619 citations · 1.3k across the 33 of their papers we have counts for
33 papers
ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations
Junke Wang, Xiao Wang, Jiacheng Pan +16
This paper introduces ARM, a discrete representation-based AutoRegressive Model that unifies image understanding, generation, and editing within a next-token prediction framework.…
Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
Yuchao Gu, Xintao Wang, Jay Zhangjie Wu +10
Public large-scale text-to-image diffusion models, such as Stable Diffusion, have gained significant attention from the community. These models can be easily customized for new con…
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation
Zitian Wang, Xuecheng Nie, Xiaochao Qu +2
In this paper, we present a novel Distribution-Aware Single-stage (DAS) model for tackling the challenging multi-person 3D pose estimation problem. Different from existing top-down…
SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations
Tao Wang, Jun Hao Liew, Yu Li +2
Recent state-of-the-art one-stage instance segmentation model SOLO divides the input image into a grid and directly predicts per grid cell object masks with fully-convolutional net…
Improved Pillar with Fine-grained Feature for 3D Object Detection
Jiahui Fu, Guanghui Ren, Yunpeng Chen +1
3D object detection with LiDAR point clouds plays an important role in autonomous driving perception module that requires high speed, stability and accuracy. However, the existing…
Dense Contrastive Visual-Linguistic Pretraining
Lei Shi, Kai Shuang, Shijie Geng +5
Inspired by the success of BERT, several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior p…
PnP-DETR: Towards Efficient Visual Analysis with Transformers
Tao Wang, Li Yuan, Yunpeng Chen +2
Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translatin…
Continual Learning via Bit-Level Information Preserving
Yujun Shi, Li Yuan, Yunpeng Chen +1
Continual learning tackles the setting of learning different tasks sequentially. Despite the lots of previous solutions, most of them still suffer significant forgetting or expensi…
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Li Yuan, Yunpeng Chen, Tao Wang +6
Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT mo…
ProxylessKD: Direct Knowledge Distillation with Inherited Classifier for Face Recognition
Weidong Shi, Guanghui Ren, Yunpeng Chen +1
Knowledge Distillation (KD) refers to transferring knowledge from a large model to a smaller one, which is widely used to enhance model performance in machine learning. It tries to…
NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
Yun-Chun Chen, Chen Gao, Esther Robb +1
Recent work has shown that the structure of deep convolutional neural networks can be used as a structured image prior for solving various inverse image restoration tasks. Instead…
ConvBERT: Improving BERT with Span-based Dynamic Convolution
Zihang Jiang, Weihao Yu, Daquan Zhou +3
Pre-trained language models like BERT and its variants have recently achieved impressive performance in various natural language understanding tasks. However, BERT heavily relies o…
Rethinking Bottleneck Structure for Efficient Mobile Network Design
Zhou Daquan, Qibin Hou, Yunpeng Chen +2
The inverted residual block is dominating architecture design for mobile networks recently. It changes the classic residual bottleneck by introducing two design rules: learning inv…
Adversarial Domain Adaptation with Prototype-Based Normalized Output Conditioner
Dapeng Hu, Jian Liang, Qibin Hou +2
In this work, we attempt to address unsupervised domain adaptation by devising simple and compact conditional domain adversarial training methods. We first revisit the simple conca…
Highly Efficient Salient Object Detection with 100K Parameters
Shang-Hua Gao, Yong-Qiang Tan, Ming-Ming Cheng +3
Salient object detection models often demand a considerable amount of computation cost to make precise prediction for each pixel, making them hardly applicable on low-power devices…
Efficient Differentiable Neural Architecture Search with Meta Kernels
Shoufa Chen, Yunpeng Chen, Shuicheng Yan +1
The searching procedure of neural architecture search (NAS) is notoriously time consuming and cost prohibitive.To make the search space continuous, most existing gradient-based NAS…
AdversarialNAS: Adversarial Neural Architecture Search for GANs
Chen Gao, Yunpeng Chen, Si Liu +2
Neural Architecture Search (NAS) that aims to automate the procedure of architecture design has achieved promising results in many computer vision fields. In this paper, we propose…
Hybrid Composition with IdleBlock: More Efficient Networks for Image Recognition
Bing Xu, Andrew Tulloch, Yunpeng Chen +2
We propose a new building block, IdleBlock, which naturally prunes connections within the block. To fully utilize the IdleBlock we break the tradition of monotonic design in state-…
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
Yunpeng Chen, Haoqi Fan, Bing Xu +5
In natural images, information is conveyed at different frequencies where higher frequencies are usually encoded with fine details and lower frequencies are usually encoded with gl…
Dynamic Feature Fusion for Semantic Edge Detection
Yuan Hu, Yunpeng Chen, Xiang Li +1
Features from multiple scales can greatly benefit the semantic edge detection task if they are well fused. However, the prevalent semantic edge detection methods apply a fixed weig…
Deep Reasoning with Multi-Scale Context for Salient Object Detection
Zun Li, Congyan Lang, Yunpeng Chen +2
To detect salient objects accurately, existing methods usually design complex backbone network architectures to learn and fuse powerful features. However, the saliency inference mo…
Graph-Based Global Reasoning Networks
Yunpeng Chen, Marcus Rohrbach, Zhicheng Yan +3
Globally modeling and reasoning over relations between regions can be beneficial for many computer vision tasks on both images and videos. Convolutional Neural Networks (CNNs) exce…
-Nets: Double Attention Networks
Yunpeng Chen, Yannis Kalantidis, Jianshu Li +2
Learning to capture long-range relations is fundamental to image/video recognition. Existing CNN models generally rely on increasing depth to model such relations which is highly i…
Multi-Fiber Networks for Video Recognition
Yunpeng Chen, Yannis Kalantidis, Jianshu Li +2
In this paper, we aim to reduce the computational cost of spatio-temporal deep neural networks, making them run as fast as their 2D counterparts while preserving state-of-the-art a…