Search Results for author: Yi Jin

Found 33 papers, 11 papers with code

Seed Optimization with Frozen Generator for Superior Zero-shot Low-light Enhancement

no code implementations15 Feb 2024 Yuxuan Gu, Yi Jin, Ben Wang, Zhixiang Wei, Xiaoxiao Ma, Pengyang Ling, Haoxuan Wang, Huaian Chen, Enhong Chen

In this work, we observe that the generators, which are pre-trained on massive natural images, inherently hold the promising potential for superior low-light image enhancement against varying scenarios. Specifically, we embed a pre-trained generator to Retinex model to produce reflectance maps with enhanced detail and vividness, thereby recovering features degraded by low-light conditions. Taking one step further, we introduce a novel optimization strategy, which backpropagates the gradients to the input seeds rather than the parameters of the low-light enhancement model, thus intactly retaining the generative knowledge learned from natural images and achieving faster convergence speed.

Low-Light Image Enhancement

Masked Pre-trained Model Enables Universal Zero-shot Denoiser

1 code implementation26 Jan 2024 Xiaoxiao Ma, Zhixiang Wei, Yi Jin, Pengyang Ling, Tianle Liu, Ben Wang, Junkang Dai, Huaian Chen, Enhong Chen

In this work, we observe that the model, which is trained on vast general images using masking strategy, has been naturally embedded with the distribution knowledge regarding natural images, and thus spontaneously attains the underlying potential for strong image denoising.

Image Denoising

Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation

1 code implementation7 Dec 2023 Zhixiang Wei, Lin Chen, Yi Jin, Xiaoxiao Ma, Tianle Liu, Pengyang Ling, Ben Wang, Huaian Chen, Jinjin Zheng

Driven by the motivation that Leveraging Stronger pre-trained models and Fewer trainable parameters for Superior generalizability, we introduce a robust fine-tuning approach, namely Rein, to parameter-efficiently harness VFMs for DGSS.

Domain Generalization +1

Transmission line condition prediction based on semi-supervised learning

no code implementations30 Oct 2023 Sizhe Li, Xun Ma, Nan Liu, Yi Jin

Transmission line state assessment and prediction are of great significance for the rational formulation of operation and maintenance strategy and improvement of operation and maintenance level.

Representation Learning

Disentangle then Parse:Night-time Semantic Segmentation with Illumination Disentanglement

1 code implementation18 Jul 2023 Zhixiang Wei, Lin Chen, Tao Tu, Huaian Chen, Pengyang Ling, Yi Jin

2) Based on the observation that the illumination component can serve as a cue for some semantically confused regions, we further introduce an Illumination-Aware Parser (IAParser) to explicitly learn the correlation between semantics and lighting, and aggregate the illumination features to yield more precise predictions.

Disentanglement Segmentation +1

Bridging the Gap: Multi-Level Cross-Modality Joint Alignment for Visible-Infrared Person Re-Identification

no code implementations17 Jul 2023 Tengfei Liang, Yi Jin, Wu Liu, Tao Wang, Songhe Feng, Yidong Li

Visible-Infrared person Re-IDentification (VI-ReID) is a challenging cross-modality image retrieval task that aims to match pedestrians' images across visible and infrared cameras.

Image Classification Image Retrieval +3

FreeDrag: Feature Dragging for Reliable Point-based Image Editing

1 code implementation10 Jul 2023 Pengyang Ling, Lin Chen, Pan Zhang, Huaian Chen, Yi Jin, Jinjin Zheng

To serve the intricate and varied demands of image editing, precise and flexible manipulation in image content is indispensable.

Point Tracking

NPS: A Framework for Accurate Program Sampling Using Graph Neural Network

no code implementations18 Apr 2023 Yuanwei Fang, Zihao Liu, Yanheng Lu, Jiawei Liu, Jiajie Li, Yi Jin, Jian Chen, Yenkuang Chen, Hongzhong Zheng, Yuan Xie

Furthermore, NPS shows higher accuracy and generality than the state-of-the-art GNN approach in code behavior learning, enabling the generation of high-quality execution embeddings.

