The Image Calculator: 10x Faster Image-AI Inference by Replacing JPEG with Self-designing Storage Format

Summary: Image Calculator: a self-designing image storage format that adapts to the AI task by exploring a large space of candidate formats with composite performance models. Outperforms JPEG variants with up to 14.2x faster inference and 8.2x storage reduction, with minimal accuracy loss, across diverse data, models, and hardware. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 6861
Venue: SIGMOD
Year: 2024
Pagerank: 4.2805224e-05
Overall Rank: 9,806 | 31.79%
DOI: 10.1145/3639307

Incoming Non-self Citations Over Time

Authors

1. Utku Sirin
2. Stratos Idreos

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
8,627	Limousine: Blending Learned and Classical Indexes to Self-Design Larger-than-Memory Cloud Storage Engines	2024	SIGMOD	4.4829101e-05
9,677	Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving	2025	SIGMOD	4.3047774e-05
9,690	Frequency-Store: Scaling Image AI by A Column-Store for Images	2025	CIDR	4.3037432e-05

Outgoing Citations (Sorted by Pagerank)

Showing 22 of 72 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
6,471	Dynamic Parameter Allocation in Parameter Servers	2020	VLDB	5.0511668e-05
6,738	Agile and Accurate CTR Prediction Model Training for Massive-Scale Online Advertising Systems	2021	SIGMOD	4.9452647e-05
7,269	Serverless Data Science - Are We There Yet? A Case Study of Model Serving	2022	SIGMOD	4.7815303e-05
7,369	Using VDMS to Index and Search 100M Images	2021	VLDB	4.750437e-05
7,656	Nautilus: An Optimized System for Deep Transfer Learning over Evolving Training Datasets	2022	SIGMOD	4.6871575e-05
7,719	WindTunnel: Towards Differentiable ML Pipelines Beyond a Single Model	2022	VLDB	4.6686188e-05
7,922	Video-zilla: An Indexing Layer for Large-Scale Video Analytics	2022	SIGMOD	4.615892e-05
8,082	Tastes Great! Less Filling! High Performance and Accurate Training Data Collection for Self-Driving Database Management Systems	2022	SIGMOD	4.5905454e-05
8,257	Automating and Optimizing Data-Centric What-If Analyses on Native Machine Learning Pipelines	2023	SIGMOD	4.5487511e-05
8,514	UPLIFT: Parallelization Strategies for Feature Transformations in Machine Learning Workloads	2022	VLDB	4.4944285e-05
8,627	Limousine: Blending Learned and Classical Indexes to Self-Design Larger-than-Memory Cloud Storage Engines	2024	SIGMOD	4.4829101e-05
8,700	SeeSaw: Interactive Ad-hoc Search Over Image Databases	2023	SIGMOD	4.4656647e-05
8,808	FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement	2023	SIGMOD	4.4454035e-05
9,094	FEC: Efficient Deep Recommendation Model Training with Flexible Embedding Communication	2023	SIGMOD	4.3980444e-05
9,192	Hyper-Tune: Towards Efficient Hyper-parameter Tuning at Scale	2022	VLDB	4.3765131e-05
9,265	COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compression	2022	VLDB	4.3667558e-05
9,296	Controlled Intentional Degradation in Analytical Video Systems	2022	SIGMOD	4.3599613e-05
9,466	Serenade - Low-Latency Session-Based Recommendation in e-Commerce at Scale	2022	SIGMOD	4.3349007e-05
9,705	ETO: Accelerating Optimization of DNN Operators by High-Performance Tensor Program Reuse	2022	VLDB	4.2994163e-05
9,964	Classifier Construction Under Budget Constraints	2022	SIGMOD	4.2269436e-05
9,965	Distributed Learning of Fully Connected Neural Networks using Independent Subnet Training	2022	VLDB	4.2269436e-05
9,966	Towards Communication-efficient Vertical Federated Learning Training via Cache-enabled Local Updates	2022	VLDB	4.2269436e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
1,967	Compressed Linear Algebra for Large-Scale Machine Learning	2016	VLDB	9.9131712e-05
3,745	DeepSqueeze: Deep Semantic Compression for Tabular Data	2020	SIGMOD	6.7926132e-05
10,663	Inference-friendly Graph Compression for Graph Neural Networks	2025	VLDB	4.1945683e-05
2,863	Incremental and Approximate Inference for Faster Occlusion-based Deep CNN Explanations	2019	SIGMOD	7.9877991e-05
10,499	Privacy and Accuracy-Aware AI/ML Model Deduplication	2025	SIGMOD	4.1945683e-05
13,142	Alphabets, Grammars, Calculators, and the End of Hand-Crafted Systems	2025	VLDB	-
10,286	QStore: Quantization-Aware Compressed Model Storage	2026	VLDB	4.1945683e-05
3,293	Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics	2021	VLDB	7.2629834e-05
6,057	Progressive Compressed Records: Taking a Byte out of Deep Learning Data	2021	VLDB	5.2317752e-05
9,690	Frequency-Store: Scaling Image AI by A Column-Store for Images	2025	CIDR	4.3037432e-05