Search Results for author: Xueming Qian

Found 34 papers, 13 papers with code

QueryCDR: Query-Based Controllable Distortion Rectification Network for Fisheye Images

1 code implementation18 Dec 2024 Pengbo Guo, Chengxu Liu, Xingsong Hou, Xueming Qian

We propose a novel Query-Based Controllable Distortion Rectification network for fisheye images (QueryCDR).

Neighborhood Commonality-aware Evolution Network for Continuous Generalized Category Discovery

no code implementations7 Dec 2024 Ye Wang, Yaxiong Wang, Guoshuai Zhao, Xueming Qian

Continuous Generalized Category Discovery (C-GCD) aims to continually discover novel classes from unlabelled image sets while maintaining performance on old classes.

Contrastive Learning Incremental Learning +2

Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery

1 code implementation26 Oct 2024 Yimin Deng, Yuxia Wu, Guoshuai Zhao, Li Zhu, Xueming Qian

To enable better knowledge transfer, we design a prototype learning method integrating the supervised and pseudo signals from IND and OOD samples.

Clustering Contrastive Learning +5

AdaDiffSR: Adaptive Region-aware Dynamic Acceleration Diffusion Model for Real-World Image Super-Resolution

no code implementations23 Oct 2024 Yuanting Fan, Chengxu Liu, Nengzhong Yin, Changlong Gao, Xueming Qian

Specifically, by introducing the multi-metrics latent entropy module (MMLE), we can achieve dynamic perception of the latent spatial information gain during the denoising process, thereby guiding the dynamic selection of the timesteps.

Denoising Image Super-Resolution +1

Knowledge Adaptation Network for Few-Shot Class-Incremental Learning

no code implementations18 Sep 2024 Ye Wang, Yaxiong Wang, Guoshuai Zhao, Xueming Qian

Few-shot class-incremental learning (FSCIL) aims to incrementally recognize new classes using a few samples while maintaining the performance on previously learned classes.

class-incremental learning Few-Shot Class-Incremental Learning +1

CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval

1 code implementation29 May 2024 Xintong Jiang, Yaxiong Wang, Mengjian Li, Yujiao Wu, Bingwen Hu, Xueming Qian

Firstly, we introduce the concept of text-bridged image alignment, where the query text serves as a bridge between the query image and the target image.

Cross-Modal Retrieval Image Retrieval +3

Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring

1 code implementation CVPR 2024 Chengxu Liu, Xuan Wang, Xiangyu Xu, Ruhao Tian, Shuai Li, Xueming Qian, Ming-Hsuan Yang

In particular, we use a motion estimation network to capture motion information from neighborhoods, thereby adaptively estimating spatially-variant motion flow, mask, kernels, weights, and offsets to obtain the MISC Filter.

Deblurring Motion Estimation

Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class Discovery

1 code implementation13 Apr 2024 Ye Wang, Yaxiong Wang, Yujiao Wu, Bingchen Zhao, Xueming Qian

To counteract this inefficiency, we opt to cluster only the unlabelled instances and subsequently expand the cluster prototypes with our introduced potential prototypes to fast explore novel classes.

Clustering Contrastive Learning

Decoupling Degradations with Recurrent Network for Video Restoration in Under-Display Camera

1 code implementation8 Mar 2024 Chengxu Liu, Xuan Wang, Yuanting Fan, Shuai Li, Xueming Qian

The pixel array of light-emitting diodes used for display diffracts and attenuates incident light, causing various degradations as the light intensity changes.

Image Restoration Video Restoration

Dual Relation Alignment for Composed Image Retrieval

no code implementations5 Sep 2023 Xintong Jiang, Yaxiong Wang, Yujiao Wu, Meng Wang, Xueming Qian

Unlike the general image-text retrieval problem with only one alignment relation, i. e., image-text, we argue for the existence of two types of relations in composed image retrieval.

Image Retrieval Image-text Retrieval +3

Dual Degradation-Inspired Deep Unfolding Network for Low-Light Image Enhancement

no code implementations5 Aug 2023 Huake Wang, Xingsong Hou, Chengcu Liu, Kaibing Zhang, Xiangyong Cao, Xueming Qian

Although low-light image enhancement has achieved great stride based on deep enhancement models, most of them mainly stress on enhancement performance via an elaborated black-box network and rarely explore the physical significance of enhancement models.

