Learning for New Visual Environments with Limited Labels

01/25/2019
by   Pengkai Zhu, et al.
0

In computer vision applications, such as domain adaptation (DA), few shot learning (FSL) and zero-shot learning (ZSL), we encounter new objects and environments, for which insufficient examples exist to allow for training "models from scratch," and methods that adapt existing models, trained on the presented training environment, to the new scenario are required. We propose a novel visual attribute encoding method that encodes each image as a low-dimensional probability vector composed of prototypical part-type probabilities. The prototypes are learnt to be representative of all training data. At test-time we utilize this encoding as an input to a classifier. At test-time we freeze the encoder and only learn/adapt the classifier component to limited annotated labels in FSL; new semantic attributes in ZSL. We conduct extensive experiments on benchmark datasets. Our method outperforms state-of-art methods trained for the specific contexts (ZSL, FSL, DA).

READ FULL TEXT
research
04/17/2022

Learning Compositional Representations for Effective Low-Shot Generalization

We propose Recognition as Part Composition (RPC), an image encoding appr...
research
07/19/2018

Few-Shot Adaptation for Multimedia Semantic Indexing

We propose a few-shot adaptation framework, which bridges zero-shot lear...
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
08/22/2022

Reference-Limited Compositional Zero-Shot Learning

Compositional zero-shot learning (CZSL) refers to recognizing unseen com...
research
12/01/2021

Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learning

Current approaches to Zero-Shot Learning (ZSL) struggle to learn general...
research
09/02/2022

Learn to Adapt to New Environment from Past Experience and Few Pilot

In recent years, deep learning has been widely applied in communications...
research
11/28/2022

A Visual Active Search Framework for Geospatial Exploration

Many problems can be viewed as forms of geospatial search aided by aeria...

Please sign up or login with your details

Forgot password? Click here to reset