RECLIP: Resource-efficient CLIP by Training with Small Images
Abstract: We present RECLIP (Resource-efficient CLIP), a simple method that minimizes computational resource footprint for CLIP (Contrastive Language Image Pretraining). Inspired by the notion of coarse-to-fine in computer vision, we leverage small images to learn from large-scale language supervision efficiently, and finetune the model with high-resolution data in the end. Since the complexity of the vision transformer heavily depends on input image size, our approach significantly reduces the training resource requirements both in theory and in practice. Using the same batch size and training epoch, RECLIP achieves highly competitive zero-shot classification and image-text retrieval accuracy with 6 to 8× less computational resources and 7 to 9× fewer FLOPs than the base- line. Compared to the state-of-the-art contrastive learning methods, RECLIP demonstrates 5 to 59× training resource savings while maintaining highly competitive zero-shot classification and retrieval performance. Finally, RECLIP matches the state of the art in transfer learning to open-vocabulary detection tasks, achieving 32 APr on LVIS. We hope this work will pave the path for the broader research community to explore language supervised pretraining in resource-friendly settings.
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: * Update the abstract. * Include basic camera-ready version changes.
Supplementary Material: pdf
Assigned Action Editor: ~Xu_Tan1
Submission Number: 1051