paper-with-me

Papers

Clusformer: A Transformer Based Clustering Approach to Unsupervised Large-Scale Face and Visual Landmark Recognition

2021-06-19 · CVPR 2021 1 · Xuan-Bac Nguyen, Duc Toan Bui, Chi Nhan Duong, Tien D. Bui, Khoa Luu

The research in automatic unsupervised visual clustering has received considerable attention over the last couple years. It aims at explaining distributions of unlabeled visual images by clustering them via a parameterized model of appearance. Graph Convolutional Neural Networks (GCN) have recently been one of the most popular clustering methods. However, it has reached some limitations. Firstly, it is quite sensitive to hard or noisy samples. Secondly, it is hard to investigate with various deep network models due to its computational training time. Finally, it is hard to design an end-to-end training model between the deep feature extraction and GCN clustering modeling. This work therefore presents the Clusformer, a simple but new perspective of Transformer based approach, to automatic visual clustering via its unsupervised attention mechanism. The proposed method is able to robustly deal with noisy or hard samples. It is also flexible and effective to collaborate with different deep network models with various model sizes in an end-to-end framework. The proposed method is evaluated on two popular large-scale visual databases, i.e. Google Landmark and MS-Celeb-1M face database, and outperforms prior unsupervised clustering methods. Code will be available at https://github.com/VinAIResearch/Clusformer

📄 PDF Abstract BibTeX

Code (1)

uark-cviu/Intraformer 공식 구현 pytorch

Tasks

ClusteringLandmark Recognition

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

QClusformer: A Quantum Transformer-based Framework for Unsupervised Visual Clustering

2024-05-30 · Xuan-Bac Nguyen, Hoang-Quan Nguyen, Samuel Yen-Chi Chen, Samee U. Khan 외

Unsupervised vision clustering, a cornerstone in computer vision, has been studied for decades, yielding significant outcomes across numerous vision tasks. However, these algorithms involve substantial computational dema…

Clustering

A Lightweight Clustering Framework for Unsupervised Semantic Segmentation

2023-11-30 · Yau Shing Jonathan Cheung, Xi Chen, Lihe Yang, Hengshuang Zhao

Unsupervised semantic segmentation aims to categorize each pixel in an image into a corresponding class without the use of annotated data. It is a widely researched area as obtaining labeled datasets is expensive. While …

ClusteringSegmentationSemantic SegmentationUnsupervised Semantic Segmentation

Fairness in Visual Clustering: A Novel Transformer Clustering Approach

2023-04-14 · Xuan-Bac Nguyen, Chi Nhan Duong, Marios Savvides, Kaushik Roy 외

Promoting fairness for deep clustering models in unsupervised clustering settings to reduce demographic bias is a challenging goal. This is because of the limitation of large-scale balanced data with well-annotated label…

AttributeClusteringDeep ClusteringFairness

Transformers can do Bayesian Clustering

2025-10-28 · Prajit Bhaskaran, Tom Viering arxiv

Bayesian clustering accounts for uncertainty but is computationally demanding at scale. Furthermore, real-world datasets often contain missing values, and simple imputation ignores the associated uncertainty, resulting i…

Vision Transformers for Zero-Shot Clustering of Animal Images: A Comparative Benchmarking Study

2026-02-03 · Hugo Markoff, Stefan Hein Bengtson, Michael Ørsted arxiv

Manual labeling of animal images remains a significant bottleneck in ecological research, limiting the scale and efficiency of biodiversity monitoring efforts. This study investigates whether state-of-the-art Vision Tran…

Dimensionality Reduction