Search Results for author: Fei Yang

Found 37 papers, 14 papers with code

Meta Distant Transfer Learning for Pre-trained Language Models

no code implementations EMNLP 2021 Chengyu Wang, Haojie Pan, Minghui Qiu, Jun Huang, Fei Yang, Yin Zhang

For tasks related to distant domains with different class label sets, PLMs may memorize non-transferable knowledge for the target domain and suffer from negative transfer.

Implicit Relations Meta-Learning +2

ScrollNet: Dynamic Weight Importance for Continual Learning

1 code implementation31 Aug 2023 Fei Yang, Kai Wang, Joost Van de Weijer

The importance of weights for each task can be determined either explicitly through learning a task-specific mask during training (e. g., parameter isolation-based approaches) or implicitly by introducing a regularization term (e. g., regularization-based approaches).

Continual Learning

Recognition of Mental Adjectives in An Efficient and Automatic Style

no code implementations16 Jul 2023 Fei Yang

We propose a new lexical inference task, Mental and Physical Classification (MPC), to handle commonsense reasoning in a reasoning graph.

Active Learning Sentiment Analysis

Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited

1 code implementation24 Mar 2023 Zheng Yuan, Fajie Yuan, Yu Song, Youhua Li, Junchen Fu, Fei Yang, Yunzhu Pan, Yongxin Ni

In fact, this question was answered ten years ago when IDRec beats MoRec by a strong margin in both recommendation accuracy and efficiency.

Recommendation Systems

Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation

1 code implementation22 Nov 2022 Marco Cotogni, Fei Yang, Claudio Cusano, Andrew D. Bagdanov, Joost Van de Weijer

Secondly, we propose a new method of feature drift compensation that accommodates feature drift in the backbone when learning new tasks.

Continual Learning

Attention Distillation: self-supervised vision transformer students need more guidance

1 code implementation3 Oct 2022 Kai Wang, Fei Yang, Joost Van de Weijer

In experiments on ImageNet-Subset and ImageNet-1K, we show that our method AttnDistill outperforms existing self-supervised knowledge distillation (SSKD) methods and achieves state-of-the-art k-NN accuracy compared with self-supervised learning (SSL) methods learning from scratch (with the ViT-S model).

Knowledge Distillation Self-Supervised Learning

SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision

no code implementations13 Jul 2022 Danna Xue, Fei Yang, Pei Wang, Luis Herranz, Jinqiu Sun, Yu Zhu, Yanning Zhang

Accurate semantic segmentation models typically require significant computational resources, inhibiting their use in practical applications.

Knowledge Distillation Semantic Segmentation

Free-form Lesion Synthesis Using a Partial Convolution Generative Adversarial Network for Enhanced Deep Learning Liver Tumor Segmentation

no code implementations18 Jun 2022 Yingao Liu, Fei Yang, Yidong Yang

The lesion synthesis framework was evaluated for lesion textures, and the synthetic lesions were used to train a lesion segmentation network to further validate the effectiveness of this framework.

Lesion Segmentation Tumor Segmentation

Exploring evolution-aware & -free protein language models as protein function predictors

1 code implementation14 Jun 2022 Mingyang Hu, Fajie Yuan, Kevin K. Yang, Fusong Ju, Jin Su, Hui Wang, Fei Yang, Qiuyang Ding

Large-scale Protein Language Models (PLMs) have improved performance in protein prediction tasks, ranging from 3D structure prediction to various function predictions.

Multiple Sequence Alignment

Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling

1 code implementation2 Jun 2022 Jian Hu, Haowen Zhong, Junchi Yan, Shaogang Gong, Guile Wu, Fei Yang

However, due to the significant imbalance between the amount of annotated data in the source and target domains, usually only the target distribution is aligned to the source domain, leading to adapting unnecessary source specific knowledge to the target domain, i. e., biased domain adaptation.

