Relational Proxies: Emergent Relationships as Fine-Grained Discriminators

10/05/2022
by   Abhra Chaudhuri, et al.
4

Fine-grained categories that largely share the same set of parts cannot be discriminated based on part information alone, as they mostly differ in the way the local parts relate to the overall global structure of the object. We propose Relational Proxies, a novel approach that leverages the relational information between the global and local views of an object for encoding its semantic label. Starting with a rigorous formalization of the notion of distinguishability between fine-grained categories, we prove the necessary and sufficient conditions that a model must satisfy in order to learn the underlying decision boundaries in the fine-grained setting. We design Relational Proxies based on our theoretical findings and evaluate it on seven challenging fine-grained benchmark datasets and achieve state-of-the-art results on all of them, surpassing the performance of all existing works with a margin exceeding 4 on fine-grained distinguishability and obtain consistent results across multiple benchmarks. Implementation is available at https://github.com/abhrac/relational-proxies.

READ FULL TEXT

page 3

page 16

page 19

page 21

research
05/26/2020

Fine-Grained 3D Shape Classification with Hierarchical Part-View Attentions

Fine-grained 3D shape classification is important and research challengi...
research
03/30/2022

Fine-Grained Object Classification via Self-Supervised Pose Alignment

Semantic patterns of fine-grained objects are determined by subtle appea...
research
12/01/2022

On Utilizing Relationships for Transferable Few-Shot Fine-Grained Object Detection

State-of-the-art object detectors are fast and accurate, but they requir...
research
11/27/2018

FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery

We propose FineGAN, a novel unsupervised GAN framework, which disentangl...
research
09/24/2019

A Rule-Based Relational XML Access Control Model in the Presence of Authorization Conflicts

There is considerable amount of sensitive XML data stored in relational ...
research
06/08/2023

Coping with Change: Learning Invariant and Minimum Sufficient Representations for Fine-Grained Visual Categorization

Fine-grained visual categorization (FGVC) is a challenging task due to s...
research
04/29/2020

Asking without Telling: Exploring Latent Ontologies in Contextual Representations

The success of pretrained contextual encoders, such as ELMo and BERT, ha...

Please sign up or login with your details

Forgot password? Click here to reset