On GLM-130B and OPT-66B, our method even achieves the same level of accuracy at 2-bit quantization as their float ones.
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.
The deployment of 3D detectors strikes one of the major challenges in real-world self-driving scenarios.
Thus, how to design a neural network to efficiently use the computing ability and memory bandwidth of hardware is a critical problem.
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
However, the typical convolution ignores the radial symmetry of the BEV features and increases the difficulty of the detector optimization.
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
In this paper, we undertake a simple and effective approach that can be easily applied to both vision transformers and convolutional neural networks.
7 code implementations • 7 Sep 2022 • Chuyi Li, Lulu Li, Hongliang Jiang, Kaiheng Weng, Yifei Geng, Liang Li, Zaidan Ke, Qingyuan Li, Meng Cheng, Weiqiang Nie, Yiduo Li, Bo Zhang, Yufei Liang, Linyuan Zhou, Xiaoming Xu, Xiangxiang Chu, Xiaoming Wei, Xiaolin Wei
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
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.
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
The goal of this work is to establish a scalable pipeline for expanding an object detector towards novel/unseen categories, using zero manual annotations.
Neural architecture search (NAS) has been an active direction of automatic machine learning (Auto-ML), aiming to explore efficient network structures.
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
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.
Recent unsupervised contrastive representation learning follows a Single Instance Multi-view (SIM) paradigm where positive pairs are usually constructed with intra-image data augmentation.
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.
Smart audio devices are gated by an always-on lightweight keyword spotting program to reduce power consumption.
We call this approach DARTS-.
Ranked #19 on Neural Architecture Search on NAS-Bench-201, CIFAR-10
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
Convolutional neural networks are widely adopted in Acoustic Scene Classification (ASC) tasks, but they generally carry a heavy computational burden.
Differentiable Architecture Search (DARTS) is now a widely disseminated weight-sharing neural architecture search method.
Ranked #24 on Neural Architecture Search on CIFAR-10
To discover powerful yet compact models is an important goal of neural architecture search.
Ranked #76 on Neural Architecture Search on ImageNet
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
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)
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.
Deep convolutional neural networks demonstrate impressive results in the super-resolution domain.
Ranked #15 on Image Super-Resolution on BSD100 - 2x upscaling
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.
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
Deep reinforcement learning for multi-agent cooperation and competition has been a hot topic recently.