Instance Image Retrieval By Learning Purely From Within The Dataset

Abstract

Quality feature representation is key to instance image retrieval. To attain it, existing methods usually resort to a deep model pre-trained on benchmark datasets or even fine-tune the model with a task-dependent labelled auxiliary dataset. Although achieving promising results, this approach is restricted by two issues: 1) the domain gap between benchmark datasets and the dataset of a given retrieval task; 2) the required auxiliary dataset cannot be readily obtained. In light of this situation, this work looks into a different approach which has not been well investigated for instance image retrieval previously: \{can we learn feature representation \textit\{specific to\} a given retrieval task in order to achieve excellent retrieval?\} Our finding is encouraging. By adding an object proposal generator to generate image regions for self-supervised learning, the investigated approach can successfully learn feature representation specific to a given dataset for retrieval. This representa

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2022instance

Related papers

• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• Feature Representation Learning For Unsupervised Cross-domain Image Retrieval (2022)11.46
• End-to-end Learning Of Deep Visual Representations For Image Retrieval (2016)19.66
• Connecting Images Through Time And Sources: Introducing Low-data, Heterogeneous Instance Retrieval (2021)0.00
• Class-weighted Convolutional Features For Visual Instance Search (2017)12.81
• Learning Super-features For Image Retrieval (2022)4.31
• Towards Unsupervised Sketch-based Image Retrieval (2021)0.00
• Irgen: Generative Modeling For Image Retrieval (2023)7.16