Comparison Knowledge Translation for Generalizable Image Classification

05/07/2022
by   Zunlei Feng, et al.
0

Deep learning has recently achieved remarkable performance in image classification tasks, which depends heavily on massive annotation. However, the classification mechanism of existing deep learning models seems to contrast to humans' recognition mechanism. With only a glance at an image of the object even unknown type, humans can quickly and precisely find other same category objects from massive images, which benefits from daily recognition of various objects. In this paper, we attempt to build a generalizable framework that emulates the humans' recognition mechanism in the image classification task, hoping to improve the classification performance on unseen categories with the support of annotations of other categories. Specifically, we investigate a new task termed Comparison Knowledge Translation (CKT). Given a set of fully labeled categories, CKT aims to translate the comparison knowledge learned from the labeled categories to a set of novel categories. To this end, we put forward a Comparison Classification Translation Network (CCT-Net), which comprises a comparison classifier and a matching discriminator. The comparison classifier is devised to classify whether two images belong to the same category or not, while the matching discriminator works together in an adversarial manner to ensure whether classified results match the truth. Exhaustive experiments show that CCT-Net achieves surprising generalization ability on unseen categories and SOTA performance on target categories.

READ FULL TEXT
research
08/01/2021

Visual Boundary Knowledge Translation for Foreground Segmentation

When confronted with objects of unknown types in an image, humans can ef...
research
06/02/2022

Leveraging Systematic Knowledge of 2D Transformations

The existing deep learning models suffer from out-of-distribution (o.o.d...
research
08/01/2021

Boundary Knowledge Translation based Reference Semantic Segmentation

Given a reference object of an unknown type in an image, human observers...
research
06/10/2015

LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop

While there has been remarkable progress in the performance of visual re...
research
09/24/2019

Image Recognition using Region Creep

This paper describes a new type of image classifier that uses a shallow ...
research
11/21/2022

Neural Dependencies Emerging from Learning Massive Categories

This work presents two astonishing findings on neural networks learned f...
research
11/25/2020

Match Them Up: Visually Explainable Few-shot Image Classification

Few-shot learning (FSL) approaches are usually based on an assumption th...

Please sign up or login with your details

Forgot password? Click here to reset