1 code implementation • 18 Dec 2024 • Pengbo Guo, Chengxu Liu, Xingsong Hou, Xueming Qian
We propose a novel Query-Based Controllable Distortion Rectification network for fisheye images (QueryCDR).
no code implementations • 7 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.
1 code implementation • 26 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.
no code implementations • 23 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.
no code implementations • 18 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
1 code implementation • 29 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.
Ranked #4 on
Image Retrieval
on CIRR
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.
1 code implementation • 13 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.
1 code implementation • 8 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.
no code implementations • 5 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.
no code implementations • 5 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.
1 code implementation • 19 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
no code implementations • 6 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.
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).
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).
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).
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.
no code implementations • 2 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.
no code implementations • 5 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)
no code implementations • 19 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.
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.
Ranked #4 on
Video Super-Resolution
on UDM10 - 4x upscaling
1 code implementation • 1 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.
no code implementations • 19 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.
1 code implementation • 20 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.
no code implementations • 23 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.
no code implementations • ICCV 2021 • Yaxiong Wang, Yunchao Wei, Yujiao Wu, Xueming Qian, Li Zhu, Yi Yang
Superpixel segmentation has seen significant progress benefiting from the deep convolutional networks.
no code implementations • 19 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.
no code implementations • 17 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.
no code implementations • 27 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.
1 code implementation • 18 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.
1 code implementation • 23 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.
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.
no code implementations • 27 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.
no code implementations • 20 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.