Search Results for author: Dmitry Kislyuk

Found 6 papers, 0 papers with code

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

no code implementations12 Aug 2021 Josh Beal, Hao-Yu Wu, Dong Huk Park, Andrew Zhai, Dmitry Kislyuk

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.

Ranked #21 on Image Classification on ObjectNet (using extra training data)

Image Classification Multi-Task Learning +1

Toward Transformer-Based Object Detection

no code implementations17 Dec 2020 Josh Beal, Eric Kim, Eric Tzeng, Dong Huk Park, Andrew Zhai, Dmitry Kislyuk

The Vision Transformer was the first major attempt to apply a pure transformer model directly to images as input, demonstrating that as compared to convolutional networks, transformer-based architectures can achieve competitive results on benchmark classification tasks.

Natural Language Processing object-detection +1

Visual Discovery at Pinterest

no code implementations15 Feb 2017 Andrew Zhai, Dmitry Kislyuk, Yushi Jing, Michael Feng, Eric Tzeng, Jeff Donahue, Yue Li Du, Trevor Darrell

Over the past three years Pinterest has experimented with several visual search and recommendation services, including Related Pins (2014), Similar Looks (2015), Flashlight (2016) and Lens (2017).

object-detection Object Detection

Human Curation and Convnets: Powering Item-to-Item Recommendations on Pinterest

no code implementations12 Nov 2015 Dmitry Kislyuk, Yuchen Liu, David Liu, Eric Tzeng, Yushi Jing

This paper presents Pinterest Related Pins, an item-to-item recommendation system that combines collaborative filtering with content-based ranking.

Collaborative Filtering

Visual Search at Pinterest

no code implementations28 May 2015 Yushi Jing, David Liu, Dmitry Kislyuk, Andrew Zhai, Jiajing Xu, Jeff Donahue, Sarah Tavel

We demonstrate that, with the availability of distributed computation platforms such as Amazon Web Services and open-source tools, it is possible for a small engineering team to build, launch and maintain a cost-effective, large-scale visual search system with widely available tools.

Cannot find the paper you are looking for? You can Submit a new open access paper.