Search Results for author:
Found 17 papers, 8 papers with code
SySMOL: A Hardware-software Co-design Framework for Ultra-Low and Fine-Grained Mixed-Precision Neural Networks
The design for mixed-precision networks that achieves optimized tradeoffs corresponds to an architecture that supports 1, 2, and 4-bit fixed-point operations with four configurable precision patterns, when coupled with system-aware training and inference optimization -- networks trained for this design achieve accuracies that closely match full-precision accuracies, while compressing and improving run-time efficiency of the neural networks drastically by 10-20x, compared to full-precision networks.
YFlows: Systematic Dataflow Exploration and Code Generation for Efficient Neural Network Inference using SIMD Architectures on CPUs
Our results demonstrate that the dataflow that keeps outputs in SIMD registers while also maximizing both input and weight reuse consistently yields the best performance for a wide variety of inference workloads, achieving up to 3x speedup for 8-bit neural networks, and up to 4. 8x speedup for binary neural networks, respectively, over the optimized implementations of neural networks today.
Representation Disparity-aware Distillation for 3D Object Detection
In this paper, we focus on developing knowledge distillation (KD) for compact 3D detectors.
DCP-NAS: Discrepant Child-Parent Neural Architecture Search for 1-bit CNNs
One natural approach is to use 1-bit CNNs to reduce the computation and memory cost of NAS by taking advantage of the strengths of each in a unified framework, while searching the 1-bit CNNs is more challenging due to the more complicated processes involved.
Bi-ViT: Pushing the Limit of Vision Transformer Quantization
Vision transformers (ViTs) quantization offers a promising prospect to facilitate deploying large pre-trained networks on resource-limited devices.
Q-DETR: An Efficient Low-Bit Quantized Detection Transformer
At the upper level, we introduce a new foreground-aware query matching scheme to effectively transfer the teacher information to distillation-desired features to minimize the conditional information entropy.
Implicit Diffusion Models for Continuous Super-Resolution
IDM integrates an implicit neural representation and a denoising diffusion model in a unified end-to-end framework, where the implicit neural representation is adopted in the decoding process to learn continuous-resolution representation.
Ranked #1 on
Image Super-Resolution
on CelebA-HQ 128x128
Confidence-driven Bounding Box Localization for Small Object Detection
C-BBL quantizes continuous labels into grids and formulates two-hot ground truth labels.
A Text-guided Protein Design Framework
Current AI-assisted protein design mainly utilizes protein sequential and structural information.
Resilient Binary Neural Network
In this paper, we introduce a Resilient Binary Neural Network (ReBNN) to mitigate the frequent oscillation for better BNNs' training.
Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer
The large pre-trained vision transformers (ViTs) have demonstrated remarkable performance on various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices.
IDa-Det: An Information Discrepancy-aware Distillation for 1-bit Detectors
This explains why existing KD methods are less effective for 1-bit detectors, caused by a significant information discrepancy between the real-valued teacher and the 1-bit student.
Recurrent Bilinear Optimization for Binary Neural Networks
To address this issue, Recurrent Bilinear Optimization is proposed to improve the learning process of BNNs (RBONNs) by associating the intrinsic bilinear variables in the back propagation process.
TerViT: An Efficient Ternary Vision Transformer
Vision transformers (ViTs) have demonstrated great potential in various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices.
POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing
Real-time point cloud processing is fundamental for lots of computer vision tasks, while still challenged by the computational problem on resource-limited edge devices.
Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking
In this work, we present an end-to-end framework to settle data association in online Multiple-Object Tracking (MOT).
Two-Stream Multi-Task Network for Fashion Recognition
In this paper, we present a two-stream multi-task network for fashion recognition.
