Alviss

The traditional model upgrading paradigm for retrieval requires recomputing all gallery embeddings before deploying the new model (dubbed as "backfilling"), which is quite expensive and time-consuming considering billions of instances in industrial applications. BCT presents the first step towards backward-compatible model upgrades to get rid of backfilling. It is workable but leaves the new model...

Remote Sensing, Vol. 14, Pages 5420: A Generative Adversarial Network for Pixel Scale Lunar DEM Generation from High Resolution Monocular Imagery and Low Resolution DEM Remote Sensing doi: 10.3390/rs14215420 Authors: Yang Liu Yexin Wang Kaichang Di Man Peng Wenhui Wan Zhaoqin Liu Digital elevation models (DEMs) provide fundamental data for scientific and engineering applications in lunar explorati...

Intellectual property protection of deep neural networks is receiving attention from more and more researchers, and the latest research applies model watermarking to generative models for image processing. However, the existing watermarking methods designed for generative models do not take into account the effects of different channels of sample images on watermarking. As a result, the watermarki...

Measurement and Control, Ahead of Print. Stabilizing the purchase cost of metal raw materials is of great significance to the metal manufacturing industry. Most enterprises use futures hedging strategies to cope with the risks arising from fluctuations in the prices of metal raw materials. However, the difference between spot and futures prices of metals makes it impossible to fully control the ri...

The task of privacy-preserving model upgrades in image retrieval desires to reap the benefits of rapidly evolving new models without accessing the raw gallery images. A pioneering work introduced backward-compatible training, where the new model can be directly deployed in a backfill-free manner, id est, the new query can be directly compared to the old gallery features. Despite a possible solutio...

Spatio-temporal representation learning is critical for video self-supervised representation. Recent approaches mainly use contrastive learning and pretext tasks. However, these approaches learn representation by discriminating sampled instances via feature similarity in the latent space while ignoring the intermediate state of the learned representations, which limits the overall performance. In ...

Text logo design heavily relies on the creativity and expertise of professional designers, in which arranging element layouts is one of the most important procedures. However, few attention has been paid to this task which needs to take many factors (e.g., fonts, linguistics, topics, etc.) into consideration. In this paper, we propose a content-aware layout generation network which takes glyph ima...

Objective To detect the influences of postoperative out of bed activity restriction on recurrence rate, low back and leg pain, functional rehabilitation after percutaneous endoscopic lumbar discectomy (PELD). Method In this research, 213 patients with lumbar intervertebral disc herniation (LDH) who underwent PELD were divided into the out of bed activity restriction group and out of bed activity n...

Conventional model upgrades for visual search systems require offline refresh of gallery features by feeding gallery images into new models (dubbed as "backfill"), which is time-consuming and expensive, especially in large-scale applications. The task of backward-compatible representation learning is therefore introduced to support backfill-free model upgrades, where the new query features are int...