RetailKLIP : Finetuning OpenCLIP backbone using metric learning on a single GPU for Zero-shot retail product image classification
This addresses the resource-intensive need for retraining in real-world retail applications like self-checkout stores, though it is incremental as it builds on existing CLIP and metric learning techniques.
The paper tackles the problem of frequent retraining needed for zero-shot retail product image classification by proposing a method to finetune a CLIP vision encoder for nearest neighbor classification, achieving accuracy close to or exceeding full finetuning.
Retail product or packaged grocery goods images need to classified in various computer vision applications like self checkout stores, supply chain automation and retail execution evaluation. Previous works explore ways to finetune deep models for this purpose. But because of the fact that finetuning a large model or even linear layer for a pretrained backbone requires to run at least a few epochs of gradient descent for every new retail product added in classification range, frequent retrainings are needed in a real world scenario. In this work, we propose finetuning the vision encoder of a CLIP model in a way that its embeddings can be easily used for nearest neighbor based classification, while also getting accuracy close to or exceeding full finetuning. A nearest neighbor based classifier needs no incremental training for new products, thus saving resources and wait time.