Yifan Pu

Yifan Pu

Auto-generated profile, based on publicly available information

Yifan Pu

Department of Automation, Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 November 2022
Verified
Book Chapter
Closed access
PDF file
YHYizeng Han
Yizeng Han
YPYifan Pu
Yifan Pu
ZLZihang Lai
Zihang Lai
CWChaofei Wang
Chaofei Wang
SSShiji Song
Shiji Song
GHGao Huang
Gao Huang

25 April 2024 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
YPYifan Pu
Yifan Pu
YHYizeng Han
Yizeng Han
YWYulin Wang
Yulin Wang
JFJunlan Feng
Junlan Feng
CDChao Deng
Chao Deng
GHGao Huang
Gao Huang
Fine-grained image recognition is a longstanding computer vision challenge that focuses on differentiating objects belonging to multiple subordinate categories within the same meta-category. Since images belonging to the same meta-category usually share similar visual appearances, mining discriminative visual cues is the key to distinguishing fine-grained categories. Although commonly used image-level data augmentation techniques have achieved great success in generic image classification problems, they are rarely applied in fine-grained scenarios, because their random editing-region behavior is prone to destroy the discriminative visual cues residing in the subtle regions. In this paper, we propose diversifying the training data at the feature-level to alleviate the discriminative region loss problem. Specifically, we produce diversified augmented samples by translating image features along semantically meaningful directions. The semantic directions are estimated with a covariance prediction network, which predicts a sample-wise covariance matrix to adapt to the large intra-class variation inherent in fine-grained images. Furthermore, the covariance prediction network is jointly optimized with the classification network in a meta-learning manner to alleviate the degenerate solution problem. Experiments on four competitive fine-grained recognition benchmarks (CUB-200-2011, Stanford Cars, FGVC Aircrafts, NABirds) demonstrate that our method significantly improves the generalization performance on several popular classification networks (e.g., ResNets, DenseNets, EfficientNets, RegNets and ViT). Combined with a recently proposed method, our semantic data augmentation approach achieves state-of-the-art performance on the CUB-200-2011 dataset. Source code is available at https://github.com/LeapLabTHU/LearnableISDA .

25 April 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YHYizeng Han
Yizeng Han
ZLZeyu Liu
Zeyu Liu
ZYZhihang Yuan
Zhihang Yuan
YPYifan Pu
Yifan Pu
CWChaofei Wang
Chaofei Wang
GHGao Huang
Gao Huang
Dynamic computation has emerged as a promising strategy to improve the inference efficiency of deep networks. It allows selective activation of various computing units, such as layers or convolution channels, or adaptive allocation of computation to highly informative spatial regions in image features, thus significantly reducing unnecessary computations conditioned on each input sample. However, the practical efficiency of dynamic models does not always correspond to theoretical outcomes. This discrepancy stems from three key challenges: 1) The absence of a unified formulation for various dynamic inference paradigms, owing to the fragmented research landscape; 2) The undue emphasis on algorithm design while neglecting scheduling strategies , which are critical for optimizing computational performance and resource utilization in CUDA-enabled GPU settings; and 3) The cumbersome process of evaluating practical latency, as most existing libraries are tailored for static operators. To address these issues, we introduce Latency-Aware Unified Dynamic Networks (LAUDNet) , a comprehensive framework that amalgamates three cornerstone dynamic paradigms-spatially-adaptive computation, dynamic layer skipping, and dynamic channel skipping-under a unified formulation. To reconcile theoretical and practical efficiency, LAUDNet integrates algorithmic design with scheduling optimization, assisted by a latency predictor that accurately and efficiently gauges the inference latency of dynamic operators. This latency predictor harmonizes considerations of algorithms, scheduling strategies, and hardware attributes. We empirically validate various dynamic paradigms within the LAUDNet framework across a range of vision tasks, including image classification, object detection, and instance segmentation. Our experiments confirm that LAUDNet effectively narrows the gap between theoretical and real-world efficiency. For example, LAUDNet can reduce the practical latency of its static counterpart, ResNet-101, by over 50% on hardware platforms such as V100, RTX3090, and TX2 GPUs. Furthermore, LAUDNet surpasses competing methods in the trade-off between accuracy and efficiency. Code is available at: https://www.github.com/LeapLabTHU/LAUDNet .

22 November 2024
Verified
Book Chapter
Closed access
PDF file
JWJiangshan Wang
Jiangshan Wang
YPYifan Pu
Yifan Pu
YHYizeng Han
Yizeng Han
JGJiayi Guo
Jiayi Guo
YWYiru Wang
Yiru Wang
GHGao Huang
Gao Huang

22 November 2024
Verified
Book Chapter
Closed access
PDF file
YPYifan Pu
Yifan Pu
ZXZhuofan Xia
Zhuofan Xia
JGJiayi Guo
Jiayi Guo
DHDongchen Han
Dongchen Han
QLQixiu Li
Qixiu Li
XLXiu Li
Xiu Li

11 December 2024 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
YWYulin Wang
Yulin Wang
ZNZanlin Ni
Zanlin Ni
YPYifan Pu
Yifan Pu
CZCai Zhou
Cai Zhou
JYJixuan Ying
Jixuan Ying
GHGao Huang
Gao Huang