Domain Adaptation Pseudo Label +1

Slimmable Video Codec

no code implementations13 May 2022 Zhaocheng Liu, Luis Herranz, Fei Yang, Saiping Zhang, Shuai Wan, Marta Mrak, Marc Górriz Blanch

Neural video compression has emerged as a novel paradigm combining trainable multilayer neural networks and machine learning, achieving competitive rate-distortion (RD) performances, but still remaining impractical due to heavy neural architectures, with large memory and computational demands.

Video Compression

Towards Unified Prompt Tuning for Few-shot Text Classification

1 code implementation11 May 2022 Jianing Wang, Chengyu Wang, Fuli Luo, Chuanqi Tan, Minghui Qiu, Fei Yang, Qiuhui Shi, Songfang Huang, Ming Gao

Prompt-based fine-tuning has boosted the performance of Pre-trained Language Models (PLMs) on few-shot text classification by employing task-specific prompts.

Few-Shot Learning Few-Shot Text Classification +5

An effective coaxiality measurement for twist drill based on line structured light sensor

no code implementations18 Dec 2021 Ailing Cheng, Jiaojiao Ye, Fei Yang, Shufang Lu, Fei Gao

Aiming at the accurate and effective coaxiality measurement for twist drill with irregular surface, an optical measurement mechanism is proposed in this paper.

A Novel Framework for Image-to-image Translation and Image Compression

no code implementations25 Nov 2021 Fei Yang, Yaxing Wang, Luis Herranz, Yongmei Cheng, Mikhail Mozerov

Thus, we further propose a unified framework that allows both translation and autoencoding capabilities in a single codec.

Image Compression Image Restoration +4

OneFlow: Redesign the Distributed Deep Learning Framework from Scratch

1 code implementation28 Oct 2021 Jinhui Yuan, Xinqi Li, Cheng Cheng, Juncheng Liu, Ran Guo, Shenghang Cai, Chi Yao, Fei Yang, Xiaodong Yi, Chuan Wu, Haoran Zhang, Jie Zhao

Aiming at a simple, neat redesign of distributed deep learning frameworks for various parallelism paradigms, we present OneFlow, a novel distributed training framework based on an SBP (split, broadcast and partial-value) abstraction and the actor model.

Continuous Conditional Random Field Convolution for Point Cloud Segmentation

1 code implementation12 Oct 2021 Fei Yang, Franck Davoine, Huan Wang, Zhong Jin

Furthermore, we build an encoder-decoder network based on the proposed continuous CRF graph convolution (CRFConv), in which the CRFConv embedded in the decoding layers can restore the details of high-level features that were lost in the encoding stage to enhance the location ability of the network, thereby benefiting segmentation.

Image Segmentation Point Cloud Segmentation +1

CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation

1 code implementation13 Sep 2021 Yunfan Shao, Zhichao Geng, Yitao Liu, Junqi Dai, Hang Yan, Fei Yang, Li Zhe, Hujun Bao, Xipeng Qiu

In this paper, we take the advantage of previous pre-trained models (PTMs) and propose a novel Chinese Pre-trained Unbalanced Transformer (CPT).

Denoising Language Modelling +3

3D Shapes Local Geometry Codes Learning with SDF

no code implementations19 Aug 2021 Shun Yao, Fei Yang, Yongmei Cheng, Mikhail G. Mozerov

We propose Local Geometry Code Learning (LGCL), a model that improves the original DeepSDF results by learning from a local shape geometry of the full 3D shape.

3D Shape Reconstruction

DANICE: Domain adaptation without forgetting in neural image compression

no code implementations19 Apr 2021 Sudeep Katakol, Luis Herranz, Fei Yang, Marta Mrak

Neural image compression (NIC) is a new coding paradigm where coding capabilities are captured by deep models learned from data.

Domain Adaptation Image Compression

Slimmable Compressive Autoencoders for Practical Neural Image Compression

1 code implementation CVPR 2021 Fei Yang, Luis Herranz, Yongmei Cheng, Mikhail G. Mozerov

Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance.

