83 citations · 305 across the 33 of their papers we have counts for
34 papers
Accelerating Diffusion Models with One-to-Many Knowledge Distillation
Linfeng Zhang, Kaisheng Ma
Significant advancements in image generation have been made with diffusion models. Nevertheless, when contrasted with previous generative models, diffusion models face substantial…
VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation
Zekun Qi, Muzhou Yu, Runpei Dong +1
Conditional 3D generation is undergoing a significant advancement, enabling the free creation of 3D content from inputs such as text or 2D images. However, previous approaches have…
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast
Guofan Fan, Zekun Qi, Wenkai Shi +1
Geometry and color information provided by the point clouds are both crucial for 3D scene understanding. Two pieces of information characterize the different aspects of point cloud…
Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Study
Muzhou Yu, Linfeng Zhang, Kaisheng Ma
The excellent performance of deep neural networks is usually accompanied by a large number of parameters and computations, which have limited their usage on the resource-limited ed…
CORSD: Class-Oriented Relational Self Distillation
Muzhou Yu, Sia Huat Tan, Kailu Wu +3
Knowledge distillation conducts an effective model compression method while holding some limitations:(1) the feature based distillation methods only focus on distilling the feature…
CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP
Junbo Zhang, Runpei Dong, Kaisheng Ma
Training a 3D scene understanding model requires complicated human annotations, which are laborious to collect and result in a model only encoding close-set object semantics. In co…
Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs
Yu Duan, Zhongfan Jia, Qian Li +2
Rapidly learning from ongoing experiences and remembering past events with a flexible memory system are two core capacities of biological intelligence. While the underlying neural…
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
Zekun Qi, Runpei Dong, Guofan Fan +4
Mainstream 3D representation learning approaches are built upon contrastive or generative modeling pretext tasks, where great improvements in performance on various downstream task…
Language-Assisted 3D Feature Learning for Semantic Scene Understanding
Junbo Zhang, Guofan Fan, Guanghan Wang +3
Learning descriptive 3D features is crucial for understanding 3D scenes with diverse objects and complex structures. However, it is usually unknown whether important geometric attr…
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
Runpei Dong, Zekun Qi, Linfeng Zhang +5
The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natura…
Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Detection
Linfeng Zhang, Yukang Shi, Hung-Shuo Tai +4
Detecting 3D objects from multi-view images is a fundamental problem in 3D computer vision. Recently, significant breakthrough has been made in multi-view 3D detection tasks. Howev…
LW-ISP: A Lightweight Model with ISP and Deep Learning
Hongyang Chen, Kaisheng Ma
The deep learning (DL)-based methods of low-level tasks have many advantages over the traditional camera in terms of hardware prospects, error accumulation and imaging effects. Rec…
Contrastive Deep Supervision
Linfeng Zhang, Xin Chen, Junbo Zhang +2
The success of deep learning is usually accompanied by the growth in neural network depth. However, the traditional training method only supervises the neural network at its last l…
Rethinking the Augmentation Module in Contrastive Learning: Learning Hierarchical Augmentation Invariance with Expanded Views
Junbo Zhang, Kaisheng Ma
A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the pre…
Region-aware Knowledge Distillation for Efficient Image-to-Image Translation
Linfeng Zhang, Xin Chen, Runpei Dong +1
Recent progress in image-to-image translation has witnessed the success of generative adversarial networks (GANs). However, GANs usually contain a huge number of parameters, which…
PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection
Linfeng Zhang, Runpei Dong, Hung-Shuo Tai +1
The remarkable breakthroughs in point cloud representation learning have boosted their usage in real-world applications such as self-driving cars and virtual reality. However, thes…
Unsupervised Deep Learning Meets Chan-Vese Model
Dihan Zheng, Chenglong Bao, Zuoqiang Shi +2
The Chan-Vese (CV) model is a classic region-based method in image segmentation. However, its piecewise constant assumption does not always hold for practical applications. Many im…
Learn from Unpaired Data for Image Restoration: A Variational Bayes Approach
Dihan Zheng, Xiaowen Zhang, Kaisheng Ma +1
Collecting paired training data is difficult in practice, but the unpaired samples broadly exist. Current approaches aim at generating synthesized training data from unpaired sampl…
Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation
Linfeng Zhang, Xin Chen, Xiaobing Tu +3
Remarkable achievements have been attained with Generative Adversarial Networks (GANs) in image-to-image translation. However, due to a tremendous amount of parameters, state-of-th…
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks
Runpei Dong, Zhanhong Tan, Mengdi Wu +2
Quantized neural networks typically require smaller memory footprints and lower computation complexity, which is crucial for efficient deployment. However, quantization inevitably…
AFEC: Active Forgetting of Negative Transfer in Continual Learning
Liyuan Wang, Mingtian Zhang, Zhongfan Jia +5
Continual learning aims to learn a sequence of tasks from dynamic data distributions. Without accessing to the old training samples, knowledge transfer from the old tasks to each n…
Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention
Sia Huat Tan, Runpei Dong, Kaisheng Ma
Most feedforward convolutional neural networks spend roughly the same efforts for each pixel. Yet human visual recognition is an interaction between eye movements and spatial atten…
PCNN: Pattern-based Fine-Grained Regular Pruning towards Optimizing CNN Accelerators
Zhanhong Tan, Jiebo Song, Xiaolong Ma +8
Weight pruning is a powerful technique to realize model compression. We propose PCNN, a fine-grained regular 1D pruning method. A novel index format called Sparsity Pattern Mask (S…
An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices
Xiaolong Ma, Wei Niu, Tianyun Zhang +8
Weight pruning has been widely acknowledged as a straightforward and effective method to eliminate redundancy in Deep Neural Networks (DNN), thereby achieving acceleration on vario…