Learning Rotation Invariant Features For Cryogenic Electron Microscopy Image Reconstruction

Bibas, Koby; Weiss-Dicker, Gili; Cohen, Dana; Cahan, Noa; Greenspan, Hayit

doi:10.1109/isbi48211.2021.9433789

Cited by 1 publication

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A large variety of CF models that use item embeddings were proposed over the last fifteen years, and we experimented with several landmark CF methods. Among other methods, we considered Bayesian Personalized Ranking (BPR) as a more traditional model [44] and Variational Autoencoders (VAE) [34], which is a state-of-the-art technique 6 . Motivated by [41], the last layer of the decoder in the autoencoder architecture serves as the item embedding matrix 𝑄.…”

Section: Experiments Setupmentioning

confidence: 99%

“…of image understanding and an area in which we observed substantial progress in recent years, largely due to innovations in deep learning [6,14,31]. Nowadays, one standard way of developing an image categorization solution for a specific task or application is to rely on pre-trained image models and to fine-tune them with application-specific data for the particular problem at hand.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Collaborative Image Understanding

Bibas

Shalom²,

Jannach

2022

Proceedings of the 31st ACM International Conference on Information &Amp; Knowledge Management

Self Cite

View full text Add to dashboard Cite

Automatically understanding the contents of an image is a highly relevant problem in practice. In e-commerce and social media settings, for example, a common problem is to automatically categorize user-provided pictures. Nowadays, a standard approach is to fine-tune pre-trained image models with application-specific data. Besides images, organizations however often also collect collaborative signals in the context of their application, in particular how users interacted with the provided online content, e.g., in forms of viewing, rating, or tagging. Such signals are commonly used for item recommendation, typically by deriving latent user and item representations from the data. In this work, we show that such collaborative information can be leveraged to improve the classification process of new images. Specifically, we propose a multitask learning framework, where the auxiliary task is to reconstruct collaborative latent item representations. A series of experiments on datasets from e-commerce and social media demonstrates that considering collaborative signals helps to significantly improve the performance of the main task of image classification by up to 9.1%.

show abstract

Section: Experiments Setupmentioning

confidence: 99%

mentioning

confidence: 99%