BEiT: BERT Pre-Training of Image Transformers

BEiT：图像Transformer中的BERT预训练.

Discovering faster matrix multiplication algorithms with reinforcement learning

AlphaTensor：通过强化学习发现更快的矩阵乘法算法.

Analyzing and Improving Representations with the Soft Nearest Neighbor Loss

通过软最近邻损失分析和改进表示学习.

Circle Loss: A Unified Perspective of Pair Similarity Optimization

Circle Loss: 成对相似性优化的统一视角.

Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning

深度度量学习的多重相似性损失与通用对加权.

Person re-identification by multi-channel parts-based CNN with improved triplet loss function

通过多通道基于部位的卷积神经网络和改进的三元组损失函数实现人体重识别.