Search Results for author:
Found 35 papers, 23 papers with code
Norm Tweaking: High-performance Low-bit Quantization of Large Language Models
On GLM-130B and OPT-66B, our method even achieves the same level of accuracy at 2-bit quantization as their float ones.
FPTQ: Fine-grained Post-Training Quantization for Large Language Models
In this study, we propose a novel W4A8 post-training quantization method for the available open-sourced LLMs, which combines the advantages of both two recipes.
FastPillars: A Deployment-friendly Pillar-based 3D Detector
The deployment of 3D detectors strikes one of the major challenges in real-world self-driving scenarios.
EfficientRep:An Efficient Repvgg-style ConvNets with Hardware-aware Neural Network Design
Thus, how to design a neural network to efficiently use the computing ability and memory bandwidth of hardware is a critical problem.
YOLOv6 v3.0: A Full-Scale Reloading
For a glimpse of performance, our YOLOv6-N hits 37. 5% AP on the COCO dataset at a throughput of 1187 FPS tested with an NVIDIA Tesla T4 GPU.
Ranked #1 on
Real-Time Object Detection
on COCO
Make RepVGG Greater Again: A Quantization-aware Approach
The tradeoff between performance and inference speed is critical for practical applications.
AeDet: Azimuth-invariant Multi-view 3D Object Detection
However, the typical convolution ignores the radial symmetry of the BEV features and increases the difficulty of the detector optimization.
SegViT: Semantic Segmentation with Plain Vision Transformers
We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit.
Ranked #4 on
Semantic Segmentation
on COCO-Stuff test
EAPruning: Evolutionary Pruning for Vision Transformers and CNNs
In this paper, we undertake a simple and effective approach that can be easily applied to both vision transformers and convolutional neural networks.
YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
The YOLO community has prospered overwhelmingly to enrich its use in a multitude of hardware platforms and abundant scenarios.
Ranked #15 on
Object Detection
on COCO-O
Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images
In this work, we tackle this challenging issue with a novel range view projection mechanism, and for the first time demonstrate the benefits of fusing multi-frame point clouds for a range-view based detector.
Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation
Text-based video segmentation aims to segment the target object in a video based on a describing sentence.
Ranked #10 on
Referring Expression Segmentation
on A2D Sentences
Optical Flow Estimation
Referring Expression Segmentation
+2
PromptDet: Towards Open-vocabulary Detection using Uncurated Images
The goal of this work is to establish a scalable pipeline for expanding an object detector towards novel/unseen categories, using zero manual annotations.
DAAS: Differentiable Architecture and Augmentation Policy Search
Neural architecture search (NAS) has been an active direction of automatic machine learning (Auto-ML), aiming to explore efficient network structures.
CCTrans: Simplifying and Improving Crowd Counting with Transformer
However, the transformer can model the global context easily.
Twins: Revisiting the Design of Spatial Attention in Vision Transformers
Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks.
Ranked #48 on
Semantic Segmentation
on ADE20K val
Conditional Positional Encodings for Vision Transformers
Built on PEG, we present Conditional Position encoding Vision Transformer (CPVT).
A Strong On-Policy Competitor To PPO
As a recognized variant and improvement for Trust Region Policy Optimization (TRPO), proximal policy optimization (PPO) has been widely used with several advantages: efficient data utilization, easy implementation and good parallelism.
A Unified Mixture-View Framework for Unsupervised Representation Learning
Recent unsupervised contrastive representation learning follows a Single Instance Multi-view (SIM) paradigm where positive pairs are usually constructed with intra-image data augmentation.
ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation
Albeit being a prevalent architecture searching approach, differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet resides in the memory.
AutoKWS: Keyword Spotting with Differentiable Architecture Search
Smart audio devices are gated by an always-on lightweight keyword spotting program to reduce power consumption.
DARTS-: Robustly Stepping out of Performance Collapse Without Indicators
We call this approach DARTS-.
Ranked #19 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-10
Noisy Differentiable Architecture Search
However, it largely suffers from the well-known performance collapse issue due to the aggregation of skip connections.
Ranked #12 on
Neural Architecture Search
on CIFAR-10
MixPath: A Unified Approach for One-shot Neural Architecture Search
However, current two-stage neural architecture search methods are mainly limited to single-path search spaces.
Neural Architecture Search on Acoustic Scene Classification
Convolutional neural networks are widely adopted in Acoustic Scene Classification (ASC) tasks, but they generally carry a heavy computational burden.
Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search
Differentiable Architecture Search (DARTS) is now a widely disseminated weight-sharing neural architecture search method.
Ranked #24 on
Neural Architecture Search
on CIFAR-10
SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search
To discover powerful yet compact models is an important goal of neural architecture search.
Ranked #76 on
Neural Architecture Search
on ImageNet
MoGA: Searching Beyond MobileNetV3
Bearing the target hardware in mind, we propose the first Mobile GPU-Aware (MoGA) neural architecture search in order to be precisely tailored for real-world applications.
Ranked #811 on
Image Classification
on ImageNet
FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search
We demonstrate that this is crucial for improving the confidence of models' ranking.
Ranked #3 on
Neural Architecture Search
on CIFAR-10
(using extra training data)
A Matrix-in-matrix Neural Network for Image Super Resolution
In recent years, deep learning methods have achieved impressive results with higher peak signal-to-noise ratio in single image super-resolution (SISR) tasks by utilizing deeper layers.
Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search
Deep convolutional neural networks demonstrate impressive results in the super-resolution domain.
Ranked #15 on
Image Super-Resolution
on BSD100 - 2x upscaling
Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search
In this paper, we present a new multi-objective oriented algorithm called MoreMNAS (Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search) by leveraging good virtues from both EA and RL.
Improved Crowding Distance for NSGA-II
Non-dominated sorting genetic algorithm II (NSGA-II) does well in dealing with multi-objective problems.
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
As the most successful variant and improvement for Trust Region Policy Optimization (TRPO), proximal policy optimization (PPO) has been widely applied across various domains with several advantages: efficient data utilization, easy implementation, and good parallelism.
Ranked #1 on
MuJoCo Games
on Swimmer
Parameter Sharing Deep Deterministic Policy Gradient for Cooperative Multi-agent Reinforcement Learning
Deep reinforcement learning for multi-agent cooperation and competition has been a hot topic recently.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
