Cut and Approximate

"Cut and Approximate" encompasses a range of techniques aiming to efficiently reduce data dimensionality or complexity while preserving essential information. Current research focuses on developing novel algorithms for data compression and feature selection, employing methods like graph neural networks for cut generation and optimization, and leveraging deep learning models for tasks such as image segmentation and 3D reconstruction. These advancements are improving the efficiency and accuracy of various applications, including large language model compression, robotic control, and medical image analysis, by enabling faster processing and reduced storage requirements. The field's impact stems from its ability to address challenges in high-dimensional data analysis and resource-constrained environments.

Papers

December 12, 2022

DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering
Amit Aflalo, Shai Bagon, Tamar Kashti, Yonina Eldar
Semantic Segmentation Image Segmentation Graph Convolutional Network Unsupervised Segmentation Cut and Approximate Deep Graph Clustering

October 22, 2022

Cut-and-Approximate: 3D Shape Reconstruction from Planar Cross-sections with Deep Reinforcement Learning
Azimkhon Ostonov
Deep Reinforcement Learning Imitation Learning 3D Reconstruction Surface Reconstruction 3D Shape Object Reconstruction Cut and Approximate 3D Shape Reconstruction Cross Section

October 11, 2022

Match Cutting: Finding Cuts with Smooth Visual Transitions
Boris Chen, Amir Ziai, Rebecca Tucker, Yuchen Xie
Similar Pair Cut and Approximate Audio Visual Speaker Extraction Visual Transition Match Cut

September 23, 2022

CUTS: A Deep Learning and Topological Framework for Multigranular Unsupervised Medical Image Segmentation
Chen Liu, Matthew Amodio, Liangbo L. Shen, Feng Gao, Arman Avesta, Sanjay Aneja, Jay C. Wang, Lucian V. Del Priore, Smita Krishnaswamy
Deep Learning Fine Grained Medical Image Segmentation Medical Image Unsupervised Method Cross Modality Cut and Approximate Unsupervised Learning Framework

July 15, 2022

Support Vector Machines with the Hard-Margin Loss: Optimal Training via Combinatorial Benders' Cuts
Ítalo Santana, Breno Serrano, Maximilian Schiffer, Thibaut Vidal
Loss Function Non Convex Loss Function Cut and Approximate Margin Loss Soft Margin Optimal Training Bender Decomposition

June 29, 2022

Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANs
Bo-Kyeong Kim, Shinkook Choi, Hancheol Park
Generative Model Pruning Method Conditional GANs Cut and Approximate Talking Face Generation Efficient GAN

February 22, 2022

Cut and Continuous Paste towards Real-time Deep Fall Detection
Sunhee Hwang, Minsong Ki, Seung-Hyun Lee, Sanghoon Park, Byoung-Ki Jeon
Human Motion Fall Detection Cut and Approximate Copy Paste Small Sized Convolutional Neural Network Winter Related Fall Injury

January 19, 2022

Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth
Doyeon Kim, Woonghyun Ka, Pyungwhan Ahn, Donggyu Joo, Sehwan Chun, Junmo Kim
Convolutional Neural Network Depth Estimation Monocular Depth Estimation Cut and Approximate Hierarchical Transformer Encoder

November 23, 2021

Isolation forests: looking beyond tree depth
David Cortes
Outlier Detection Cut and Approximate Isolation Forest Interpretable Tree Outlier Event Outlier Score