paper-with-me

홈 › Papers

ClusterFormer: Clustering As A Universal Visual Learner

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

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. For its efficacy, we hope our work can catalyze a paradigm shift in universal models in computer vision.

📄 PDF Abstract BibTeX arXiv:2309.13196

Code (1)

clusterformer/clusterformer 공식 구현 pytorch

Tasks

Clusteringimage-classificationImage ClassificationImage SegmentationInstance Segmentationobject-detectionObject DetectionPanoptic SegmentationRepresentation LearningSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
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…

Similar Papers 제목 키워드 기반

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…

10-shot image generation

Clusterformer: Cluster-based Transformer for 3D Object Detection in Point Clouds

2023-01-01 · ICCV 2023 1 · Yu Pei, Xian Zhao, Hao Li, Jingyuan Ma 외

Attributed to the unstructured and sparse nature of point clouds, the transformer shows greater potential in point clouds data processing. However, the recent query-based 3D detectors usually project the features acq…

3D Object DetectionDecoderObjectobject-detection+1

ClusterFormer: Neural Clustering Attention for Efficient and Effective Transformer

2022-05-01 · ACL 2022 5 · Ningning Wang, Guobing Gan, Peng Zhang, Shuai Zhang 외

Recently, a lot of research has been carried out to improve the efficiency of Transformer. Among them, the sparse pattern-based method is an important branch of efficient Transformers. However, some existing sparse metho…

ClusteringMachine TranslationNatural Language Inferencetext-classification+2

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