Unicom: Universal And Compact Representation Learning For Image Retrieval

Abstract

Modern image retrieval methods typically rely on fine-tuning pre-trained encoders to extract image-level descriptors. However, the most widely used models are pre-trained on ImageNet-1K with limited classes. The pre-trained feature representation is therefore not universal enough to generalize well to the diverse open-world classes. In this paper, we first cluster the large-scale LAION400M into one million pseudo classes based on the joint textual and visual features extracted by the CLIP model. Due to the confusion of label granularity, the automatically clustered dataset inevitably contains heavy inter-class conflict. To alleviate such conflict, we randomly select partial inter-class prototypes to construct the margin-based softmax loss. To further enhance the low-dimensional feature representation, we randomly select partial feature dimensions when calculating the similarities between embeddings and class-wise prototypes. The dual random partial selections are with respect to the cl

Stats

• citations0
• S2 citations—
• github stars703
• HF likes0
• heat score5.70
• arxiv keyan2023unicom

Related papers

• Coarse-to-fine: Learning Compact Discriminative Representation For Single-stage Image Retrieval (2023)9.35
• Feature Representation Learning For Unsupervised Cross-domain Image Retrieval (2022)11.46
• Efficient And Discriminative Image Feature Extraction For Universal Image Retrieval (2024)4.94
• From Selective Deep Convolutional Features To Compact Binary Representations For Image Retrieval (2018)10.35
• Unifier: A Unified Retriever For Large-scale Retrieval (2022)7.50
• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• Unicvr: From Alignment To Reranking For Unified Zero-shot Composed Visual Retrieval (2026)0.00
• Unified Representation Learning For Cross Model Compatibility (2020)5.24