본문 바로가기

IT 와 Social 이야기/ML-DL48

[DSBA] Paper Review - Gated RNN [1] 발표자 : DSBA 연구실 석사과정 김혜연 [2] 발표 논문 : Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling (https://arxiv.org/abs/1412.3555) [3] 개요 - RNN의 기본 개요 및 단점 - RNN의 단점을 해결할 수 있는 Gated RNN 소개 2021. 11. 30.
PR-359: Audio-Visual Instance Discrimination with Cross-Modal Agreement - 이준호님 설명 - 논문 : https://arxiv.org/abs/2004.12943 Audio-Visual Instance Discrimination with Cross-Modal Agreement We present a self-supervised learning approach to learn audio-visual representations from video and audio. Our method uses contrastive learning for cross-modal discrimination of video from audio and vice-versa. We show that optimizing for cross-modal discr arxiv.org ○ 논문 설명 - 이 논문은 UC San Dieg.. 2021. 11. 29.
[딥러닝논문읽기모임] 2022 ICLR : Understanding Dimensional Collapse in Contrastive Self Supervised Learning Paper explain 2021. 11. 21.
[DSBA] Paper Review - ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases [1] 발표자 : DSBA 연구실 석사과정 정의석 [2] 발표 논문 : https://arxiv.org/abs/2103.10697 ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases Convolutional architectures have proven extremely successful for vision tasks. Their hard inductive biases enable sample-efficient learning, but come at the cost of a potentially lower performance ceiling. Vision Transformers (ViTs) rely on more .. 2021. 11. 18.