2 citations · 3 across the 5 of their papers we have counts for
5 papers
MixBCT: Towards Self-Adapting Backward-Compatible Training
Yu Liang, Yufeng Zhang, Shiliang Zhang +4
Backward-compatible training circumvents the need for expensive updates to the old gallery database when deploying an advanced new model in the retrieval system. Previous methods a…
DYNAFED: Tackling Client Data Heterogeneity with Global Dynamics
Renjie Pi, Weizhong Zhang, Yueqi Xie +4
The Federated Learning (FL) paradigm is known to face challenges under heterogeneous client data. Local training on non-iid distributed data results in deflected local optimum, whi…
Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commerce
Yincen Qu, Ningyu Zhang, Hui Chen +6
In e-commerce, the salience of commonsense knowledge (CSK) is beneficial for widespread applications such as product search and recommendation. For example, when users search for `…
FaceMap: Towards Unsupervised Face Clustering via Map Equation
Xiaotian Yu, Yifan Yang, Aibo Wang +4
Face clustering is an essential task in computer vision due to the explosion of related applications such as augmented reality or photo album management. The main challenge of this…
Enhancing Social Relation Inference with Concise Interaction Graph and Discriminative Scene Representation
Xiaotian Yu, Hanling Yi, Yi Yu +3
There has been a recent surge of research interest in attacking the problem of social relation inference based on images. Existing works classify social relations mainly by creatin…