The Cascaded Forward Algorithm for Neural Network Training

1 code implementation17 Mar 2023 Gongpei Zhao, Tao Wang, Yidong Li, Yi Jin, Congyan Lang, Haibin Ling

Backpropagation algorithm has been widely used as a mainstream learning procedure for neural networks in the past decade, and has played a significant role in the development of deep learning.

Image Classification

Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges

1 code implementation16 Jan 2023 Yushan Han, HUI ZHANG, Huifang Li, Yi Jin, Congyan Lang, Yidong Li

The former focuses on collaboration modules and efficiency, and the latter is devoted to addressing the problems in actual application.

Autonomous Driving

Disentangle then Parse: Night-time Semantic Segmentation with Illumination Disentanglement

1 code implementation ICCV 2023 Zhixiang Wei, Lin Chen, Tao Tu, Pengyang Ling, Huaian Chen, Yi Jin

2) Based on the observation that the illumination component can serve as a cue for some semantically confused regions, we further introduce an Illumination-Aware Parser (IAParser) to explicitly learn the correlation between semantics and lighting, and aggregate the illumination features to yield more precise predictions.

Disentanglement Segmentation +1

Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation

1 code implementation16 Sep 2022 Lin Chen, Zhixiang Wei, Xin Jin, Huaian Chen, Miao Zheng, Kai Chen, Yi Jin

In this work, we resort to data mixing to establish a deliberated domain bridging (DDB) for DASS, through which the joint distributions of source and target domains are aligned and interacted with each in the intermediate space.

Knowledge Distillation Semantic Segmentation +3

Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation

1 code implementation CVPR 2022 Lin Chen, Huaian Chen, Zhixiang Wei, Xin Jin, Xiao Tan, Yi Jin, Enhong Chen

Such NWD can be coupled with the classifier to serve as a discriminator satisfying the K-Lipschitz constraint without the requirements of additional weight clipping or gradient penalty strategy.

Unsupervised Domain Adaptation

Boundary Corrected Multi-scale Fusion Network for Real-time Semantic Segmentation

no code implementations1 Mar 2022 Tianjiao Jiang, Yi Jin, Tengfei Liang, Xu Wang, Yidong Li

Image semantic segmentation aims at the pixel-level classification of images, which has requirements for both accuracy and speed in practical application.

Real-Time Semantic Segmentation Scene Parsing +1

LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling

no code implementations13 Feb 2022 Xu Wang, Yi Jin, Yigang Cen, Tao Wang, Bowen Tang, Yidong Li

Compared with traditional task-irrelevant downsampling methods, task-oriented neural networks have shown improved performance in point cloud downsampling range.

2D+3D facial expression recognition via embedded tensor manifold regularization

no code implementations29 Jan 2022 Yunfang Fu, Qiuqi Ruan, Ziyan Luo, Gaoyun An, Yi Jin, Jun Wan

In this paper, a novel approach via embedded tensor manifold regularization for 2D+3D facial expression recognition (FERETMR) is proposed.

3D Facial Expression Recognition Dimensionality Reduction +1

Prototype Guided Network for Anomaly Segmentation

no code implementations15 Jan 2022 Yiqing Hao, Yi Jin, Gaoyun An

In the model, prototypes are used to model the hierarchical category semantic information and distinguish OOD pixels.

Segmentation Semantic Segmentation

GLAN: A Graph-based Linear Assignment Network

no code implementations5 Jan 2022 He Liu, Tao Wang, Congyan Lang, Songhe Feng, Yi Jin, Yidong Li

The experimental results on a synthetic dataset reveal that our method outperforms state-of-the-art baselines and achieves consistently high accuracy with the increment of the problem size.

Multi-Object Tracking

MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification

no code implementations21 Oct 2021 Yajun Gao, Tengfei Liang, Yi Jin, Xiaoyan Gu, Wu Liu, Yidong Li, Congyan Lang

The RGB-infrared cross-modality person re-identification (ReID) task aims to recognize the images of the same identity between the visible modality and the infrared modality.

Cross-Modality Person Re-identification Person Re-Identification

CMTR: Cross-modality Transformer for Visible-infrared Person Re-identification

no code implementations18 Oct 2021 Tengfei Liang, Yi Jin, Yajun Gao, Wu Liu, Songhe Feng, Tao Wang, Yidong Li

The existing convolutional neural network-based methods mainly face the problem of insufficient perception of modalities' information, and can not learn good discriminative modality-invariant embeddings for identities, which limits their performance.

