Edge medical segmentation must reconcile small model size, high accuracy, and fast inference. TernScope addresses this tradeoff through model--hardware co-design, learning a compact segmentation netwo...
The paper presents a lightweight, energy‑efficient lung tumor segmentation model that combines the ENet architecture with UNet‑style skip connections and a lightweight Convolutional Block Attention Module (CBAM). Trained on TCIA data and evaluated on LIDC‑IDRI, the model achieves a Dice score of 0.90812 while using only 430,052 parameters and 0.549 GMAC, making it up to 10 times faster and far less computationally demanding than UNet or SegNet. Grad‑CAM is employed to provide visual interpretability and highlight areas needing improvement.
SpineContextResUNet is a lightweight 3D Residual U‑Net that uses a Context Block with parallel multi‑dilated convolutions to efficiently capture long‑range anatomical dependencies for spine CT segmentation. It achieves Dice scores of 88.17% on VerSe2020 and 88.13% on CTSpine1K while maintaining a small ~1.7 M parameter footprint. Compared to resource‑heavy Transformers and baselines that fail on commodity hardware, SpineContextResUNet delivers robust inference on edge devices such as the Nvidia Jetson Orin Nano.
arXiv:2606. 26650v1 Announce Type: cross Abstract: In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs.
arXiv:2602. 23334v2 Announce Type: replace-cross Abstract: Neural network accelerators have been widely applied to edge devices for complex tasks like object tracking, image recognition, etc.
This paper presents an energy-efficient hardware acceleration of the convolutional layers in the U-Net architecture for image segmentation, implemented on FPGA. While digit-serial arithmetic, particularly most-significant-digit-first (MSDF) techniques, offers a compact hardware footprint, it suffers from initial latency before producing the first output digit.
arXiv:1812.00877v2 Announce Type: replace-cross Abstract: Segmentation of skin lesion boundaries in dermoscopic imaging is an important prerequisite step for computer-aided diagnosis of malignant mel...
In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs. Unlike existing state-of-the-art ternary quantization methods that rely on data-intensive and costly quantization-aware training to mitigate severe performance degradation, CAT-Q is a simple yet effective post-training quantization scheme that is readily applicable to LLMs with diverse architectures and model sizes.
arXiv:2509. 10334v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, yet their deployment on resource-constrained devices remains limited due to their high memory footprint and computational cost.
arXiv:2609.28327v1 Announce Type: new Abstract: We present LightMIS, a scalable family of ultra-lightweight convolutional networks for 2D binary medical image segmentation without a learned stage-wis...
arXiv:2507. 15958v5 Announce Type: replace-cross Abstract: On-device skin lesion analysis is constrained by the compute and energy cost of conventional CNN inference and by the need for lightweight calibration under clinical data shift.
arXiv:2610.15092v1 Announce Type: cross Abstract: Quantization plays a crucial role in efficiently deploying deep learning models on resource-constrained devices. Post-training quantization does not...