paper-with-me

Papers

Cluster and Predict Latents Patches for Improved Masked Image Modeling

2025-02-12 · Timothée Darcet, Federico Baldassarre, Maxime Oquab, Julien Mairal, Piotr Bojanowski

Masked Image Modeling (MIM) offers a promising approach to self-supervised representation learning, however existing MIM models still lag behind the state-of-the-art. In this paper, we systematically analyze target representations, loss functions, and architectures, to introduce CAPI - a novel pure-MIM framework that relies on the prediction of latent clusterings. Our approach leverages a clustering-based loss, which is stable to train, and exhibits promising scaling properties. Our ViT-L backbone, CAPI, achieves 83.8% accuracy on ImageNet and 32.1% mIoU on ADE20K with simple linear probes, substantially outperforming previous MIM methods and approaching the performance of the current state-of-the-art, DINOv2. We release all our code and models.

📄 PDF Abstract BibTeX arXiv:2502.08769

Code (2)

facebookresearch/capi 공식 구현 jax
https://gitlab.com/birder/birder pytorch

Tasks

Representation Learning

Methods 이 논문이 사용한 방법론

MIM 설명 없음

Similar Papers 제목 키워드 기반

E-MD3C: Taming Masked Diffusion Transformers for Efficient Zero-Shot Object Customization

2025-02-13 · Trung X. Pham, Zhang Kang, Ji Woo Hong, Xuran Zheng 외

We propose E-MD3C ($\underline{E}$fficient $\underline{M}$asked $\underline{D}$iffusion Transformer with Disentangled $\underline{C}$onditions and $\underline{C}$ompact $\underline{C}$ollector), a highly efficient framew…

Computational EfficiencyDenoisingGPUSSIM

Context Autoencoder for Self-Supervised Representation Learning

2022-02-07 · Xiaokang Chen, Mingyu Ding, Xiaodi Wang, Ying Xin 외

We present a novel masked image modeling (MIM) approach, context autoencoder (CAE), for self-supervised representation pretraining. We pretrain an encoder by making predictions in the encoded representation space. The pr…

DecoderInstance Segmentationobject-detectionObject Detection+4

PointGAC: Geometric-Aware Codebook for Masked Point Cloud Modeling

2025-07-07 · Abiao Li, Chenlei Lv, Yuming Fang, Yifan Zuo 외 arxiv

Most masked point cloud modeling (MPM) methods follow a regression paradigm to reconstruct the coordinate or feature of masked regions. However, they tend to over-constrain the model to learn the details of the masked re…

Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input

2022-10-26 · Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada 외

Masked Autoencoders is a simple yet powerful self-supervised learning method. However, it learns representations indirectly by reconstructing masked input patches. Several methods learn representations directly by predic…

Audio ClassificationAudio TaggingKeyword SpottingKeyword Spotting on Google Speech Commands+3

Efficient Vision-Language Pre-training by Cluster Masking

2024-05-14 · CVPR 2024 1 · Zihao Wei, Zixuan Pan, Andrew Owens

We propose a simple strategy for masking image patches during visual-language contrastive learning that improves the quality of the learned representations and the training speed. During each iteration of training, we ra…

Contrastive Learning