Escaping The Big Data Paradigm in Self-Supervised Representation Learning

• URL: http://arxiv.org/abs/2502.18056v1
• Date: Tue, 25 Feb 2025 10:21:49 GMT
• Title: Escaping The Big Data Paradigm in Self-Supervised Representation Learning
• Authors: Carlos Vélez García, Miguel Cazorla, Jorge Pomares,
• Abstract summary: We introduce SCOTT, a shallow tokenization architecture compatible with Masked Image Modeling tasks.<n>SCOTT injects convolutional inductive biases into Vision Transformers (ViTs), enhancing their efficacy in small-scale data regimes.<n>We validate our method on three small-size, standard-resoultion, fine-grained datasets: Oxford Flowers-102, Oxford IIIT Pets-37, and ImageNet-100.
• Score: 2.10796947080293
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The reliance on large-scale datasets and extensive computational resources has become a major barrier to advancing representation learning in vision, especially in data-scarce domains. In this paper, we address the critical question: Can we escape the big data paradigm in self-supervised representation learning from images? We introduce SCOTT (Sparse Convolutional Tokenizer for Transformers), a shallow tokenization architecture that is compatible with Masked Image Modeling (MIM) tasks. SCOTT injects convolutional inductive biases into Vision Transformers (ViTs), enhancing their efficacy in small-scale data regimes. Alongside, we propose to train on a Joint-Embedding Predictive Architecture within a MIM framework (MIM-JEPA), operating in latent representation space to capture more semantic features. Our approach enables ViTs to be trained from scratch on datasets orders of magnitude smaller than traditionally required --without relying on massive external datasets for pretraining. We validate our method on three small-size, standard-resoultion, fine-grained datasets: Oxford Flowers-102, Oxford IIIT Pets-37, and ImageNet-100. Despite the challenges of limited data and high intra-class similarity, frozen SCOTT models pretrained with MIM-JEPA significantly outperform fully supervised methods and achieve competitive results with SOTA approaches that rely on large-scale pretraining, complex image augmentations and bigger model sizes. By demonstrating that robust off-the-shelf representations can be learned with limited data, compute, and model sizes, our work paves the way for computer applications in resource constrained environments such as medical imaging or robotics. Our findings challenge the prevailing notion that vast amounts of data are indispensable for effective representation learning in vision, offering a new pathway toward more accessible and inclusive advancements in the field.

Related papers

• A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning [67.72413262980272]
  Pre-trained vision models (PVMs) are fundamental to modern robotics, yet their optimal configuration remains unclear. We develop SlotMIM, a method that induces object-centric representations by introducing a semantic bottleneck. Our approach achieves significant improvements over prior work in image recognition, scene understanding, and robot learning evaluations.
  arXiv  Detail & Related papers  (2025-03-10T06:18:31Z)
• Pretraining Billion-scale Geospatial Foundational Models on Frontier [0.16492989697868893]
  Foundation Models (FMs) are trained with internet-scale unlabeled data via self-supervised learning. We investigate billion scale FMs and HPC training profiles for geospatial applications by pretraining on publicly available data. Our larger 3B parameter size model achieves up to 30% improvement in top1 scene classification accuracy.
  arXiv  Detail & Related papers  (2024-04-17T19:16:32Z)
• Data-efficient Large Vision Models through Sequential Autoregression [58.26179273091461]
  We develop an efficient, autoregression-based vision model on a limited dataset. We demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint.
  arXiv  Detail & Related papers  (2024-02-07T13:41:53Z)
• A Simple and Efficient Baseline for Data Attribution on Images [107.12337511216228]
  Current state-of-the-art approaches require a large ensemble of as many as 300,000 models to accurately attribute model predictions. In this work, we focus on a minimalist baseline, utilizing the feature space of a backbone pretrained via self-supervised learning to perform data attribution. Our method is model-agnostic and scales easily to large datasets.
  arXiv  Detail & Related papers  (2023-11-03T17:29:46Z)
• Spatio-Temporal Encoding of Brain Dynamics with Surface Masked Autoencoders [10.097983222759884]
  Surface Masked AutoEncoder (sMAE) and surface Masked AutoEncoder (MAE) These models are trained to reconstruct cortical feature maps from masked versions of the input by learning strong latent representations of cortical development and structure function. Results show that (v)sMAE pre-trained models improve phenotyping prediction performance on multiple tasks by $ge 26%$, and offer faster convergence relative to models trained from scratch.
  arXiv  Detail & Related papers  (2023-08-10T10:01:56Z)
• An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training [79.78201886156513]
  We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Our approach achieves comparable results to single-task state-of-the-art models and demonstrates strong generalization on downstream tasks.
  arXiv  Detail & Related papers  (2023-06-29T17:59:57Z)
• Retrieval-Enhanced Contrastive Vision-Text Models [61.783728119255365]
  We propose to equip vision-text models with the ability to refine their embedding with cross-modal retrieved information from a memory at inference time. Remarkably, we show that this can be done with a light-weight, single-layer, fusion transformer on top of a frozen CLIP. Our experiments validate that our retrieval-enhanced contrastive (RECO) training improves CLIP performance substantially on several challenging fine-grained tasks.
  arXiv  Detail & Related papers  (2023-06-12T15:52:02Z)
• Delving Deeper into Data Scaling in Masked Image Modeling [145.36501330782357]
  We conduct an empirical study on the scaling capability of masked image modeling (MIM) methods for visual recognition. Specifically, we utilize the web-collected Coyo-700M dataset. Our goal is to investigate how the performance changes on downstream tasks when scaling with different sizes of data and models.
  arXiv  Detail & Related papers  (2023-05-24T15:33:46Z)
• Multimodal Masked Autoencoders Learn Transferable Representations [127.35955819874063]
  We propose a simple and scalable network architecture, the Multimodal Masked Autoencoder (M3AE) M3AE learns a unified encoder for both vision and language data via masked token prediction. We provide an empirical study of M3AE trained on a large-scale image-text dataset, and find that M3AE is able to learn generalizable representations that transfer well to downstream tasks.
  arXiv  Detail & Related papers  (2022-05-27T19:09:42Z)
• On The State of Data In Computer Vision: Human Annotations Remain Indispensable for Developing Deep Learning Models [0.0]
  High-quality labeled datasets play a crucial role in fueling the development of machine learning (ML) Since the emergence of the ImageNet dataset and the AlexNet model in 2012, the size of new open-source labeled vision datasets has remained roughly constant. Only a minority of publications in the computer vision community tackle supervised learning on datasets that are orders of magnitude larger than Imagenet.
  arXiv  Detail & Related papers  (2021-07-31T00:08:21Z)
• Deflating Dataset Bias Using Synthetic Data Augmentation [8.509201763744246]
  State-of-the-art methods for most vision tasks for Autonomous Vehicles (AVs) rely on supervised learning. The goal of this paper is to investigate the use of targeted synthetic data augmentation for filling gaps in real datasets for vision tasks. Empirical studies on three different computer vision tasks of practical use to AVs consistently show that having synthetic data in the training mix provides a significant boost in cross-dataset generalization performance.
  arXiv  Detail & Related papers  (2020-04-28T21:56:10Z)

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.