Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations

• URL: http://arxiv.org/abs/2108.05887v1
• Date: Thu, 12 Aug 2021 17:58:56 GMT
• Title: Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations
• Authors: Josh Beal, Hao-Yu Wu, Dong Huk Park, Andrew Zhai, Dmitry Kislyuk
• Abstract summary: We describe how we generate a dataset with over a billion images via large weakly-supervised pretraining. We leverage Transformers to replace the traditional convolutional backbone. We show that large-scale Transformer-based pretraining provides significant benefits to industry computer vision applications.
• Score: 9.6221436745451
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large-scale pretraining of visual representations has led to state-of-the-art performance on a range of benchmark computer vision tasks, yet the benefits of these techniques at extreme scale in complex production systems has been relatively unexplored. We consider the case of a popular visual discovery product, where these representations are trained with multi-task learning, from use-case specific visual understanding (e.g. skin tone classification) to general representation learning for all visual content (e.g. embeddings for retrieval). In this work, we describe how we (1) generate a dataset with over a billion images via large weakly-supervised pretraining to improve the performance of these visual representations, and (2) leverage Transformers to replace the traditional convolutional backbone, with insights into both system and performance improvements, especially at 1B+ image scale. To support this backbone model, we detail a systematic approach to deriving weakly-supervised image annotations from heterogenous text signals, demonstrating the benefits of clustering techniques to handle the long-tail distribution of image labels. Through a comprehensive study of offline and online evaluation, we show that large-scale Transformer-based pretraining provides significant benefits to industry computer vision applications. The model is deployed in a production visual shopping system, with 36% improvement in top-1 relevance and 23% improvement in click-through volume. We conduct extensive experiments to better understand the empirical relationships between Transformer-based architectures, dataset scale, and the performance of production vision systems.

Related papers

• Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems [80.62854148838359]
  Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate. We use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data. Our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.
  arXiv  Detail & Related papers  (2024-03-23T22:32:06Z)
• Unveiling Backbone Effects in CLIP: Exploring Representational Synergies and Variances [49.631908848868505]
  Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. We investigate the differences in CLIP performance among various neural architectures. We propose a simple, yet effective approach to combine predictions from multiple backbones, leading to a notable performance boost of up to 6.34%.
  arXiv  Detail & Related papers  (2023-12-22T03:01:41Z)
• GPT4Image: Can Large Pre-trained Models Help Vision Models on Perception Tasks? [51.22096780511165]
  We present a new learning paradigm in which the knowledge extracted from large pre-trained models are utilized to help models like CNN and ViT learn enhanced representations. We feed detailed descriptions into a pre-trained encoder to extract text embeddings with rich semantic information that encodes the content of images.
  arXiv  Detail & Related papers  (2023-06-01T14:02:45Z)
• Efficient Large-Scale Visual Representation Learning And Evaluation [0.13192560874022083]
  We describe challenges in e-commerce vision applications at scale and highlight methods to efficiently train, evaluate, and serve visual representations. We present ablation studies evaluating visual representations in several downstream tasks. We include online results from deployed machine learning systems in production on a large scale e-commerce platform.
  arXiv  Detail & Related papers  (2023-05-22T18:25:03Z)
• Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model [97.9548609175831]
  We resort to plain vision transformers with about 100 million parameters and make the first attempt to propose large vision models customized for remote sensing tasks. Specifically, to handle the large image size and objects of various orientations in RS images, we propose a new rotated varied-size window attention. Experiments on detection tasks demonstrate the superiority of our model over all state-of-the-art models, achieving 81.16% mAP on the DOTA-V1.0 dataset.
  arXiv  Detail & Related papers  (2022-08-08T09:08:40Z)
• Three things everyone should know about Vision Transformers [67.30250766591405]
  transformer architectures have rapidly gained traction in computer vision. We offer three insights based on simple and easy to implement variants of vision transformers. We evaluate the impact of these design choices using the ImageNet-1k dataset, and confirm our findings on the ImageNet-v2 test set.
  arXiv  Detail & Related papers  (2022-03-18T08:23:03Z)
• ProFormer: Learning Data-efficient Representations of Body Movement with Prototype-based Feature Augmentation and Visual Transformers [31.908276711898548]
  Methods for data-efficient recognition from body poses increasingly leverage skeleton sequences structured as image-like arrays. We look at this paradigm from the perspective of transformer networks, for the first time exploring visual transformers as data-efficient encoders of skeleton movement. In our pipeline, body pose sequences cast as image-like representations are converted into patch embeddings and then passed to a visual transformer backbone optimized with deep metric learning.
  arXiv  Detail & Related papers  (2022-02-23T11:11:54Z)
• Efficient Self-supervised Vision Transformers for Representation Learning [86.57557009109411]
  We show that multi-stage architectures with sparse self-attentions can significantly reduce modeling complexity. We propose a new pre-training task of region matching which allows the model to capture fine-grained region dependencies. Our results show that combining the two techniques, EsViT achieves 81.3% top-1 on the ImageNet linear probe evaluation.
  arXiv  Detail & Related papers  (2021-06-17T19:57:33Z)
• Generative Adversarial Transformers [13.633811200719627]
  We introduce the GANsformer, a novel and efficient type of transformer, and explore it for the task of visual generative modeling. The network employs a bipartite structure that enables long-range interactions across the image, while maintaining computation of linearly efficiency. We show it achieves state-of-the-art results in terms of image quality and diversity, while enjoying fast learning and better data-efficiency.
  arXiv  Detail & Related papers  (2021-03-01T18:54:04Z)

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.