ymgw55

segment-anything-edge-detection

Unofficial edge detection implementation using the Automatic Mask Generation (AMG) of the Segment Anything Model (SAM).

SCESAME

Zero-Shot Edge Detection with SCESAME: Spectral Clustering-based Ensemble for Segment Anything Model Estimation (Published in WACV 2024 Workshop)

WSMD

Improving word mover’s distance by leveraging self-attention matrix (Published in EMNLP 2023 Findings)

OT-Seq2Seq-PyTorch

an unofficial PyTorch implementation of ICLR 2019 paper IMPROVING SEQUENCE-TO-SEQUENCE LEARNING VIA OPTIMAL TRANSPORT

Cosine-Similarity-via-ICA

Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings (Published in COLING 2025)

dendro-thresh-cluster

In the dendrogram generated from sklearn.cluster.AgglomerativeClustering, it is difficult to understand the clustering to which each node belongs for each threshold. dendro-thresh-cluster is a program that shows the clustering to which each node belongs for each threshold.

Norm-and-Variance

Norm of Mean Contextualized Embeddings Determines their Variance (Published in COLING 2025)

Axis-Tour

Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings (Published in EMNLP 2024 Findings)

ymgw55