Image Compression

Representation, Analysis of Bayesian Refinement Approximation Network: A Survey

no code implementations27 Mar 2021 Ningbo Zhu, Fei Yang

In our modified U-Net model, the result of background subtraction from other models will be combined with the source image as input for learning the statistical distribution.


Learn to Predict Vertical Track Irregularity with Extremely Imbalanced Data

no code implementations5 Dec 2020 Yutao Chen, Yu Zhang, Fei Yang

Railway systems require regular manual maintenance, a large part of which is dedicated to inspecting track deformation.

Ensemble Learning Time Series +1

Gaussian Constrained Attention Network for Scene Text Recognition

1 code implementation19 Oct 2020 Zhi Qiao, Xugong Qin, Yu Zhou, Fei Yang, Weiping Wang

In this paper, we propose Gaussian Constrained Attention Network to deal with this problem.

Scene Text Recognition

Two-Level Residual Distillation based Triple Network for Incremental Object Detection

no code implementations27 Jul 2020 Dongbao Yang, Yu Zhou, Dayan Wu, Can Ma, Fei Yang, Weiping Wang

Modern object detection methods based on convolutional neural network suffer from severe catastrophic forgetting in learning new classes without original data.

Incremental Learning object-detection +2

Self-Training for Domain Adaptive Scene Text Detection

no code implementations23 May 2020 Yudi Chen, Wei Wang, Yu Zhou, Fei Yang, Dongbao Yang, Weiping Wang

To address this problem, we propose a self-training framework to automatically mine hard examples with pseudo-labels from unannotated videos or images.

Image to Video Generation Scene Text Detection +1

Variable Rate Deep Image Compression with Modulated Autoencoder

1 code implementation11 Dec 2019 Fei Yang, Luis Herranz, Joost Van de Weijer, José A. Iglesias Guitián, Antonio López, Mikhail Mozerov

Addressing these limitations, we formulate the problem of variable rate-distortion optimization for deep image compression, and propose modulated autoencoders (MAEs), where the representations of a shared autoencoder are adapted to the specific rate-distortion tradeoff via a modulation network.

Image Compression Navigate +1

Sparse data interpolation using the geodesic distance affinity space

no code implementations6 May 2019 Mikhail G. Mozerov, Fei Yang, Joost Van de Weijer

In this paper, we adapt the geodesic distance-based recursive filter to the sparse data interpolation problem.

Optical Flow Estimation

Quality Classified Image Analysis with Application to Face Detection and Recognition

no code implementations19 Jan 2018 Fei Yang, Qian Zhang, Miaohui Wang, Guoping Qiu

We will present experimental results to show that our quality classified framework can accurately classify images based on the type and severity of image degradations and can significantly boost the performances of state-of-the-art face detector and recognizer in dealing with image datasets containing mixed quality images.

Face Detection

Web Scale Photo Hash Clustering on A Single Machine

no code implementations CVPR 2015 Yunchao Gong, Marcin Pawlowski, Fei Yang, Louis Brandy, Lubomir Bourdev, Rob Fergus

In addition, we propose an online clustering method based on binary k-means that is capable of clustering large photo stream on a single machine, and show applications to spam detection and trending photo discovery.

Clustering Online Clustering +1

Deep Poselets for Human Detection

no code implementations2 Jul 2014 Lubomir Bourdev, Fei Yang, Rob Fergus

We train the poselet model on top of PDF features and combine them with object-level CNNs for detection and bounding box prediction.

Human Detection

Face Recognition via Globality-Locality Preserving Projections

no code implementations6 Nov 2013 Sheng Huang, Dan Yang, Fei Yang, Yongxin Ge, Xiaohong Zhang, Jiwen Lu

We present an improved Locality Preserving Projections (LPP) method, named Gloablity-Locality Preserving Projections (GLPP), to preserve both the global and local geometric structures of data.

Face Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.