no code implementations • 29 Sep 2021 • Jun-Hyun Bae, Inchul Choi, Minho Lee
In this paper, we propose a novel bi-level learning framework for OOD generalization, which can effectively remove multiple unknown types of biases without any prior bias information or separate re-training steps of a model.
no code implementations • 24 Mar 2021 • Jun-Hyun Bae, Inchul Choi, Minho Lee
Our method is more robust to the data with spurious correlations and can provide an invariant optimal classifier even when data from each distribution are scarce.
no code implementations • 1 Jan 2021 • Taewon Park, Inchul Choi, Minho Lee
To address these problems, here we introduce a novel Distributed Associative Memory architecture (DAM) with Association Reinforcing Loss (ARL) function which enhances the relation reasoning performance of memory augmented neural network.
1 code implementation • 21 Jul 2020 • Taewon Park, Inchul Choi, Minho Lee
For this procedure, we replace a single external memory with a set of multiple smaller associative memory blocks and update these sub-memory blocks simultaneously and independently for the distributed representation of input data.
no code implementations • 11 Apr 2018 • Inchul Choi, Arunava Banerjee
In this paper, we propose a novel optical flow estimation framework which can provide accurate dense correspondence and occlusion localization through a multi-scale generalized plane matching approach.