-
Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier
Long-tail recognition tackles the natural non-uniformly distributed data...
read it
-
Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective
This paper considers learning deep features from long-tailed data. We ob...
read it
-
Harnessing GANs for Addition of New Classes in VSR
It is an easy task for humans to learn and generalize a problem, perhaps...
read it
-
A Multi-class Approach – Building a Visual Classifier based on Textual Descriptions using Zero-Shot Learning
Machine Learning (ML) techniques for image classification routinely requ...
read it
-
Write a Classifier: Predicting Visual Classifiers from Unstructured Text
People typically learn through exposure to visual concepts associated wi...
read it
-
Feature Transfer Learning for Deep Face Recognition with Long-Tail Data
Real-world face recognition datasets exhibit long-tail characteristics, ...
read it
-
Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning
We develop methods for detector learning which exploit joint training ov...
read it
Alpha Net: Adaptation with Composition in Classifier Space
Deep learning classification models typically train poorly on classes with small numbers of examples. Motivated by the human ability to solve this task, models have been developed that transfer knowledge from classes with many examples to learn classes with few examples. Critically, the majority of these models transfer knowledge within model feature space. In this work, we demonstrate that transferring knowledge within classified space is more effective and efficient. Specifically, by linearly combining strong nearest neighbor classifiers along with a weak classifier, we are able to compose a stronger classifier. Uniquely, our model can be implemented on top of any existing classification model that includes a classifier layer. We showcase the success of our approach in the task of long-tailed recognition, whereby the classes with few examples, otherwise known as the "tail" classes, suffer the most in performance and are the most challenging classes to learn. Using classifier-level knowledge transfer, we are able to drastically improve - by a margin as high as 12.6 categories.
READ FULL TEXT
Comments
There are no comments yet.