20 citations · 79 across the 25 of their papers we have counts for
25 papers
Sequential Token Merging: Revisiting Hidden States
Yan Wen, Peng Ye, Lin Zhang +4
Vision Mambas (ViMs) achieve remarkable success with sub-quadratic complexity, but their efficiency remains constrained by quadratic token scaling with image resolution. While exis…
DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models
Yongqi Huang, Peng Ye, Chenyu Huang +5
Upcycled Mixture-of-Experts (MoE) models have shown great potential in various tasks by converting the original Feed-Forward Network (FFN) layers in pre-trained dense models into M…
Enhanced Sparsification via Stimulative Training
Shengji Tang, Weihao Lin, Hancheng Ye +4
Sparsification-based pruning has been an important category in model compression. Existing methods commonly set sparsity-inducing penalty terms to suppress the importance of droppe…
Efficient Architecture Search via Bi-level Data Pruning
Chongjun Tu, Peng Ye, Weihao Lin +5
Improving the efficiency of Neural Architecture Search (NAS) is a challenging but significant task that has received much attention. Previous works mainly adopted the Differentiabl…
BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-task Dense Predictions
Jingdong Zhang, Jiayuan Fan, Peng Ye +5
Multi-task dense prediction aims at handling multiple pixel-wise prediction tasks within a unified network simultaneously for visual scene understanding. However, cross-task featur…
Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors
Yancheng Cai, Bo Zhang, Baopu Li +4
Cross-domain pedestrian detection aims to generalize pedestrian detectors from one label-rich domain to another label-scarce domain, which is crucial for various real-world applica…
Boosting Residual Networks with Group Knowledge
Shengji Tang, Peng Ye, Baopu Li +5
Recent research understands the residual networks from a new perspective of the implicit ensemble model. From this view, previous methods such as stochastic depth and stimulative t…
Stimulative Training++: Go Beyond The Performance Limits of Residual Networks
Peng Ye, Tong He, Shengji Tang +4
Residual networks have shown great success and become indispensable in recent deep neural network models. In this work, we aim to re-investigate the training process of residual ne…
Multi-view Vision-Prompt Fusion Network: Can 2D Pre-trained Model Boost 3D Point Cloud Data-scarce Learning?
Haoyang Peng, Baopu Li, Bo Zhang +3
Point cloud based 3D deep model has wide applications in many applications such as autonomous driving, house robot, and so on. Inspired by the recent prompt learning in natural lan…
-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search
Peng Ye, Tong He, Baopu Li +3
Neural Architecture Search has attracted increasing attention in recent years. Among them, differential NAS approaches such as DARTS, have gained popularity for the search efficien…
Instance-aware Model Ensemble With Distillation For Unsupervised Domain Adaptation
Weimin Wu, Jiayuan Fan, Tao Chen +3
The linear ensemble based strategy, i.e., averaging ensemble, has been proposed to improve the performance in unsupervised domain adaptation tasks. However, a typical UDA task is u…
Stimulative Training of Residual Networks: A Social Psychology Perspective of Loafing
Peng Ye, Shengji Tang, Baopu Li +2
Residual networks have shown great success and become indispensable in today's deep models. In this work, we aim to re-investigate the training process of residual networks from a…
ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design
Haoran You, Zhanyi Sun, Huihong Shi +6
Vision Transformers (ViTs) have achieved state-of-the-art performance on various vision tasks. However, ViTs' self-attention module is still arguably a major bottleneck, limiting t…
Effective Invertible Arbitrary Image Rescaling
Zhihong Pan, Baopu Li, Dongliang He +2
Great successes have been achieved using deep learning techniques for image super-resolution (SR) with fixed scales. To increase its real world applicability, numerous models have…
Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation
Peng Ye, Baopu Li, Tao Chen +6
Semantic segmentation is a popular research topic in computer vision, and many efforts have been made on it with impressive results. In this paper, we intend to search an optimal n…
Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification
Bo Zhang, Jiakang Yuan, Baopu Li +3
Few-shot fine-grained learning aims to classify a query image into one of a set of support categories with fine-grained differences. Although learning different objects' local diff…
SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning
Haoran You, Baopu Li, Zhanyi Sun +2
Neural architecture search (NAS) has demonstrated amazing success in searching for efficient deep neural networks (DNNs) from a given supernet. In parallel, the lottery ticket hypo…
ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks
Haoran You, Baopu Li, Huihong Shi +2
Neural networks (NNs) with intensive multiplications (e.g., convolutions and transformers) are capable yet power hungry, impeding their more extensive deployment into resource-cons…
Towards Robust Adaptive Object Detection under Noisy Annotations
Xinyu Liu, Wuyang Li, Qiushi Yang +2
Domain Adaptive Object Detection (DAOD) models a joint distribution of images and labels from an annotated source domain and learns a domain-invariant transformation to estimate th…
Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence
Zhihong Pan, Baopu Li, Dongliang He +5
Deep learning based single image super-resolution models have been widely studied and superb results are achieved in upscaling low-resolution images with fixed scale factor and dow…
-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
Peng Ye, Baopu Li, Yikang Li +3
Neural Architecture Search~(NAS) has attracted increasingly more attention in recent years because of its capability to design deep neural networks automatically. Among them, diffe…
Exploring Gradient Flow Based Saliency for DNN Model Compression
Xinyu Liu, Baopu Li, Zhen Chen +1
Model pruning aims to reduce the deep neural network (DNN) model size or computational overhead. Traditional model pruning methods such as l-1 pruning that evaluates the channel si…
Learning-based Fast Path Planning in Complex Environments
Jianbang Liu, Baopu Li, Tingguang Li +3
In this paper, we present a novel path planning algorithm to achieve fast path planning in complex environments. Most existing path planning algorithms are difficult to quickly fin…
BN-NAS: Neural Architecture Search with Batch Normalization
Boyu Chen, Peixia Li, Baopu Li +5
We present BN-NAS, neural architecture search with Batch Normalization (BN-NAS), to accelerate neural architecture search (NAS). BN-NAS can significantly reduce the time required b…