Learning To Compress And Search Visual Data In Large-scale Systems

Abstract

The problem of high-dimensional and large-scale representation of visual data is addressed from an unsupervised learning perspective. The emphasis is put on discrete representations, where the description length can be measured in bits and hence the model capacity can be controlled. The algorithmic infrastructure is developed based on the synthesis and analysis prior models whose rate-distortion properties, as well as capacity vs. sample complexity trade-offs are carefully optimized. These models are then extended to multi-layers, namely the RRQ and the ML-STC frameworks, where the latter is further evolved as a powerful deep neural network architecture with fast and sample-efficient training and discrete representations. For the developed algorithms, three important applications are developed. First, the problem of large-scale similarity search in retrieval systems is addressed, where a double-stage solution is proposed leading to faster query times and shorter database storage. Secon

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyferdowsi2019learning

Related papers

• Compressible And Searchable: Ai-native Multi-modal Retrieval System With Learned Image Compression (2024)0.00
• Unsupervised Deep Hashing For Large-scale Visual Search (2016)9.59
• Visualizing Large-scale And High-dimensional Data (2016)18.48
• Exploiting Local Indexing And Deep Feature Confidence Scores For Fast Image-to-video Search (2018)2.26
• Deep Learning For Image Search And Retrieval In Large Remote Sensing Archives (2020)10.74
• Fast, Compact And Highly Scalable Visual Place Recognition Through Sequence-based Matching Of Overloaded Representations (2020)9.41
• Exquisitor: Interactive Learning At Large (2019)0.00
• A Multimodal Deep Learning Framework For Scalable Content Based Visual Media Retrieval (2021)0.00