Fine-Grained Visual Categorization via Multi-stage Metric Learning

02/03/2014
by   Qi Qian, et al.
0

Fine-grained visual categorization (FGVC) is to categorize objects into subordinate classes instead of basic classes. One major challenge in FGVC is the co-occurrence of two issues: 1) many subordinate classes are highly correlated and are difficult to distinguish, and 2) there exists the large intra-class variation (e.g., due to object pose). This paper proposes to explicitly address the above two issues via distance metric learning (DML). DML addresses the first issue by learning an embedding so that data points from the same class will be pulled together while those from different classes should be pushed apart from each other; and it addresses the second issue by allowing the flexibility that only a portion of the neighbors (not all data points) from the same class need to be pulled together. However, feature representation of an image is often high dimensional, and DML is known to have difficulty in dealing with high dimensional feature vectors since it would require O(d^2) for storage and O(d^3) for optimization. To this end, we proposed a multi-stage metric learning framework that divides the large-scale high dimensional learning problem to a series of simple subproblems, achieving O(d) computational complexity. The empirical study with FVGC benchmark datasets verifies that our method is both effective and efficient compared to the state-of-the-art FGVC approaches.

READ FULL TEXT

page 1

page 7

research
12/16/2015

Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop

Existing fine-grained visual categorization methods often suffer from th...
research
03/01/2017

Incorporating Intra-Class Variance to Fine-Grained Visual Recognition

Fine-grained visual recognition aims to capture discriminative character...
research
07/14/2022

Learning Discriminative Representation via Metric Learning for Imbalanced Medical Image Classification

Data imbalance between common and rare diseases during model training of...
research
03/11/2020

Channel Interaction Networks for Fine-Grained Image Categorization

Fine-grained image categorization is challenging due to the subtle inter...
research
01/21/2022

Distance-Ratio-Based Formulation for Metric Learning

In metric learning, the goal is to learn an embedding so that data point...
research
08/11/2022

Regressing Relative Fine-Grained Change for Sub-Groups in Unreliable Heterogeneous Data Through Deep Multi-Task Metric Learning

Fine-Grained Change Detection and Regression Analysis are essential in m...
research
05/18/2018

Tree Edit Distance Learning via Adaptive Symbol Embeddings: Supplementary Materials and Results

Metric learning has the aim to improve classification accuracy by learni...

Please sign up or login with your details

Forgot password? Click here to reset