Learning Representations For Images With Hierarchical Labels

04/02/2020
by   Ankit Dhall, et al.
4

Image classification has been studied extensively but there has been limited work in the direction of using non-conventional, external guidance other than traditional image-label pairs to train such models. In this thesis we present a set of methods to leverage information about the semantic hierarchy induced by class labels. In the first part of the thesis, we inject label-hierarchy knowledge to an arbitrary classifier and empirically show that availability of such external semantic information in conjunction with the visual semantics from images boosts overall performance. Taking a step further in this direction, we model more explicitly the label-label and label-image interactions by using order-preserving embedding-based models, prevalent in natural language, and tailor them to the domain of computer vision to perform image classification. Although, contrasting in nature, both the CNN-classifiers injected with hierarchical information, and the embedding-based models outperform a hierarchy-agnostic model on the newly presented, real-world ETH Entomological Collection image dataset.

READ FULL TEXT

page 11

page 12

research
04/02/2020

Hierarchical Image Classification using Entailment Cone Embeddings

Image classification has been studied extensively, but there has been li...
research
11/17/2019

Learning with Hierarchical Complement Objective

Label hierarchies widely exist in many vision-related problems, ranging ...
research
07/22/2020

Angle-based hierarchical classification using exact label embedding

Hierarchical classification problems are commonly seen in practice. Howe...
research
08/01/2023

Beyond One-Hot-Encoding: Injecting Semantics to Drive Image Classifiers

Images are loaded with semantic information that pertains to real-world ...
research
12/14/2015

Semantic-enriched Visual Vocabulary Construction in a Weakly Supervised Context

One of the prevalent learning tasks involving images is content-based im...
research
11/01/2021

Hierarchical Image Classification with A Literally Toy Dataset

Unsupervised domain adaptation (UDA) in image classification remains a b...
research
08/28/2020

Semantics Preserving Hierarchy based Retrieval of Indian heritage monuments

Monument classification can be performed on the basis of their appearanc...

Please sign up or login with your details

Forgot password? Click here to reset