Low-Light Image Enhancement Specificity

Knowledge Transfer-Driven Few-Shot Class-Incremental Learning

1 code implementation19 Jun 2023 Ye Wang, Yaxiong Wang, Guoshuai Zhao, Xueming Qian

Concretely, RESA mimics the real incremental setting and constructs pseudo incremental tasks globally and locally, where the global pseudo incremental tasks are designed to coincide with the learning objective of FSCIL and the local pseudo incremental tasks are designed to improve the model's plasticity, respectively.

class-incremental learning Few-Shot Class-Incremental Learning +2

Logic Diffusion for Knowledge Graph Reasoning

no code implementations6 Jun 2023 Xiaoying Xie, Biao Gong, Yiliang Lv, Zhen Han, Guoshuai Zhao, Xueming Qian

Most recent works focus on answering first order logical queries to explore the knowledge graph reasoning via multi-hop logic predictions.

Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution

1 code implementation ICCV 2023 Zixi Tuo, Huan Yang, Jianlong Fu, Yujie Dun, Xueming Qian

Existing real-world video super-resolution (VSR) methods focus on designing a general degradation pipeline for open-domain videos while ignoring data intrinsic characteristics which strongly limit their performance when applying to some specific domains (eg., animation videos).

valid Video Super-Resolution

FSI: Frequency and Spatial Interactive Learning for Image Restoration in Under-Display Cameras

no code implementations ICCV 2023 Chengxu Liu, Xuan Wang, Shuai Li, Yuzhi Wang, Xueming Qian

In this paper, we introduce a new perspective to handle various diffraction in UDC images by jointly exploring the feature restoration in the frequency and spatial domains, and present a Frequency and Spatial Interactive Learning Network (FSI).

Image Restoration

Space-time Prompting for Video Class-incremental Learning

no code implementations ICCV 2023 Yixuan Pei, Zhiwu Qing, Shiwei Zhang, Xiang Wang, Yingya Zhang, Deli Zhao, Xueming Qian

In this paper, we will fill this gap by learning multiple prompts based on a powerful image-language pre-trained model, i. e., CLIP, making it fit for video class-incremental learning (VCIL).

class-incremental learning Class Incremental Learning +1

CSDA: Learning Category-Scale Joint Feature for Domain Adaptive Object Detection

no code implementations ICCV 2023 Changlong Gao, Chengxu Liu, Yujie Dun, Xueming Qian

For better category-level feature alignment, we propose a novel DAOD framework of joint category and scale information, dubbed CSDA, such a design enables effective object learning for different scales.

Object object-detection +1

Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning

no code implementations2 Nov 2022 Yixuan Pei, Zhiwu Qing, Jun Cen, Xiang Wang, Shiwei Zhang, Yaxiong Wang, Mingqian Tang, Nong Sang, Xueming Qian

The former is to reduce the memory cost by preserving only one condensed frame instead of the whole video, while the latter aims to compensate the lost spatio-temporal details in the Frame Condensing stage.

Action Recognition class-incremental learning +2

4D LUT: Learnable Context-Aware 4D Lookup Table for Image Enhancement

no code implementations5 Sep 2022 Chengxu Liu, Huan Yang, Jianlong Fu, Xueming Qian

In particular, we first introduce a lightweight context encoder and a parameter encoder to learn a context map for the pixel-level category and a group of image-adaptive coefficients, respectively.

Ranked #7 on Image Enhancement on MIT-Adobe 5k (SSIM on proRGB metric)

Image Enhancement

TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation

no code implementations19 Jul 2022 Chengxu Liu, Huan Yang, Jianlong Fu, Xueming Qian

In particular, we formulate the warped features with inconsistent motions as query tokens, and formulate relevant regions in a motion trajectory from two original consecutive frames into keys and values.

Video Frame Interpolation

Learning Trajectory-Aware Transformer for Video Super-Resolution

1 code implementation CVPR 2022 Chengxu Liu, Huan Yang, Jianlong Fu, Xueming Qian

Existing approaches usually align and aggregate video frames from limited adjacent frames (e. g., 5 or 7 frames), which prevents these approaches from satisfactory results.

