paper-with-me

Papers

Learning Compatible Embeddings

2021-08-04 · ICCV 2021 10 · Qiang Meng, Chixiang Zhang, Xiaoqiang Xu, Feng Zhou

Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. Previous related works usually leverage losses used in knowledge distillation which can cause performance degradations or not guarantee compatibility. To address these issues, we propose a general framework called Learning Compatible Embeddings (LCE) which is applicable for both cross model compatibility and compatible training in direct/forward/backward manners. Our compatibility is achieved by aligning class centers between models directly or via a transformation, and restricting more compact intra-class distributions for the new model. Experiments are conducted in extensive scenarios such as changes of training dataset, loss functions, network architectures as well as feature dimensions, and demonstrate that LCE efficiently enables model compatibility with marginal sacrifices of accuracies. The code will be available at https://github.com/IrvingMeng/LCE.

📄 PDF Abstract BibTeX arXiv:2108.01958

Code (1)

IrvingMeng/LCE 공식 구현 pytorch

Tasks

Knowledge DistillationRetrieval

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Learning Backward Compatible Embeddings

2022-06-07 · Weihua Hu, Rajas Bansal, Kaidi Cao, Nikhil Rao 외

Embeddings, low-dimensional vector representation of objects, are fundamental in building modern machine learning systems. In industrial settings, there is usually an embedding team that trains an embedding model to solv…

Fraud DetectionProduct RecommendationRecommendation Systems

Towards Backward-Compatible Representation Learning

2020-03-26 · CVPR 2020 6 · Yantao Shen, Yuanjun Xiong, Wei Xia, Stefano Soatto

We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network architectures and loss functions. Compatib…

Face RecognitionRepresentation Learning

Privacy-Preserving Model Upgrades with Bidirectional Compatible Training in Image Retrieval

2022-04-29 · Shupeng Su, Binjie Zhang, Yixiao Ge, Xuyuan Xu 외

The task of privacy-preserving model upgrades in image retrieval desires to reap the benefits of rapidly evolving new models without accessing the raw gallery images. A pioneering work introduced backward-compatible trai…

Image RetrievalPrivacy PreservingRetrieval

Metric Compatible Training for Online Backfilling in Large-Scale Retrieval

2023-01-10 · Seonguk Seo, Mustafa Gokhan Uzunbas, Bohyung Han, Sara Cao 외

Backfilling is the process of re-extracting all gallery embeddings from upgraded models in image retrieval systems. It inevitably requires a prohibitively large amount of computational cost and even entails the downtime …

Contrastive LearningImage RetrievalRetrieval

Adaptive Global and Fine-Grained Perceptual Fusion for MLLM Embeddings Compatible with Hard Negative Amplification

2026-02-05 · Lexiang Hu, Youze Xue, Dian Li, Gang Liu 외 arxiv

Multimodal embeddings serve as a bridge for aligning vision and language, with the two primary implementations -- CLIP-based and MLLM-based embedding models -- both limited to capturing only global semantic information. …