16 citations · 90 across the 26 of their papers we have counts for
16 papers · 1 filter
MLLMs-Augmented Visual-Language Representation Learning
Yanqing Liu, Kai Wang, Wenqi Shao +5
Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we…
DREAM+: Efficient Dataset Distillation by Bidirectional Representative Matching
Yanqing Liu, Jianyang Gu, Kai Wang +4
Dataset distillation plays a crucial role in creating compact datasets with similar training performance compared with original large-scale ones. This is essential for addressing t…
Does Graph Distillation See Like Vision Dataset Counterpart?
Beining Yang, Kai Wang, Qingyun Sun +5
Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have attracted increasing concerns. Existing graph condens…
Can pre-trained models assist in dataset distillation?
Yao Lu, Xuguang Chen, Yuchen Zhang +7
Dataset Distillation (DD) is a prominent technique that encapsulates knowledge from a large-scale original dataset into a small synthetic dataset for efficient training. Meanwhile,…
Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching
Ziyao Guo, Kai Wang, George Cazenavette +3
The ultimate goal of Dataset Distillation is to synthesize a small synthetic dataset such that a model trained on this synthetic set will perform equally well as a model trained on…
DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation
Zelin Zang, Hao Luo, Kai Wang +4
Unsupervised Contrastive learning has gained prominence in fields such as vision, and biology, leveraging predefined positive/negative samples for representation learning. Data aug…
Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification
Jianyang Gu, Hao Luo, Kai Wang +3
Unsupervised domain adaptive person re-identification (Re-ID) methods alleviate the burden of data annotation through generating pseudo supervision messages. However, real-world Re…
Dataset Quantization
Daquan Zhou, Kai Wang, Jianyang Gu +5
State-of-the-art deep neural networks are trained with large amounts (millions or even billions) of data. The expensive computation and memory costs make it difficult to train them…
The Snowflake Hypothesis: Training Deep GNN with One Node One Receptive field
Kun Wang, Guohao Li, Shilong Wang +6
Despite Graph Neural Networks demonstrating considerable promise in graph representation learning tasks, GNNs predominantly face significant issues with over-fitting and over-smoot…
Summarizing Stream Data for Memory-Constrained Online Continual Learning
Jianyang Gu, Kai Wang, Wei Jiang +1
Replay-based methods have proved their effectiveness on online continual learning by rehearsing past samples from an auxiliary memory. With many efforts made on improving training…
MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID
Jianyang Gu, Kai Wang, Hao Luo +6
Neural Architecture Search (NAS) has been increasingly appealing to the society of object Re-Identification (ReID), for that task-specific architectures significantly improve the r…
BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency
Shuo Yang, Zhaopan Xu, Kai Wang +4
As one of the most fundamental techniques in multimodal learning, cross-modal matching aims to project various sensory modalities into a shared feature space. To achieve this, mass…
Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models
Zangwei Zheng, Mingyuan Ma, Kai Wang +3
Continual learning (CL) can help pre-trained vision-language models efficiently adapt to new or under-trained data distributions without re-training. Nevertheless, during the conti…
InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning
Ziheng Qin, Kai Wang, Zangwei Zheng +8
Data pruning aims to obtain lossless performances with less overall cost. A common approach is to filter out samples that make less contribution to the training. This could lead to…
DiM: Distilling Dataset into Generative Model
Kai Wang, Jianyang Gu, Daquan Zhou +3
Dataset distillation reduces the network training cost by synthesizing small and informative datasets from large-scale ones. Despite the success of the recent dataset distillation…
DREAM: Efficient Dataset Distillation by Representative Matching
Yanqing Liu, Jianyang Gu, Kai Wang +3
Dataset distillation aims to synthesize small datasets with little information loss from original large-scale ones for reducing storage and training costs. Recent state-of-the-art…