Vision Models Can Be Efficiently Specialized via Few-Shot Task-Aware Compression

• Published in: arXiv.org 2023-03
• Main Authors: Kuznedelev, Denis, Tabesh, Soroush, Noorbakhsh, Kimia, Frantar, Elias, Beery, Sara, Kurtic, Eldar, Alistarh, Dan
• Format: Article
• Language: English
• Subjects: Classification; Computing costs; Mathematical models; Parameters
• ISSN: 2331-8422

Recent vision architectures and self-supervised training methods enable vision models that are extremely accurate and general, but come with massive parameter and computational costs. In practical settings, such as camera traps, users have limited resources, and may fine-tune a pretrained model on (often limited) data from a small set of specific categories of interest. These users may wish to make use of modern, highly-accurate models, but are often computationally constrained. To address this, we ask: can we quickly compress large generalist models into accurate and efficient specialists? For this, we propose a simple and versatile technique called Few-Shot Task-Aware Compression (TACO). Given a large vision model that is pretrained to be accurate on a broad task, such as classification over ImageNet-22K, TACO produces a smaller model that is accurate on specialized tasks, such as classification across vehicle types or animal species. Crucially, TACO works in few-shot fashion, i.e. only a few task-specific samples are used, and the procedure has low computational overheads. We validate TACO on highly-accurate ResNet, ViT/DeiT, and ConvNeXt models, originally trained on ImageNet, LAION, or iNaturalist, which we specialize and compress to a diverse set of "downstream" subtasks. TACO can reduce the number of non-zero parameters in existing models by up to 20x relative to the original models, leading to inference speedups of up to 3\(\times\), while remaining accuracy-competitive with the uncompressed models on the specialized tasks.