Content-Based Image Retrieval
31 papers with code • 1 benchmarks • 5 datasets
Content-Based Image Retrieval is a well studied problem in computer vision, with retrieval problems generally divided into two groups: category-level retrieval and instance-level retrieval. Given a query image of the Sydney Harbour bridge, for instance, category-level retrieval aims to find any bridge in a given dataset of images, whilst instance-level retrieval must find the Sydney Harbour bridge to be considered a match.
Source: Camera Obscurer: Generative Art for Design Inspiration
Benchmarks
These leaderboards are used to track progress in Content-Based Image Retrieval
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Oxford5k
PS-Battles
GPR1200
European Flood 2013 Dataset
INRIA Holidays Dataset
Latest papers
Leveraging Foundation Models for Content-Based Medical Image Retrieval in Radiology
mic-dkfz/foundation-models-for-cbmir
•
•
Despite these challenges, our research underscores the vast potential of foundation models for CBIR in radiology, proposing a shift towards versatile, general-purpose medical image retrieval systems that do not require specific tuning.
Exploring Masked Autoencoders for Sensor-Agnostic Image Retrieval in Remote Sensing
jakhac/csmae
•
•
We finally derive a guideline to exploit masked image modeling for uni-modal and cross-modal CBIR problems in RS.
Integrating Visual and Semantic Similarity Using Hierarchies for Image Retrieval
vaishwarya96/hierarchy-image-retrieval
•
•
Most of the research in content-based image retrieval (CBIR) focus on developing robust feature representations that can effectively retrieve instances from a database of images that are visually similar to a query.
iQPP: A Benchmark for Image Query Performance Prediction
eduard6421/iqpp
•
•
To date, query performance prediction (QPP) in the context of content-based image retrieval remains a largely unexplored task, especially in the query-by-example scenario, where the query is an image.
A clinically motivated self-supervised approach for content-based image retrieval of CT liver images
wickstrom/relax
•
•
We address these limitations by (1) proposing a self-supervised learning framework that incorporates domain-knowledge into the training procedure and (2) providing the first representation learning explainability analysis in the context of CBIR of CT liver images.
Conditioned and Composed Image Retrieval Combining and Partially Fine-Tuning CLIP-Based Features
ABaldrati/CLIP4Cir
•
•
CVPRW 2022
The proposed method is based on an initial training stage where a simple combination of visual and textual features is used, to fine-tune the CLIP text encoder.
NORPPA: NOvel Ringed seal re-identification by Pelage Pattern Aggregation
We propose a method for Saimaa ringed seal (Pusa hispida saimensis) re-identification.
AdaTriplet: Adaptive Gradient Triplet Loss with Automatic Margin Learning for Forensic Medical Image Matching
CBIR with DNNs is generally solved by minimizing a ranking loss, such as Triplet loss (TL), computed on image representations extracted by a DNN from the original data.
Cross-Modality Sub-Image Retrieval using Contrastive Multimodal Image Representations
mida-group/crossmodal_imgretrieval
•
•
We propose a new application-independent content-based image retrieval (CBIR) system for reverse (sub-)image search across modalities, which combines deep learning to generate representations (embedding the different modalities in a common space) with classical feature extraction and bag-of-words models for efficient and reliable retrieval.
GPR1200: A Benchmark for General-Purpose Content-Based Image Retrieval
Even though it has extensively been shown that retrieval specific training of deep neural networks is beneficial for nearest neighbor image search quality, most of these models are trained and tested in the domain of landmarks images.
