community lacks...
A lightweight object-detection system based on the Jetson Nano that uses lower-resolution input, TensorRT operator fusion, and FP16 half-precision quantization to overcome the trade-off between constrained on-board computation of edge devices like AGVs in smart warehousing and logistics and the high real-time demands o...
Jun-Lin He, Wen-Bo Peng, Hong-Bo Zhou et al.· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
