Mask-Guided Feature Extraction and Augmentation for Ultra-Fine-Grained Visual Categorization

by   Zicheng Pan, et al.

While the fine-grained visual categorization (FGVC) problems have been greatly developed in the past years, the Ultra-fine-grained visual categorization (Ultra-FGVC) problems have been understudied. FGVC aims at classifying objects from the same species (very similar categories), while the Ultra-FGVC targets at more challenging problems of classifying images at an ultra-fine granularity where even human experts may fail to identify the visual difference. The challenges for Ultra-FGVC mainly comes from two aspects: one is that the Ultra-FGVC often arises overfitting problems due to the lack of training samples; and another lies in that the inter-class variance among images is much smaller than normal FGVC tasks, which makes it difficult to learn discriminative features for each class. To solve these challenges, a mask-guided feature extraction and feature augmentation method is proposed in this paper to extract discriminative and informative regions of images which are then used to augment the original feature map. The advantage of the proposed method is that the feature detection and extraction model only requires a small amount of target region samples with bounding boxes for training, then it can automatically locate the target area for a large number of images in the dataset at a high detection accuracy. Experimental results on two public datasets and ten state-of-the-art benchmark methods consistently demonstrate the effectiveness of the proposed method both visually and quantitatively.


page 1

page 5

page 7


A Compositional Feature Embedding and Similarity Metric for Ultra-Fine-Grained Visual Categorization

Fine-grained visual categorization (FGVC), which aims at classifying obj...

Mask guided attention for fine-grained patchy image classification

In this work, we present a novel mask guided attention (MGA) method for ...

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...

Attention for Fine-Grained Categorization

This paper presents experiments extending the work of Ba et al. (2014) o...

A Two-Layer Local Constrained Sparse Coding Method for Fine-Grained Visual Categorization

Fine-grained categories are more difficulty distinguished than generic c...

The Fishnet Open Images Database: A Dataset for Fish Detection and Fine-Grained Categorization in Fisheries

Camera-based electronic monitoring (EM) systems are increasingly being d...

Facing the Hard Problems in FGVC

In fine-grained visual categorization (FGVC), there is a near-singular f...

Please sign up or login with your details

Forgot password? Click here to reset