1 code implementation • 11 Apr 2024 • Shaocong Long, Qianyu Zhou, Xiangtai Li, Xuequan Lu, Chenhao Ying, Yuan Luo, Lizhuang Ma, Shuicheng Yan
SPR strives to encourage the model to concentrate more on objects rather than context, consisting of two designs: Prior-Free Scanning~(PFS), and Domain Context Interchange~(DCI).
no code implementations • 28 Mar 2024 • Qianyu Zhou, Ke-Yue Zhang, Taiping Yao, Xuequan Lu, Shouhong Ding, Lizhuang Ma
Our method, consisting of Test-Time Style Projection (TTSP) and Diverse Style Shifts Simulation (DSSS), effectively projects the unseen data to the seen domain space.
1 code implementation • 31 Jan 2024 • Yiran Song, Qianyu Zhou, Xuequan Lu, Zhiwen Shao, Lizhuang Ma
In this paper, we aim to investigate the impact of the general vision modules on finetuning SAM and enable them to generalize across all downstream tasks.
1 code implementation • 17 Jan 2024 • Hexiang Wang, Fengqi Liu, Qianyu Zhou, Ran Yi, Xin Tan, Lizhuang Ma
To address this issue, we propose to model motion from the source image to the driving frame in highly-expressive diffeomorphism spaces.
1 code implementation • 4 Jan 2024 • Yiran Song, Qianyu Zhou, Xiangtai Li, Deng-Ping Fan, Xuequan Lu, Lizhuang Ma
To this end, we propose Scalable Bias-Mode Attention Mask (BA-SAM) to enhance SAM's adaptability to varying image resolutions while eliminating the need for structure modifications.
no code implementations • 28 Sep 2023 • Shaocong Long, Qianyu Zhou, Chenhao Ying, Lizhuang Ma, Yuan Luo
On the one hand, the simultaneous attainment of generalizability and discriminability of features presents a complex challenge, often entailing inherent contradictions.
no code implementations • 28 Sep 2023 • Shaocong Long, Qianyu Zhou, Chenhao Ying, Lizhuang Ma, Yuan Luo
In specific, DTS employs distinct soft labels as training targets to account for various feature distributions across domains and thereby mitigates the gradient conflicts, and DCB dynamically balances the contributions of source domains by ensuring a fair decline in losses of different source domains.
1 code implementation • CVPR 2023 • Qianyu Zhou, Ke-Yue Zhang, Taiping Yao, Xuequan Lu, Ran Yi, Shouhong Ding, Lizhuang Ma
To address these issues, we propose a novel perspective for DG FAS that aligns features on the instance level without the need for domain labels.
no code implementations • 22 Nov 2022 • Yiran Song, Qianyu Zhou, Lizhuang Ma
Existing INRs methods suffer from two problems: 1) narrow theoretical definitions of INRs are inapplicable to high-level tasks; 2) lack of representation capabilities to deep networks.
no code implementations • 20 Jul 2022 • Qianyu Zhou, Ke-Yue Zhang, Taiping Yao, Ran Yi, Shouhong Ding, Lizhuang Ma
Existing DG-based FAS approaches always capture the domain-invariant features for generalizing on the various unseen domains.
no code implementations • 20 Jul 2022 • Qianyu Zhou, Ke-Yue Zhang, Taiping Yao, Ran Yi, Kekai Sheng, Shouhong Ding, Lizhuang Ma
Most existing UDA FAS methods typically fit the trained models to the target domain via aligning the distribution of semantic high-level features.
3 code implementations • 13 Jan 2022 • Qianyu Zhou, Xiangtai Li, Lu He, Yibo Yang, Guangliang Cheng, Yunhai Tong, Lizhuang Ma, DaCheng Tao
Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors.
Ranked #4 on Video Object Detection on ImageNet VID (using extra training data)
1 code implementation • 11 Oct 2021 • Qianyu Zhou, Chuyun Zhuang, Ran Yi, Xuequan Lu, Lizhuang Ma
In this paper, we propose a novel and fully end-to-end trainable approach, called regional contrastive consistency regularization (RCCR) for domain adaptive semantic segmentation.
1 code implementation • ICCV 2021 • Qiqi Gu, Qianyu Zhou, Minghao Xu, Zhengyang Feng, Guangliang Cheng, Xuequan Lu, Jianping Shi, Lizhuang Ma
Extensive experiments demonstrate that our method can soundly boost the performance on both cross-domain object detection and segmentation for state-of-the-art techniques.
no code implementations • 15 Aug 2021 • Hongyi Xu, Fengqi Liu, Qianyu Zhou, Jinkun Hao, Zhijie Cao, Zhengyang Feng, Lizhuang Ma
Inspired by this, we propose a novel semi-supervised framework based on pseudo-labeling for outdoor 3D object detection tasks.
1 code implementation • 8 Aug 2021 • Qianyu Zhou, Zhengyang Feng, Qiqi Gu, Jiangmiao Pang, Guangliang Cheng, Xuequan Lu, Jianping Shi, Lizhuang Ma
The generated contextual mask is critical in this work and will guide the context-aware domain mixup on three different levels.
Ranked #5 on Image-to-Image Translation on SYNTHIA-to-Cityscapes
no code implementations • 8 Aug 2021 • Qianyu Zhou, Qiqi Gu, Jiangmiao Pang, Xuequan Lu, Lizhuang Ma
In this paper, we study a practical setting called Specific Domain Adaptation (SDA) that aligns the source and target domains in a demanded-specific dimension.
Image-to-Image Translation on Cityscapes-to-Foggy Cityscapes object-detection +3
1 code implementation • 23 May 2021 • Lu He, Qianyu Zhou, Xiangtai Li, Li Niu, Guangliang Cheng, Xiao Li, Wenxuan Liu, Yunhai Tong, Lizhuang Ma, Liqing Zhang
Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors.
no code implementations • 19 Apr 2020 • Qianyu Zhou, Zhengyang Feng, Qiqi Gu, Guangliang Cheng, Xuequan Lu, Jianping Shi, Lizhuang Ma
Guided by this mask, we propose a ClassOut strategy to realize effective regional consistency in a fine-grained manner.
1 code implementation • 18 Apr 2020 • Zhengyang Feng, Qianyu Zhou, Qiqi Gu, Xin Tan, Guangliang Cheng, Xuequan Lu, Jianping Shi, Lizhuang Ma
Instead, leveraging inter-model disagreement between different models is a key to locate pseudo label errors.