arXiv AI
Hardware-Aware Learned Representation Compression for Distributed In-Sensor Vision
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 14
Adaptive AI: Energy Efficient Multi-exit TinyML on Intelligent Vision Systems at the Edge
The paper presents a novel multi‑exit computational scheme for TinyML on an ultra‑low‑power GAP9 SoC, adding confidence‑based gating points to a MobileNetV2 CNN for ImageNet‑100. By allowing inference to stop early, the approach cuts average MAC operations by 41 % (from 313 MMAC to 185 MMAC), reduces inference time by 29 % (49 ms to 35 ms), and saves 24 % in energy (2.1 mJ to 1.6 mJ per frame) with only a ~1 % drop in accuracy. Compared to a state‑of‑the‑art adaptive CNN on the same hardware, the method more than doubles computational efficiency, raising MAC/cycle from 8.1 to 17.2.
arXiv Machine Learning
Oct 23
Spike-Aware Gradient-Based Mixed-Precision Quantization of Spiking Neural Networks for Vision Applications
The paper introduces a spike‑aware, gradient‑based mixed‑precision quantization framework for Spiking Neural Networks (SNNs), which assigns bit‑widths adaptively using first‑order gradient information. This approach avoids the memory and computational overhead of Hessian‑based methods like HAWQ‑V2 and is evaluated on VGG, ResNet, and Vision Transformer architectures across CIFAR‑10/100, ImageNet, and DVS‑CIFAR‑10 datasets. On ResNet‑34 with ImageNet, the method attains 73.30% accuracy at 4.78× compression, matching HAWQ‑V2 while reducing memory usage by 2.31× and bit‑allocation runtime by 100×, and it demonstrates energy‑efficient deployment without performance loss.
arXiv Machine Learning
Sep 17
FAME: An FPGA-Based Platform for Approximate Multipliers Evaluation with Pattern-Guided DNN Retraining
FAME is an FPGA-based platform that evaluates approximate multipliers directly in hardware, eliminating slow CPU/GPU LUT emulation and reducing evaluation time for DNN inference. It also introduces a pattern-guided retraining method that uses multiplier-specific patterns to recover accuracy losses. Experiments on ResNet‑18 and MobileNetV2 over ImageNet show up to 3.47× faster multiplier evaluation and a 65.5% accuracy improvement over prior retraining approaches.
arXiv Machine Learning
Jun 3
SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction
arXiv:2606. 03940v1 Announce Type: cross Abstract: In robotics systems, vast amounts of visual data are easily captured at high resolution using low-cost, low-power hardware.
Hugging Face Trending Papers
Oct 21
Spike-Aware Gradient-Based Mixed-Precision Quantization of Spiking Neural Networks for Vision Applications
In recent years, Spiking Neural Networks (SNNs) have gained massive attention as an energy-efficient neural computing paradigm due to their event-driven and sparse computing capability. However, maint...
arXiv AI
Oct 15
VLCQ: Post-training quantization for deep neural networks using variable length coding
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...