Cross-Modality Person Re-identification Person Re-Identification

Joint Graph Learning and Matching for Semantic Feature Correspondence

2 code implementations1 Sep 2021 He Liu, Tao Wang, Yidong Li, Congyan Lang, Yi Jin, Haibin Ling

In this paper, we propose a joint \emph{graph learning and matching} network, named GLAM, to explore reliable graph structures for boosting graph matching.

Graph Learning Graph Matching

Time-Frequency Analysis based Deep Interference Classification for Frequency Hopping System

no code implementations21 Jul 2021 Changzhi Xu, Jingya Ren, Wanxin Yu, Yi Jin, Zhenxin Cao, Xiaogang Wu, Weiheng Jiang

Considering the possibility of presence multiple interferences in the frequency hopping system, in order to fully extract effective features of the interferences from the received signals, the linear and bilinear transform based composite time-frequency analysis method is adopted.

Classification Transfer Learning

Attention Models for Point Clouds in Deep Learning: A Survey

no code implementations22 Feb 2021 Xu Wang, Yi Jin, Yigang Cen, Tao Wang, Yidong Li

Recently, the advancement of 3D point clouds in deep learning has attracted intensive research in different application domains such as computer vision and robotic tasks.

3D Pose Estimation 3D Semantic Segmentation

FASG: Feature Aggregation Self-training GCN for Semi-supervised Node Classification

no code implementations1 Jan 2021 Gongpei Zhao, Tao Wang, Yidong Li, Yi Jin

Recently, Graph Convolutioal Networks (GCNs) have achieved significant success in many graph-based learning tasks, especially for node classification, due to its excellent ability in representation learning.

Classification General Classification +2

Cross-ethnicity Face Anti-spoofing Recognition Challenge: A Review

no code implementations23 Apr 2020 Ajian Liu, Xuan Li, Jun Wan, Sergio Escalera, Hugo Jair Escalante, Meysam Madadi, Yi Jin, Zhuoyuan Wu, Xiaogang Yu, Zichang Tan, Qi Yuan, Ruikun Yang, Benjia Zhou, Guodong Guo, Stan Z. Li

Although ethnic bias has been verified to severely affect the performance of face recognition systems, it still remains an open research problem in face anti-spoofing.

Face Anti-Spoofing Face Recognition

Time-Frequency Analysis based Blind Modulation Classification for Multiple-Antenna Systems

no code implementations1 Apr 2020 Weiheng Jiang, Xiaogang Wu, Bolin Chen, Wenjiang Feng, Yi Jin

Hence, in this paper, to resolve the problem of blind modulation classification in MIMO systems, the time-frequency analysis method based on the windowed short-time Fourier transform is used to analyse the time-frequency characteristics of time-domain modulated signals.

Classification General Classification +1

HERA: Partial Label Learning by Combining Heterogeneous Loss with Sparse and Low-Rank Regularization

no code implementations3 Jun 2019 Gengyu Lyu, Songhe Feng, Yi Jin, Guojun Dai, Congyan Lang, Yidong Li

Partial Label Learning (PLL) aims to learn from the data where each training instance is associated with a set of candidate labels, among which only one is correct.

Partial Label Learning

Domain Adaptive Attention Model for Unsupervised Cross-Domain Person Re-Identification

no code implementations25 May 2019 Yangru Huang, Peixi Peng, Yi Jin, Junliang Xing, Congyan Lang, Songhe Feng

To reduce domain divergence caused by that the source and target datasets are collected from different environments, we force to project the DSH feature maps from different domains to a new nominal domain, and a novel domain similarity loss is proposed based on one-class classification.

Domain Adaptation General Classification +2

Compositional Belief Update

no code implementations15 Jan 2014 James Delgrande, Yi Jin, Francis Jeffry Pelletier

We also explore other compositional belief change operators: erasure is developed as a dual operator to update; we show that a forget operator is definable in terms of update; and we give a definition of the compositional revision operator.

Sentence

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