Towards Better Text-to-Image Generation Alignment via Attention Modulation

no code implementations • 22 Apr 2024 • Yihang Wu, Xiao Cao, Kaixin Li, Zitan Chen, Haonan Wang, Lei Meng, Zhiyong Huang

To achieve this, we incorporate a temperature control mechanism within the early phases of the self-attention modules to mitigate entity leakage issues.

Attribute Text-to-Image Generation

Class-level Structural Relation Modelling and Smoothing for Visual Representation Learning

1 code implementation • 8 Aug 2023 • Zitan Chen, Zhuang Qi, Xiao Cao, Xiangxian Li, Xiangxu Meng, Lei Meng

Representation learning for images has been advanced by recent progress in more complex neural models such as the Vision Transformers and new learning theories such as the structural causal models.

Graph Sampling Relation +1

Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Data

1 code implementation • 7 Aug 2023 • Zhuang Qi, Lei Meng, Zitan Chen, Han Hu, Hui Lin, Xiangxu Meng

To address this issue, this paper presents a cross-silo prototypical calibration method (FedCSPC), which takes additional prototype information from the clients to learn a unified feature space on the server side.

Contrastive Learning Federated Learning +1

Multi-modal Video Chapter Generation

1 code implementation • 26 Sep 2022 • Xiao Cao, Zitan Chen, Canyu Le, Lei Meng

On top of this dataset, we design an effective baseline specificlly for video chapters generation task.