Masked Image Modeling with Denoising Contrast

• URL: http://arxiv.org/abs/2205.09616v1
• Date: Thu, 19 May 2022 15:22:29 GMT
• Title: Masked Image Modeling with Denoising Contrast
• Authors: Kun Yi, Yixiao Ge, Xiaotong Li, Shusheng Yang, Dian Li, Jianping Wu, Ying Shan, Xiaohu Qie
• Abstract summary: Masked image modeling dominates this line of research with state-of-the-art performance on vision Transformers. We introduce a new pre-training method, ConMIM, to produce simple intra-image inter-patch contrastive constraints. ConMIM-pretrained vision Transformers with various scales achieve promising results on downstream image classification, semantic segmentation, object detection, and instance segmentation tasks.
• Score: 30.31920660487222
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling, there is no significant difference in essence, that is, how to design proper pretext tasks for vision dictionary look-up. Masked image modeling recently dominates this line of research with state-of-the-art performance on vision Transformers, where the core is to enhance the patch-level visual context capturing of the network via denoising auto-encoding mechanism. Rather than tailoring image tokenizers with extra training stages as in previous works, we unleash the great potential of contrastive learning on denoising auto-encoding and introduce a new pre-training method, ConMIM, to produce simple intra-image inter-patch contrastive constraints as the learning objectives for masked patch prediction. We further strengthen the denoising mechanism with asymmetric designs, including image perturbations and model progress rates, to improve the network pre-training. ConMIM-pretrained vision Transformers with various scales achieve promising results on downstream image classification, semantic segmentation, object detection, and instance segmentation tasks.

Related papers

• Denoising Autoregressive Representation Learning [13.185567468951628]
  Our method, DARL, employs a decoder-only Transformer to predict image patches autoregressively. We show that the learned representation can be improved by using tailored noise schedules and longer training in larger models.
  arXiv  Detail & Related papers  (2024-03-08T10:19:00Z)
• Cross-Image Attention for Zero-Shot Appearance Transfer [68.43651329067393]
  We introduce a cross-image attention mechanism that implicitly establishes semantic correspondences across images. We harness three mechanisms that either manipulate the noisy latent codes or the model's internal representations throughout the denoising process. Experiments show that our method is effective across a wide range of object categories and is robust to variations in shape, size, and viewpoint.
  arXiv  Detail & Related papers  (2023-11-06T18:33:24Z)
• Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training [59.923672191632065]
  We propose a new self-supervised pre-training approach, named Masked and Permuted Vision Transformer (MaPeT) MaPeT employs autoregressive and permuted predictions to capture intra-patch dependencies. Our results demonstrate that MaPeT achieves competitive performance on ImageNet.
  arXiv  Detail & Related papers  (2023-06-12T18:12:19Z)
• Masked Autoencoders as Image Processors [35.531254533198165]
  Masked autoencoders (MAE) for feature pre-training have unleashed the potential of Transformers. In this paper, we show that masked autoencoders are also scalable self-supervised learners for image processing tasks.
  arXiv  Detail & Related papers  (2023-03-30T12:09:35Z)
• Improving Masked Autoencoders by Learning Where to Mask [65.89510231743692]
  Masked image modeling is a promising self-supervised learning method for visual data. We present AutoMAE, a framework that uses Gumbel-Softmax to interlink an adversarially-trained mask generator and a mask-guided image modeling process. In our experiments, AutoMAE is shown to provide effective pretraining models on standard self-supervised benchmarks and downstream tasks.
  arXiv  Detail & Related papers  (2023-03-12T05:28:55Z)
• Exploring Stochastic Autoregressive Image Modeling for Visual Representation [24.582376834198403]
  We propose a novel autoregressive image modeling (named SAIM) by the two simple designs. By introducing prediction and the parallel encoder-decoder, SAIM significantly improve the performance of autoregressive image modeling. Our method achieves the best accuracy (83.9%) on the vanilla ViT-Base model among methods using only ImageNet-1K data.
  arXiv  Detail & Related papers  (2022-12-03T13:04:29Z)
• The Devil is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-Training [13.087987450384036]
  We present a new Masked Image Modeling (MIM), termed Geminated Autoencoder (Ge$2$-AE) for visual pre-training. Specifically, we equip our model with geminated decoders in charge of reconstructing image contents from both pixel and frequency space.
  arXiv  Detail & Related papers  (2022-04-18T09:22:55Z)
• Adversarial Masking for Self-Supervised Learning [81.25999058340997]
  Masked image model (MIM) framework for self-supervised learning, ADIOS, is proposed. It simultaneously learns a masking function and an image encoder using an adversarial objective. It consistently improves on state-of-the-art self-supervised learning (SSL) methods on a variety of tasks and datasets.
  arXiv  Detail & Related papers  (2022-01-31T10:23:23Z)
• FILIP: Fine-grained Interactive Language-Image Pre-Training [106.19474076935363]
  Fine-grained Interactive Language-Image Pre-training achieves finer-level alignment through a cross-modal late interaction mechanism. We construct a new large-scale image-text pair dataset called FILIP300M for pre-training. Experiments show that FILIP achieves state-of-the-art performance on multiple downstream vision-language tasks.
  arXiv  Detail & Related papers  (2021-11-09T17:15:38Z)
• Less is More: Pay Less Attention in Vision Transformers [61.05787583247392]
  Less attention vIsion Transformer builds upon the fact that convolutions, fully-connected layers, and self-attentions have almost equivalent mathematical expressions for processing image patch sequences. The proposed LIT achieves promising performance on image recognition tasks, including image classification, object detection and instance segmentation.
  arXiv  Detail & Related papers  (2021-05-29T05:26:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.