arXiv:2610.29617v1 Announce Type: cross Abstract: Edge medical segmentation must reconcile small model size, high accuracy, and fast inference. TernScope addresses this tradeoff through model--hardwa...
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.
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.
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.
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.
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.
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.
The paper introduces DEX, an MSDF (most‑significant‑digit‑first) accelerator for quantized U‑Net brain‑tumor segmentation. It employs a two‑stage grouped processing element that supports signed INT8 operands and in‑stream bias accumulation, and implements four runtime mechanisms—exact early negative detection, exact sign‑only decision making, calibrated low‑order‑digit skipping, and calibrated pruning—to dynamically reduce computation. In experiments on a BraTS‑trained residual U‑Net, the approach cuts digit cycles by 38.38 % while maintaining a mean Dice score of 80.58 % (vs. 81.20 % for the floating‑point model), and the exact mechanisms alone achieve an 18.79 % cycle reduction without altering the quantized output.
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...
The paper presents a PyTorch-based framework for designing and optimizing binarized neural networks, incorporating freezing and pruning mechanisms. It introduces a novel pruning method that uses a global weighting scheme to assess parameter importance across abstraction levels, achieving a 70% pruning rate on VGG11 without sacrificing accuracy—outperforming existing binarized pruning results of 41%. The framework facilitates rapid, reproducible evaluation and prototyping of state‑of‑the‑art binarized network techniques.
Deep learning frameworks like nnU-Net achieve state-of-theart brain lesion segmentation performance but remain difficult to deploy in clinical research environments due to, among other reasons, software dependencies and computational requirements. We introduce StrokeSeg2, a lightweight, modular, cross-platform C++/Qt framework designed to adapt resource-intensive 3D stroke segmentation pipelines into portable and reproducible applications.
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...