Search Results for author:
Found 40 papers, 13 papers with code
PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion
PathFusion introduces a path consistency loss between shallow and deep features, which encourages the 2D backbone and its fusion path to transform 2D features in a way that is semantically aligned with the transform of the 3D backbone.
SDRM3: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloads
Emerging real-time multi-model ML (RTMM) workloads such as AR/VR and drone control often involve dynamic behaviors in various levels; task, model, and layers (or, ML operators) within a model.
Fast Point Cloud Generation with Straight Flows
We perform evaluations on multiple 3D tasks and find that our PSF performs comparably to the standard diffusion model, outperforming other efficient 3D point cloud generation methods.
XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse
Real-time MMMT workloads impose heterogeneity and concurrency requirements on future ML systems and devices, necessitating the development of new capabilities.
LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spotting
This paper proposes a hardware-efficient architecture, Linearized Convolution Network (LiCo-Net) for keyword spotting.
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
Efficient deep neural network (DNN) models equipped with compact operators (e. g., depthwise convolutions) have shown great potential in reducing DNNs' theoretical complexity (e. g., the total number of weights/operations) while maintaining a decent model accuracy.
Streaming parallel transducer beam search with fast-slow cascaded encoders
Streaming ASR with strict latency constraints is required in many speech recognition applications.
Low-Rank+Sparse Tensor Compression for Neural Networks
Low-rank tensor compression has been proposed as a promising approach to reduce the memory and compute requirements of neural networks for their deployment on edge devices.
Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation
Therefore, we propose HRViT, which enhances ViTs to learn semantically-rich and spatially-precise multi-scale representations by integrating high-resolution multi-branch architectures with ViTs.
Ranked #18 on
Semantic Segmentation
on Cityscapes val
Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet
From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with different computational budgets.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Contrastive Quant: Quantization Makes Stronger Contrastive Learning
Contrastive learning, which learns visual representations by enforcing feature consistency under different augmented views, has emerged as one of the most effective unsupervised learning methods.
NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training
In this work, we observe that the poor performance is due to a gradient conflict issue: the gradients of different sub-networks conflict with that of the supernet more severely in ViTs than CNNs, which leads to early saturation in training and inferior convergence.
Ranked #7 on
Neural Architecture Search
on ImageNet
Noisy Training Improves E2E ASR for the Edge
We apply noisy training to improve both dense and sparse state-of-the-art Emformer models and observe consistent WER reduction.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Collaborative Training of Acoustic Encoders for Speech Recognition
On-device speech recognition requires training models of different sizes for deploying on devices with various computational budgets.
Vision Transformers with Patch Diversification
To alleviate this problem, in this work, we introduce novel loss functions in vision transformer training to explicitly encourage diversity across patch representations for more discriminative feature extraction.
Ranked #15 on
Semantic Segmentation
on Cityscapes val
Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search
The key idea is to derive a smooth, differentiable approximation to the otherwise non-smooth, non-convex search space.
Feature-Align Network with Knowledge Distillation for Efficient Denoising
(2) A novel Feature Matching Loss that allows knowledge distillation from large denoising networks in the form of a perceptual content loss.
Memory-efficient Speech Recognition on Smart Devices
Recurrent transducer models have emerged as a promising solution for speech recognition on the current and next generation smart devices.
AlphaNet: Improved Training of Supernets with Alpha-Divergence
Weight-sharing NAS builds a supernet that assembles all the architectures as its sub-networks and jointly trains the supernet with the sub-networks.
Ranked #12 on
Neural Architecture Search
on ImageNet
CPT: Efficient Deep Neural Network Training via Cyclic Precision
In this paper, we attempt to explore low-precision training from a new perspective as inspired by recent findings in understanding DNN training: we conjecture that DNNs' precision might have a similar effect as the learning rate during DNN training, and advocate dynamic precision along the training trajectory for further boosting the time/energy efficiency of DNN training.
ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition
We use ScaleNAS to create high-resolution models for two different tasks, ScaleNet-P for human pose estimation and ScaleNet-S for semantic segmentation.
Ranked #5 on
Multi-Person Pose Estimation
on COCO test-dev
Can Temporal Information Help with Contrastive Self-Supervised Learning?
To this end, we present Temporal-aware Contrastive self-supervised learningTaCo, as a general paradigm to enhance video CSL.
KeepAugment: A Simple Information-Preserving Data Augmentation Approach
Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems.
AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
Our discovered model family, AttentiveNAS models, achieves top-1 accuracy from 77. 3% to 80. 7% on ImageNet, and outperforms SOTA models, including BigNAS and Once-for-All networks.
Ranked #21 on
Neural Architecture Search
on ImageNet
DNA: Differentiable Network-Accelerator Co-Search
Powerful yet complex deep neural networks (DNNs) have fueled a booming demand for efficient DNN solutions to bring DNN-powered intelligence into numerous applications.
One Weight Bitwidth to Rule Them All
Weight quantization for deep ConvNets has shown promising results for applications such as image classification and semantic segmentation and is especially important for applications where memory storage is limited.
NASGEM: Neural Architecture Search via Graph Embedding Method
To preserve graph correlation information in encoding, we propose NASGEM which stands for Neural Architecture Search via Graph Embedding Method.
Improving Efficiency in Neural Network Accelerator Using Operands Hamming Distance optimization
Neural network accelerator is a key enabler for the on-device AI inference, for which energy efficiency is an important metric.
Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks
Neural Architecture Search (NAS) has demonstrated its power on various AI accelerating platforms such as Field Programmable Gate Arrays (FPGAs) and Graphic Processing Units (GPUs).
Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent
Designing energy-efficient networks is of critical importance for enabling state-of-the-art deep learning in mobile and edge settings where the computation and energy budgets are highly limited.
On the Pareto Efficiency of Quantized CNN
Weight Quantization for deep convolutional neural networks (CNNs) has shown promising results in compressing and accelerating CNN-powered applications such as semantic segmentation, gesture recognition, and scene understanding.
Heterogeneous Dataflow Accelerators for Multi-DNN Workloads
The results suggest that HDA is an alternative class of Pareto-optimal accelerators to RDA with strength in energy, which can be a better choice than RDAs depending on the use cases.
Distributed, Parallel, and Cluster Computing
Federated Learning with Non-IID Data
Experiments show that accuracy can be increased by 30% for the CIFAR-10 dataset with only 5% globally shared data.
CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs
Deep Neural Networks are becoming increasingly popular in always-on IoT edge devices performing data analytics right at the source, reducing latency as well as energy consumption for data communication.
Not All Ops Are Created Equal!
Efficient and compact neural network models are essential for enabling the deployment on mobile and embedded devices.
Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks
Compared to Stripes, BitFusion provides 2. 6x speedup and 3. 9x energy reduction at 45 nm node when BitFusion area and frequency are set to those of Stripes.
Hello Edge: Keyword Spotting on Microcontrollers
We train various neural network architectures for keyword spotting published in literature to compare their accuracy and memory/compute requirements.
Ranked #13 on
Keyword Spotting
on Google Speech Commands
PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training
Massive data exist among user local platforms that usually cannot support deep neural network (DNN) training due to computation and storage resource constraints.
Deep Convolutional Neural Network Inference with Floating-point Weights and Fixed-point Activations
To alleviate these problems to some extent, prior research utilize low precision fixed-point numbers to represent the CNN weights and activations.
