Efficient Large-Scale Visual Representation Learning And Evaluation
Not on the map. Why?
Abstract (arXiv)
Efficiently learning visual representations of items is vital for large-scale recommendations. In this article we compare several pretrained efficient backbone architectures, both in the convolutional neural network (CNN) and in the vision transformer (ViT) family. 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. To this end, we present a novel multilingual text-to-image generative offline evaluation method for visually similar recommendation systems. Finally, we include online results from deployed machine learning systems in production on a large scale e-commerce platform.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 46 of its 60 references that are in the map. First posted on arXiv 22 May 2023.
Builds on
46 of 60 references.
References · 46
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
34 more
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2017Billion-scale similarity search with GPUscited by 2,477
- 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
- 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 671
- 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 636
- 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
- 2021MetaFormer Is Actually What You Need for Visioncited by 523
- 2014Deep metric learning using Triplet networkcited by 421
- 2021Understanding Robustness of Transformers for Image Classificationcited by 250
- 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 240
- 2023Stable Bias: Analyzing Societal Representations in Diffusion Modelscited by 225
- 2023Token Merging for Fast Stable Diffusioncited by 220
- 2022Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Modelscited by 179
- 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 161
- 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 153
- 2023Cones: Concept Neurons in Diffusion Models for Customized Generationcited by 150
- 2021Efficient Self-supervised Vision Transformers for Representation Learningcited by 149
- 2023SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applicationscited by 66
- 2022PinnerFormer: Sequence Modeling for User Representation at Pinterestcited by 57
- 2022Hydra Attention: Efficient Attention with Many Headscited by 55
- 2017Label Efficient Learning of Transferable Representations across Domains and Taskscited by 49
- 2021Visual Search at Alibabacited by 27
- 2017Visual Search at eBaycited by 25
- 2019Learning a Unified Embedding for Visual Search at Pinterestcited by 25
- 2021Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representationscited by 24
- 2022ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterestcited by 23
- 2018Complete the Look: Scene-based Complementary Product Recommendationcited by 21
- 2013Efficient Learning of Domain-invariant Image Representationscited by 20
- 2015Visual Search at Pinterestcited by 19
- 2017Visual Discovery at Pinterestcited by 11
- 2020Bootstrapping Complete The Look at Pinterestcited by 6
- 2023adSformers: Personalization from Short-Term Sequences and Diversity of Representations in Etsy Adscited by 4
- 2020Multilingual Evidence Retrieval and Fact Verification to Combat Global Disinformation: The Power of Polyglotismcited by 3
- 2021Learning to Match Job Candidates Using Multilingual Bi-Encoder BERTcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.