161 citations · 268 across the 13 of their papers we have counts for
15 papers
GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies
Ziye Wang, Li Kang, Yiran Qin +4
Recently, effective coordination in embodied multi-agent systems has remained a fundamental challenge, particularly in scenarios where agents must balance individual perspectives w…
Foundation Model is Efficient Multimodal Multitask Model Selector
Fanqing Meng, Wenqi Shao, Zhanglin Peng +4
This paper investigates an under-explored but important problem: given a collection of pre-trained neural networks, predicting their performance on each multi-modal task without fi…
Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification
Ziyi Tang, Ruimao Zhang, Zhanglin Peng +2
In recent years, the Transformer architecture has shown its superiority in the video-based person re-identification task. Inspired by video representation learning, these methods m…
Active Domain Adaptation with Multi-level Contrastive Units for Semantic Segmentation
Hao Zhang, Ruimao Zhang, Zhanglin Peng +2
To further reduce the cost of semi-supervised domain adaptation (SSDA) labeling, a more effective way is to use active learning (AL) to annotate a selected subset with specific pro…
AIM 2020 Challenge on Learned Image Signal Processing Pipeline
Andrey Ignatov, Radu Timofte, Zhilu Zhang +36
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world RAW-to…
Exemplar Normalization for Learning Deep Representation
Ruimao Zhang, Zhanglin Peng, Lingyun Wu +2
Normalization techniques are important in different advanced neural networks and different tasks. This work investigates a novel dynamic learning-to-normalize (L2N) problem by prop…
Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks
Zhaoyang Zhang, Jingyu Li, Wenqi Shao +4
Group convolution, which divides the channels of ConvNets into groups, has achieved impressive improvement over the regular convolution operation. However, existing models, eg. Res…
Switchable Normalization for Learning-to-Normalize Deep Representation
Ping Luo, Ruimao Zhang, Jiamin Ren +2
We address a learning-to-normalize problem by proposing Switchable Normalization (SN), which learns to select different normalizers for different normalization layers of a deep neu…
Do Normalization Layers in a Deep ConvNet Really Need to Be Distinct?
Ping Luo, Zhanglin Peng, Jiamin Ren +1
Yes, they do. This work investigates a perspective for deep learning: whether different normalization layers in a ConvNet require different normalizers. This is the first step towa…
Towards Understanding Regularization in Batch Normalization
Ping Luo, Xinjiang Wang, Wenqi Shao +1
Batch Normalization (BN) improves both convergence and generalization in training neural networks. This work understands these phenomena theoretically. We analyze BN by using a bas…
Differentiable Learning-to-Normalize via Switchable Normalization
Ping Luo, Jiamin Ren, Zhanglin Peng +2
We address a learning-to-normalize problem by proposing Switchable Normalization (SN), which learns to select different normalizers for different normalization layers of a deep neu…
Progressively Diffused Networks for Semantic Image Segmentation
Ruimao Zhang, Wei Yang, Zhanglin Peng +2
This paper introduces Progressively Diffused Networks (PDNs) for unifying multi-scale context modeling with deep feature learning, by taking semantic image segmentation as an exemp…
Geometric Scene Parsing with Hierarchical LSTM
Zhanglin Peng, Ruimao Zhang, Xiaodan Liang +2
This paper addresses the problem of geometric scene parsing, i.e. simultaneously labeling geometric surfaces (e.g. sky, ground and vertical plane) and determining the interaction r…
Deep Boosting: Joint Feature Selection and Analysis Dictionary Learning in Hierarchy
Zhanglin Peng, Ya Li, Zhaoquan Cai +1
This work investigates how the traditional image classification pipelines can be extended into a deep architecture, inspired by recent successes of deep neural networks. We propose…
Deep Boosting: Layered Feature Mining for General Image Classification
Zhanglin Peng, Liang Lin, Ruimao Zhang +1
Constructing effective representations is a critical but challenging problem in multimedia understanding. The traditional handcraft features often rely on domain knowledge, limitin…