Adversarial Knowledge Transfer from Unlabeled Data

by   Akash Gupta, et al.

While machine learning approaches to visual recognition offer great promise, most of the existing methods rely heavily on the availability of large quantities of labeled training data. However, in the vast majority of real-world settings, manually collecting such large labeled datasets is infeasible due to the cost of labeling data or the paucity of data in a given domain. In this paper, we present a novel Adversarial Knowledge Transfer (AKT) framework for transferring knowledge from internet-scale unlabeled data to improve the performance of a classifier on a given visual recognition task. The proposed adversarial learning framework aligns the feature space of the unlabeled source data with the labeled target data such that the target classifier can be used to predict pseudo labels on the source data. An important novel aspect of our method is that the unlabeled source data can be of different classes from those of the labeled target data, and there is no need to define a separate pretext task, unlike some existing approaches. Extensive experiments well demonstrate that models learned using our approach hold a lot of promise across a variety of visual recognition tasks on multiple standard datasets.


page 1

page 8


A Survey of Unsupervised Domain Adaptation for Visual Recognition

While huge volumes of unlabeled data are generated and made available in...

Domain Adaptation with Adversarial Training and Graph Embeddings

The success of deep neural networks (DNNs) is heavily dependent on the a...

Where is the Bottleneck of Adversarial Learning with Unlabeled Data?

Deep neural networks (DNNs) are incredibly brittle due to adversarial ex...

Flexible deep transfer learning by separate feature embeddings and manifold alignment

Object recognition is a key enabler across industry and defense. As tech...

Factors of Transferability for a Generic ConvNet Representation

Evidence is mounting that Convolutional Networks (ConvNets) are the most...

Spacing Loss for Discovering Novel Categories

Novel Class Discovery (NCD) is a learning paradigm, where a machine lear...

Visual Recognition by Request

In this paper, we present a novel protocol of annotation and evaluation ...

Code Repositories