1 code implementation • 4 Feb 2024 • Chao Li, Aojun Zhou, Anbang Yao
We observe that the head structures of mainstream DNNs adopt a similar feature encoding pipeline, exploiting global feature dependencies while disregarding local ones.
1 code implementation • 7 Dec 2023 • Jiawei Fan, Chao Li, Xiaolong Liu, Meina Song, Anbang Yao
In order to address this problem, we present Augmentation-free Dense Contrastive Knowledge Distillation (Af-DCD), a new contrastive distillation learning paradigm to train compact and accurate deep neural networks for semantic segmentation applications.
1 code implementation • 16 Aug 2023 • Chao Li, Anbang Yao
Dynamic convolution learns a linear mixture of $n$ static kernels weighted with their sample-dependent attentions, demonstrating superior performance compared to normal convolution.
1 code implementation • 15 Aug 2023 • Dongqi Cai, Yangyuxuan Kang, Anbang Yao, Yurong Chen
This paper presents Ske2Grid, a new representation learning framework for improved skeleton-based action recognition.
1 code implementation • 23 May 2023 • Xiaolong Liu, Lujun Li, Chao Li, Anbang Yao
By sequentially splitting the expanded student representation into N non-overlapping feature segments having the same number of feature channels as the teacher's, they can be readily forced to approximate the intact teacher representation simultaneously, formulating a novel many-to-one representation matching mechanism conditioned on a single teacher-student layer pair.
no code implementations • CVPR 2023 • Yikai Wang, Wenbing Huang, Yinpeng Dong, Fuchun Sun, Anbang Yao
Binary Neural Network (BNN) represents convolution weights with 1-bit values, which enhances the efficiency of storage and computation.
1 code implementation • 17 Feb 2023 • Yangyuxuan Kang, Yuyang Liu, Anbang Yao, Shandong Wang, Enhua Wu
Existing lifting networks for regressing 3D human poses from 2D single-view poses are typically constructed with linear layers based on graph-structured representation learning.
1 code implementation • ICLR 2022 • Chao Li, Aojun Zhou, Anbang Yao
Learning a single static convolutional kernel in each convolutional layer is the common training paradigm of modern Convolutional Neural Networks (CNNs).
1 code implementation • 20 Jul 2022 • Xiaoqi Li, Jiaming Liu, Shizun Wang, Cheng Lyu, Ming Lu, Yurong Chen, Anbang Yao, Yandong Guo, Shanghang Zhang
Our method significantly reduces the computational cost and achieves even better performance, paving the way for applying neural video delivery techniques to practical applications.
1 code implementation • NeurIPS 2021 • Dongqi Cai, Anbang Yao, Yurong Chen
In this paper, we present Dynamic Normalization and Relay (DNR), an improved normalization design, to augment the spatial-temporal representation learning of any deep action recognition model, adapting to small batch size training settings.
1 code implementation • ICCV 2021 • Yikai Wang, Yi Yang, Fuchun Sun, Anbang Yao
In the low-bit quantization field, training Binary Neural Networks (BNNs) is the extreme solution to ease the deployment of deep models on resource-constrained devices, having the lowest storage cost and significantly cheaper bit-wise operations compared to 32-bit floating-point counterparts.
1 code implementation • 11 Aug 2021 • Yikai Wang, Fuchun Sun, Ming Lu, Anbang Yao
We propose a compact and effective framework to fuse multimodal features at multiple layers in a single network.
Ranked #42 on Semantic Segmentation on NYU Depth v2
no code implementations • 1 Jan 2021 • Lujun Li, Yikai Wang, Anbang Yao, Yi Qian, Xiao Zhou, Ke He
In this paper, we present Explicit Connection Distillation (ECD), a new KD framework, which addresses the knowledge distillation problem in a novel perspective of bridging dense intermediate feature connections between a student network and its corresponding teacher generated automatically in the training, achieving knowledge transfer goal via direct cross-network layer-to-layer gradients propagation, without need to define complex distillation losses and assume a pre-trained teacher model to be available.
no code implementations • 1 Jan 2021 • Zhaole Sun, Anbang Yao
Binary Weight Networks (BWNs) have significantly lower computational and memory costs compared to their full-precision counterparts.
no code implementations • 17 Oct 2020 • Yunchao Wei, Shuai Zheng, Ming-Ming Cheng, Hang Zhao, LiWei Wang, Errui Ding, Yi Yang, Antonio Torralba, Ting Liu, Guolei Sun, Wenguan Wang, Luc van Gool, Wonho Bae, Junhyug Noh, Jinhwan Seo, Gunhee Kim, Hao Zhao, Ming Lu, Anbang Yao, Yiwen Guo, Yurong Chen, Li Zhang, Chuangchuang Tan, Tao Ruan, Guanghua Gu, Shikui Wei, Yao Zhao, Mariia Dobko, Ostap Viniavskyi, Oles Dobosevych, Zhendong Wang, Zhenyuan Chen, Chen Gong, Huanqing Yan, Jun He
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
1 code implementation • ECCV 2020 • Anbang Yao, Dawei Sun
Knowledge Distillation (KD) based methods adopt the one-way Knowledge Transfer (KT) scheme in which training a lower-capacity student network is guided by a pre-trained high-capacity teacher network.
