paper-with-me

홈 › Papers

ClusterFomer: Clustering As A Universal Visual Learner

2023-09-21 · NeurIPS 2023 11

This paper presents ClusterFormer, a universal vision model that is based on the Clustering paradigm with TransFormer. It comprises two novel designs: 1) recurrent cross-attention clustering, which reformulates the cross-attention mechanism in Transformer and enables recursive updates of cluster centers to facilitate strong representation learning; and 2) feature dispatching, which uses the updated cluster centers to redistribute image features through similarity-based metrics, resulting in a transparent pipeline. This elegant design streamlines an explainable and transferable workflow, capable of tackling heterogeneous vision tasks (i.e., image classification, object detection, and image segmentation) with varying levels of clustering granularity (i.e., image-, box-, and pixel-level). Empirical results demonstrate that ClusterFormer outperforms various well-known specialized architectures, achieving 83.41% top-1 acc. over ImageNet-1K for image classification, 54.2% and 47.0% mAP over MS COCO for object detection and instance segmentation, 52.4% mIoU over ADE20K for semantic segmentation, and 55.8% PQ over COCO Panoptic for panoptic segmentation. This work aims to initiate a paradigm shift in universal visual understanding and to benefit the broader field.

📄 PDF Abstract BibTeX

Code (1)

clusterformer/clusterformer 공식 구현 pytorch

Tasks

10-shot image generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
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…
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…
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…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

ClusterFormer: Clustering As A Universal Visual Learner

2023-09-22 · James C. Liang, Yiming Cui, Qifan Wang, Tong Geng 외

This paper presents CLUSTERFORMER, a universal vision model that is based on the CLUSTERing paradigm with TransFORMER. It comprises two novel designs: 1. recurrent cross-attention clustering, which reformulates the cross…

Clusteringimage-classificationImage ClassificationImage Segmentation+7

Attention-based Dynamic Subspace Learners for Medical Image Analysis

2022-06-18 · Sukesh Adiga V, Jose Dolz, Herve Lombaert

Learning similarity is a key aspect in medical image analysis, particularly in recommendation systems or in uncovering the interpretation of anatomical data in images. Most existing methods learn such similarities in the…

ClusteringImage ClusteringImage RetrievalMedical Image Analysis+3

X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation

2022-03-16 · Yinan He, Gengshi Huang, Siyu Chen, Jianing Teng 외

In computer vision, pre-training models based on largescale supervised learning have been proven effective over the past few years. However, existing works mostly focus on learning from individual task with single data s…

object-detectionObject DetectionOpen-Ended Question AnsweringRepresentation Learning+1

Unsupervised Visual Attention and Invariance for Reinforcement Learning

2021-04-07 · CVPR 2021 1 · Xudong Wang, Long Lian, Stella X. Yu

Vision-based reinforcement learning (RL) is successful, but how to generalize it to unknown test environments remains challenging. Existing methods focus on training an RL policy that is universal to changing visual doma…

Domain GeneralizationKeypoint Detectionreinforcement-learningReinforcement Learning+1

Meta Clustering for Collaborative Learning

2020-05-29 · Chenglong Ye, Reza Ghanadan, Jie Ding

In collaborative learning, learners coordinate to enhance each of their learning performances. From the perspective of any learner, a critical challenge is to filter out unqualified collaborators. We propose a framework …

ClusteringFairness