Field-Guide-Inspired Zero-Shot Learning

08/24/2021
by   Utkarsh Mall, et al.
5

Modern recognition systems require large amounts of supervision to achieve accuracy. Adapting to new domains requires significant data from experts, which is onerous and can become too expensive. Zero-shot learning requires an annotated set of attributes for a novel category. Annotating the full set of attributes for a novel category proves to be a tedious and expensive task in deployment. This is especially the case when the recognition domain is an expert domain. We introduce a new field-guide-inspired approach to zero-shot annotation where the learner model interactively asks for the most useful attributes that define a class. We evaluate our method on classification benchmarks with attribute annotations like CUB, SUN, and AWA2 and show that our model achieves the performance of a model with full annotations at the cost of a significantly fewer number of annotations. Since the time of experts is precious, decreasing annotation cost can be very valuable for real-world deployment.

READ FULL TEXT

page 4

page 8

page 11

page 14

page 15

research
12/11/2018

Zero-Shot Learning with Sparse Attribute Propagation

Zero-shot learning (ZSL) aims to recognize a set of unseen classes witho...
research
11/28/2021

Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis

Most of the existing algorithms for zero-shot classification problems ty...
research
10/14/2014

Zero-Shot Object Recognition System based on Topic Model

Object recognition systems usually require fully complete manually label...
research
10/15/2016

Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning

Collecting training images for all visual categories is not only expensi...
research
03/29/2016

Multi-Cue Zero-Shot Learning with Strong Supervision

Scaling up visual category recognition to large numbers of classes remai...
research
05/20/2019

Learning Image-Specific Attributes by Hyperbolic Neighborhood Graph Propagation

As a kind of semantic representation of visual object descriptions, attr...
research
09/08/2022

FETA: Towards Specializing Foundation Models for Expert Task Applications

Foundation Models (FMs) have demonstrated unprecedented capabilities inc...

Please sign up or login with your details

Forgot password? Click here to reset