1 code implementation • ECCV 2020 • Yikai Wang, Fuchun Sun, Duo Li, Anbang Yao
We propose a general method to train a single convolutional neural network which is capable of switching image resolutions at inference.
no code implementations • 17 Jul 2020 • Xiaolong Liu, Yuqing Hou, Anbang Yao, Yurong Chen, Keqiang Li
Given the insight that pixels belonging to one instance have one or more common attributes of current instance, we bring up an one-stage instance segmentation network named Common Attribute Support Network (CASNet), which realizes instance segmentation by predicting and clustering common attributes.
1 code implementation • ECCV 2020 • Duo Li, Anbang Yao, Qifeng Chen
Despite their strong modeling capacities, Convolutional Neural Networks (CNNs) are often scale-sensitive.
1 code implementation • ECCV 2020 • Duo Li, Anbang Yao, Qifeng Chen
To achieve efficient and flexible image classification at runtime, we employ meta learners to generate convolutional weights of main networks for various input scales and maintain privatized Batch Normalization layers per scale.
1 code implementation • ICCV 2019 • Jiahui Zhang, Dawei Sun, Zixin Luo, Anbang Yao, Lei Zhou, Tianwei Shen, Yurong Chen, Long Quan, Hongen Liao
First, to capture the local context of sparse correspondences, the network clusters unordered input correspondences by learning a soft assignment matrix.
1 code implementation • ICCV 2019 • Duo Li, Aojun Zhou, Anbang Yao
MobileNets, a class of top-performing convolutional neural network architectures in terms of accuracy and efficiency trade-off, are increasingly used in many resourceaware vision applications.
1 code implementation • ECCV 2018 • Jiahui Zhang, Hao Zhao, Anbang Yao, Yurong Chen, Li Zhang, Hongen Liao
We introduce Spatial Group Convolution (SGC) for accelerating the computation of 3D dense prediction tasks.
Ranked #9 on 3D Semantic Scene Completion on SemanticKITTI
1 code implementation • CVPR 2019 • Dawei Sun, Anbang Yao, Aojun Zhou, Hao Zhao
Convolutional Neural Networks (CNNs) have become deeper and more complicated compared with the pioneering AlexNet.
3 code implementations • ICCV 2019 • Ming Lu, Hao Zhao, Anbang Yao, Yurong Chen, Feng Xu, Li Zhang
Although plenty of methods have been proposed, a theoretical analysis of feature transform is still missing.
no code implementations • 27 Sep 2018 • Kuan Wang, Hao Zhao, Anbang Yao, Aojun Zhou, Dawei Sun, Yurong Chen
During the training phase, we generate binary weights on-the-fly since what we actually maintain is the policy network, and all the binary weights are used in a burn-after-reading style.
no code implementations • CVPR 2018 • Aojun Zhou, Anbang Yao, Kuan Wang, Yurong Chen
Through explicitly regularizing the loss perturbation and the weight approximation error in an incremental way, we show that such a new optimization method is theoretically reasonable and practically effective.
no code implementations • ICCV 2017 • Ming Lu, Hao Zhao, Anbang Yao, Feng Xu, Yurong Chen, Li Zhang
Our method decomposes the semantic style transfer problem into feature reconstruction part and feature decoder part.
1 code implementation • CVPR 2017 • Tao Kong, Fuchun Sun, Anbang Yao, Huaping Liu, Ming Lu, Yurong Chen
To address (a), we design the reverse connection, which enables the network to detect objects on multi-levels of CNNs.
no code implementations • CVPR 2017 • Hao Zhao, Ming Lu, Anbang Yao, Yiwen Guo, Yurong Chen, Li Zhang
In this paper, we propose an alternative method to estimate room layouts of cluttered indoor scenes.
no code implementations • CVPR 2017 • Yiwen Guo, Anbang Yao, Hao Zhao, Yurong Chen
Convolutional neural networks (CNNs) with deep architectures have substantially advanced the state-of-the-art in computer vision tasks.
3 code implementations • 10 Feb 2017 • Aojun Zhou, Anbang Yao, Yiwen Guo, Lin Xu, Yurong Chen
The weights in the other group are responsible to compensate for the accuracy loss from the quantization, thus they are the ones to be re-trained.
3 code implementations • NeurIPS 2016 • Yiwen Guo, Anbang Yao, Yurong Chen
In this paper, we propose a novel network compression method called dynamic network surgery, which can remarkably reduce the network complexity by making on-the-fly connection pruning.
no code implementations • CVPR 2016 • Tao Kong, Anbang Yao, Yurong Chen, Fuchun Sun
Almost all of the current top-performing object detection networks employ region proposals to guide the search for object instances.