paper-with-me

홈 › Papers

Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens

2024-05-22 · Qihang Fan, Huaibo Huang, Mingrui Chen, Ran He

The Vision Transformer (ViT) has gained prominence for its superior relational modeling prowess. However, its global attention mechanism's quadratic complexity poses substantial computational burdens. A common remedy spatially groups tokens for self-attention, reducing computational requirements. Nonetheless, this strategy neglects semantic information in tokens, possibly scattering semantically-linked tokens across distinct groups, thus compromising the efficacy of self-attention intended for modeling inter-token dependencies. Motivated by these insights, we introduce a fast and balanced clustering method, named \textbf{S}emantic \textbf{E}quitable \textbf{C}lustering (SEC). SEC clusters tokens based on their global semantic relevance in an efficient, straightforward manner. In contrast to traditional clustering methods requiring multiple iterations, our method achieves token clustering in a single pass. Additionally, SEC regulates the number of tokens per cluster, ensuring a balanced distribution for effective parallel processing on current computational platforms without necessitating further optimization. Capitalizing on SEC, we propose a versatile vision backbone, SECViT. Comprehensive experiments in image classification, object detection, instance segmentation, and semantic segmentation validate the effectiveness of SECViT. Moreover, SEC can be conveniently and swiftly applied to multimodal large language models (MLLM), such as LLaVA, to serve as a vision language connector, effectively accelerating the model's efficiency while maintaining unchanged or better performance.

📄 PDF Abstract BibTeX arXiv:2405.13337

Code (0)

등록된 구현이 없습니다.

Tasks

Clusteringimage-classificationImage ClassificationInstance Segmentationobject-detectionObject DetectionSemantic Segmentation

Methods 이 논문이 사용한 방법론

Attention 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…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Equitable Federated Learning with Activation Clustering

2024-10-24 · Antesh Upadhyay, Abolfazl Hashemi

Federated learning is a prominent distributed learning paradigm that incorporates collaboration among diverse clients, promotes data locality, and thus ensures privacy. These clients have their own technological, cultura…

ClusteringFederated Learning

Equitable Mechanism Design for Facility Location

2025-06-12 · Toby Walsh

We consider strategy proof mechanisms for facility location which maximize equitability between agents. As is common in the literature, we measure equitability with the Gini index. We first prove a simple but fundamental…

Redundancy-Free Self-Supervised Relational Learning for Graph Clustering

2023-09-09 · Si-Yu Yi, Wei Ju, Yifang Qin, Xiao Luo 외

Graph clustering, which learns the node representations for effective cluster assignments, is a fundamental yet challenging task in data analysis and has received considerable attention accompanied by graph neural networ…

AttributeClusteringGraph ClusteringRelation+2

Unsupervised Search for Ethnic Minorities' Medical Segmentation Training Set

2025-01-05 · Yixiao Chen, Yue Yao, Ruining Yang, Md Zakir Hossain 외

This article investigates the critical issue of dataset bias in medical imaging, with a particular emphasis on racial disparities caused by uneven population distribution in dataset collection. Our analysis reveals that …

Efficient Network Embedding by Approximate Equitable Partitions

2024-09-16 · Giuseppe Squillace, Mirco Tribastone, Max Tschaikowski, Andrea Vandin

Structural network embedding is a crucial step in enabling effective downstream tasks for complex systems that aims to project a network into a lower-dimensional space while preserving similarities among nodes. We introd…

Network Embedding