Video deraining Video Super-Resolution

Multi-Sample based Contrastive Loss for Top-k Recommendation

1 code implementation1 Sep 2021 Hao Tang, Guoshuai Zhao, Yuxia Wu, Xueming Qian

Therefore, we propose a Multi-Sample based Contrastive Loss (MSCL) function which solves the two problems by balancing the importance of positive and negative samples and data augmentation.

Contrastive Learning Data Augmentation +1

Generating Superpixels for High-resolution Images with Decoupled Patch Calibration

no code implementations19 Aug 2021 Yaxiong Wang, Yunchao Wei, Xueming Qian, Li Zhu, Yi Yang

Superpixel segmentation has recently seen important progress benefiting from the advances in differentiable deep learning.

Segmentation Superpixels +1

ReGO: Reference-Guided Outpainting for Scenery Image

1 code implementation20 Jun 2021 Yaxiong Wang, Yunchao Wei, Xueming Qian, Li Zhu, Yi Yang

We aim to tackle the challenging yet practical scenery image outpainting task in this work.

Image Outpainting

Diversity Regularized Interests Modeling for Recommender Systems

no code implementations23 Mar 2021 Junmei Hao, JingCheng Shi, Qing Da, AnXiang Zeng, Yujie Dun, Xueming Qian, Qianying Lin

Each interest of the user should have a certain degree of distinction, thus we introduce three strategies as the diversity regularized separator to separate multiple user interest vectors.

Diversity Recommendation Systems

DONet: Dual Objective Networks for Skin Lesion Segmentation

no code implementations19 Aug 2020 Yaxiong Wang, Yunchao Wei, Xueming Qian, Li Zhu, Yi Yang

Skin lesion segmentation is a crucial step in the computer-aided diagnosis of dermoscopic images.

Lesion Segmentation Segmentation +2

Sketch-Guided Scenery Image Outpainting

no code implementations17 Jun 2020 Yaxiong Wang, Yunchao Wei, Xueming Qian, Li Zhu, Yi Yang

In this work, we take the image outpainting one step forward by allowing users to harvest personal custom outpainting results using sketches as the guidance.

Decoder Image Outpainting

Crowd Scene Analysis by Output Encoding

no code implementations27 Jan 2020 Yao Xue, Siming Liu, Yonghui Li, Xueming Qian

In addition, proper receptive field sizes are crucial for crowd analysis due to human size variations.

regression

Preparing Lessons: Improve Knowledge Distillation with Better Supervision

1 code implementation18 Nov 2019 Tiancheng Wen, Shenqi Lai, Xueming Qian

Knowledge distillation (KD) is widely used for training a compact model with the supervision of another large model, which could effectively improve the performance.

Knowledge Distillation

Position Focused Attention Network for Image-Text Matching

1 code implementation23 Jul 2019 Yaxiong Wang, Hao Yang, Xueming Qian, Lin Ma, Jing Lu, Biao Li, Xin Fan

Then, an attention mechanism is proposed to model the relations between the image region and blocks and generate the valuable position feature, which will be further utilized to enhance the region expression and model a more reliable relationship between the visual image and the textual sentence.

Image-text matching Position +2

VrR-VG: Refocusing Visually-Relevant Relationships

no code implementations ICCV 2019 Yuanzhi Liang, Yalong Bai, Wei zhang, Xueming Qian, Li Zhu, Tao Mei

Relationships encode the interactions among individual instances, and play a critical role in deep visual scene understanding.

Image Captioning Question Answering +3

GraphSeq2Seq: Graph-Sequence-to-Sequence for Neural Machine Translation

no code implementations27 Sep 2018 Guoshuai Zhao, Jun Li, Lu Wang, Xueming Qian, Yun Fu

In this paper, we propose a Graph-Sequence-to-Sequence(GraphSeq2Seq) model to fuse the dependency graph among words into the traditional Seq2Seq framework.

Decoder Image Captioning +6

Adaptive Co-weighting Deep Convolutional Features For Object Retrieval

no code implementations20 Mar 2018 Jiaxing Wang, Jihua Zhu, Shanmin Pang, Zhongyu Li, Yaochen Li, Xueming Qian

Aggregating deep convolutional features into a global image vector has attracted sustained attention in image retrieval.

Image Retrieval Object +1

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