Feature Affinity

Feature affinity, in the context of recent research, focuses on leveraging relationships between features within and across data modalities to improve model performance. Current work explores this concept through various approaches, including multi-scale affinity learning in video segmentation and the integration of context and affinity information in transformer architectures for tasks like few-shot segmentation and image dehazing. These methods aim to enhance accuracy, robustness, and efficiency in diverse applications such as medical image analysis, recommendation systems, and computer vision, often by incorporating attribute information and handling noisy or limited data. The resulting improvements in model performance and efficiency have significant implications for various fields.

Papers

September 23, 2024

MIMAFace: Face Animation via Motion-Identity Modulated Appearance Feature Learning
Yue Han, Junwei Zhu, Yuxiang Feng, Xiaozhong Ji, Keke He, Xiangtai Li, zhucun xue, Yong Liu
Facial Expression Appearance Learning Feature Affinity Face Animation

May 20, 2024

Effective Clustering on Large Attributed Bipartite Graphs
Renchi Yang, Yidu Wu, Xiaoyang Lin, Qichen Wang, Tsz Nam Chan, Jieming Shi
Bipartite Graph Co Authorship Network Feature Affinity Bipartite Network Entropic Affinity

July 12, 2023

Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation
Beilei Cui, Minqing Zhang, Mengya Xu, An Wang, Wu Yuan, Hongliang Ren
Label Noise Video Segmentation Prior Model Medical Object Detection NoIsy Label CorrEction Feature Affinity

June 1, 2023

Affinity-based Attention in Self-supervised Transformers Predicts Dynamics of Object Grouping in Humans
Hossein Adeli, Seoyoung Ahn, Nikolaus Kriegeskorte, Gregory Zelinsky
Human Attention Arbitrary Object Real Human Visual Representation Learning Self Supervised Vision Transformer Self Supervised Transformer Reaction Time Feature Affinity

February 10, 2023

Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data
Zhijian Li, Biao Yang, Penghang Yin, Yingyong Qi, Jack Xin
Deep Neural Network Knowledge Distillation Quantization Operator Quantization Aware Training Feature Affinity

November 12, 2022

Affinity Feature Strengthening for Accurate, Complete and Robust Vessel Segmentation
Tianyi Shi, Xiaohuan Ding, Wei Zhou, Feng Pan, Zengqiang Yan, Xiang Bai, Xin Yang
Vessel Segmentation Feature Affinity

July 13, 2022

Rich Feature Distillation with Feature Affinity Module for Efficient Image Dehazing
Sai Mitheran, Anushri Suresh, Nisha J. S., Varun P. Gopi
Knowledge Distillation Super Resolution Image Dehazing Feature Distillation Haze Removal Feature Affinity

April 27, 2022

CATrans: Context and Affinity Transformer for Few-Shot Segmentation
Shan Zhang, Tianyi Wu, Sitong Wu, Guodong Guo
Segmentation Based Approach Context Information Shot Segmentation Reaction Ship Relation Transformer Query Image Segmentation Feature Affinity

Feature Affinity

Papers

MIMAFace: Face Animation via Motion-Identity Modulated Appearance Feature Learning

Effective Clustering on Large Attributed Bipartite Graphs

Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation

Affinity-based Attention in Self-supervised Transformers Predicts Dynamics of Object Grouping in Humans

Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data

Affinity Feature Strengthening for Accurate, Complete and Robust Vessel Segmentation

Rich Feature Distillation with Feature Affinity Module for Efficient Image Dehazing

CATrans: Context and Affinity Transformer for Few-Shot Segmentation