Joint Contrastive Learning with Infinite Possibilities -- Supplementary Materials
–Neural Information Processing Systems
W e use notation Eq.(M.xx) to refer to the equation Eq.(xx) presented in the main paper, and use Eq.(S.xx) Similarly, we use Fig./Section/T able (M.xx) JCL more efficiently exploit these samples. Qi Cai and Y u Wang contributed equally to this work. This work was performed at JD AI Research. Eq.(M.8), we update the queue The ablation experiments are conducted on a subset of ImageNet1K (i.e., ImageNet100) following For the experiments that visualize the distributions of similarities and variances in Section (M.4.5),
Neural Information Processing Systems
Nov-14-2025, 13:50:21 GMT
- Country:
- Asia > China
- Anhui Province > Hefei (0.05)
- Beijing > Beijing (0.05)
- North America > Canada (0.05)
- Asia > China
- Technology: