A comparison of dense region detectors for image search and fine-grained classification
arXiv:1410.8151 · doi:10.1109/TIP.2015.2423557
Abstract
We consider a pipeline for image classification or search based on coding approaches like Bag of Words or Fisher vectors. In this context, the most common approach is to extract the image patches regularly in a dense manner on several scales. This paper proposes and evaluates alternative choices to extract patches densely. Beyond simple strategies derived from regular interest region detectors, we propose approaches based on super-pixels, edges, and a bank of Zernike filters used as detectors. The different approaches are evaluated on recent image retrieval and fine-grain classification benchmarks. Our results show that the regular dense detector is outperformed by other methods in most situations, leading us to improve the state of the art in comparable setups on standard retrieval and fined-grain benchmarks. As a byproduct of our study, we show that existing methods for blob and super-pixel extraction achieve high accuracy if the patches are extracted along the edges and not around the detected regions.
arXiv commentAccepted to IEEE Transactions on Image Processing
References in corpus (4)
Cited by in corpus (8)
- Object-Part Attention Model for Fine-grained Image Classification
- Delving Deep into Label Smoothing
- Weakly Supervised Fine-Grained Image Categorization
- Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification
- A Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation
- Analysis of feature detector and descriptor combinations with a localization experiment for various performance metrics
- A Principled Design of Image Representation: Towards Forensic Tasks
- Dynamicity and Durability in Scalable Visual Instance Search