1 code implementation • 29 May 2024 • Jihao Liu, Jinliang Zheng, Boxiao Liu, Yu Liu, Hongsheng Li
Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a standard technique for learning multi-modal visual-language representations.
no code implementations • 5 Nov 2023 • Shuo Chen, Boxiao Liu, Haihang You
Firstly, we propose a low-cost metric for the criticality in SNNs.
no code implementations • NeurIPS 2023 • Zeyue Xue, Guanglu Song, Qiushan Guo, Boxiao Liu, Zhuofan Zong, Yu Liu, Ping Luo
Text-to-image generation has recently witnessed remarkable achievements.
Ranked #11 on Text-to-Image Generation on MS COCO
1 code implementation • ICCV 2023 • Jihao Liu, Tai Wang, Boxiao Liu, Qihang Zhang, Yu Liu, Hongsheng Li
In this paper, we propose Geometry Enhanced Masked Image Modeling (GeoMIM) to transfer the knowledge of the LiDAR model in a pretrain-finetune paradigm for improving the multi-view camera-based 3D detection.
no code implementations • ICCV 2023 • Shanshan Lao, Guanglu Song, Boxiao Liu, Yu Liu, Yujiu Yang
In MKD, random patches of the input image are masked, and the corresponding missing feature is recovered by forcing it to imitate the output of the teacher.
no code implementations • ICCV 2023 • Shanshan Lao, Guanglu Song, Boxiao Liu, Yu Liu, Yujiu Yang
Bridging this semantic gap now requires case-by-case algorithm design which is time-consuming and heavily relies on experienced adjustment.
no code implementations • 8 Aug 2022 • Bingqi Ma, Guanglu Song, Boxiao Liu, Yu Liu
To better understand this, we reformulate the noise type of each class in a more fine-grained manner as N-identities|K^C-clusters.
1 code implementation • 18 Jul 2022 • Jihao Liu, Boxiao Liu, Hang Zhou, Hongsheng Li, Yu Liu
In this paper, we propose a novel data augmentation technique TokenMix to improve the performance of vision transformers.
no code implementations • 16 Feb 2022 • Jihao Liu, Boxiao Liu, Hongsheng Li, Yu Liu
Recent studies pointed out that knowledge distillation (KD) suffers from two degradation problems, the teacher-student gap and the incompatibility with strong data augmentations, making it not applicable to training state-of-the-art models, which are trained with advanced augmentations.
Ranked #134 on Image Classification on ImageNet
no code implementations • 22 Dec 2021 • Zite Jiang, Boxiao Liu, Shuai Zhang, Xingzhong Hou, Mengting Yuan, Haihang You
Subgraph matching is a NP-complete problem that extracts isomorphic embeddings of a query graph $q$ in a data graph $G$.
no code implementations • ICCV 2021 • Boxiao Liu, Shenghan Zhang, Guanglu Song, Haihang You, Yu Liu
In this paper, we first quantitatively define the uniformity of the sampled data for training, providing a unified view for methods that learn from biased data.
Ranked #1 on Face Verification on IJB-C (training dataset metric)
no code implementations • 29 Sep 2021 • Xingzhong Hou, Boxiao Liu, Fang Wan, Haihang You
The existing pipeline is first pretraining a source model (which contains a generator and a discriminator) on a large-scale dataset and finetuning it on a target domain with limited samples.
no code implementations • 25 May 2021 • Jihao Liu, Ming Zhang, Yangting Sun, Boxiao Liu, Guanglu Song, Yu Liu, Hongsheng Li
Further, an architecture knowledge pool together with a block similarity function is proposed to utilize parameter knowledge and reduces the searching time by 2 times.
no code implementations • 1 Jan 2021 • Jihao Liu, Yangting Sun, Ming Zhang, Boxiao Liu, Yu Liu
Further, a life-long knowledge pool together with a block similarity function is proposed to utilize the lifelong parameter knowledge and reduces the searching time by 2 times.
no code implementations • ICCV 2021 • Boxiao Liu, Guanglu Song, Manyuan Zhang, Haihang You, Yu Liu
When collaborated with the popular ArcFace on million-level data representation learning, we found that the switchable manner in SKH can effectively eliminate the gradient conflict generated by real-world label noise on a single K-class hyperplane.
no code implementations • 14 Jun 2019 • Yan Gao, Boxiao Liu, Nan Guo, Xiaochun Ye, Fang Wan, Haihang You, Dongrui Fan
Weakly supervised object detection (WSOD) focuses on training object detector with only image-level annotations, and is challenging due to the gap between the supervision and the objective.