Author name cluster

Keisuke Kawano

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

AAAI Conference 2022 Conference Paper

Partial Wasserstein Covering

Keisuke Kawano
Satoshi Koide
Keisuke Otaki

We consider a general task called partial Wasserstein covering with the goal of providing information on what patterns are not being taken into account in a dataset (e. g. , dataset used during development) compared with another dataset(e. g. , dataset obtained from actual applications). We model this task as a discrete optimization problem with partial Wasserstein divergence as an objective function. Although this problem is NP-hard, we prove that it satisfies the submodular property, allowing us to use a greedy algorithm with a 0. 63 approximation. However, the greedy algorithm is still inefficient because it requires solving linear programming for each objective function evaluation. To overcome this inefficiency, we propose quasi-greedy algorithms that consist of a series of acceleration techniques, such as sensitivity analysis based on strong duality and the so-called C-transform in the optimal transport field. Experimentally, we demonstrate that we can efficiently fill in the gaps between the two datasets and find missing scene in real driving scenes datasets.

PDF Details

ICRA Conference 2021 Conference Paper

PLG-IN: Pluggable Geometric Consistency Loss with Wasserstein Distance in Monocular Depth Estimation

Noriaki Hirose
Satoshi Koide
Keisuke Kawano
Ruho Kondo

We propose a novel objective for penalizing geometric inconsistencies and improving the depth and pose estimation performance of monocular camera images. Our objective is designed using the Wasserstein distance between two point clouds, estimated from images with different camera poses. The Wasserstein distance can impose a soft and symmetric coupling between two point clouds, which suitably maintains geometric constraints and results in a differentiable objective. By adding our objective to those of other state-of-the-art methods, we can effectively penalize geometric inconsistencies and obtain highly accurate depth and pose estimations. Our proposed method was evaluated using the KITTI dataset.

Details

NeurIPS Conference 2019 Conference Paper

Flow-based Image-to-Image Translation with Feature Disentanglement

Ruho Kondo
Keisuke Kawano
Satoshi Koide
Takuro Kutsuna

Learning non-deterministic dynamics and intrinsic factors from images obtained through physical experiments is at the intersection of machine learning and material science. Disentangling the origins of uncertainties involved in microstructure growth, for example, is of great interest because future states vary due to thermal fluctuation and other environmental factors. To this end we propose a flow-based image-to-image model, called Flow U-Net with Squeeze modules (FUNS), that allows us to disentangle the features while retaining the ability to generate highquality diverse images from condition images. Our model successfully captures probabilistic phenomena by incorporating a U-Net-like architecture into the flowbased model. In addition, our model automatically separates the diversity of target images into condition-dependent/independent parts. We demonstrate that the quality and diversity of the images generated for microstructure growth and CelebA datasets outperform existing variational generative models.

PDF Details

NeurIPS Conference 2018 Conference Paper

Neural Edit Operations for Biological Sequences

Satoshi Koide
Keisuke Kawano
Takuro Kutsuna

The evolution of biological sequences, such as proteins or DNAs, is driven by the three basic edit operations: substitution, insertion, and deletion. Motivated by the recent progress of neural network models for biological tasks, we implement two neural network architectures that can treat such edit operations. The first proposal is the edit invariant neural networks, based on differentiable Needleman-Wunsch algorithms. The second is the use of deep CNNs with concatenations. Our analysis shows that CNNs can recognize star-free regular expressions, and that deeper CNNs can recognize more complex regular expressions including the insertion/deletion of characters. The experimental results for the protein secondary structure prediction task suggest the importance of insertion/deletion. The test accuracy on the widely-used CB513 dataset is 71. 5%, which is 1. 2-points better than the current best result on non-ensemble models.

PDF Details