no code implementations • 11 Apr 2024 • Jiachen Zhu, Yichao Wang, Jianghao Lin, Jiarui Qin, Ruiming Tang, Weinan Zhang, Yong Yu
Furthermore, through causal graph analysis, we have discovered that the scenario itself directly influences click behavior, yet existing approaches directly incorporate data from other scenarios during the training of the current scenario, leading to prediction biases when they directly utilize click behaviors from other scenarios to train models.
no code implementations • 23 Jun 2023 • Jiachen Zhu, Katrina Evtimova, Yubei Chen, Ravid Shwartz-Ziv, Yann Lecun
In summary, VCReg offers a universally applicable regularization framework that significantly advances transfer learning and highlights the connection between gradient starvation, neural collapse, and feature transferability.
1 code implementation • 9 Oct 2022 • Shraman Pramanick, Li Jing, Sayan Nag, Jiachen Zhu, Hardik Shah, Yann Lecun, Rama Chellappa
Extensive experiments on a wide range of vision- and vision-language downstream tasks demonstrate the effectiveness of VoLTA on fine-grained applications without compromising the coarse-grained downstream performance, often outperforming methods using significantly more caption and box annotations.
2 code implementations • 21 Jun 2022 • Jiachen Zhu, Rafael M. Moraes, Serkan Karakulak, Vlad Sobol, Alfredo Canziani, Yann Lecun
Similar to other recent self-supervised learning methods, our method is based on maximizing the agreement among embeddings of different distorted versions of the same image, which pushes the encoder to produce transformation invariant representations.
no code implementations • 15 Jun 2022 • Li Jing, Jiachen Zhu, Yann Lecun
Self-supervised learning has shown superior performances over supervised methods on various vision benchmarks.