Home

PATAN - Partial Video-based Domain Adaptation

Download this dataset

Partial Adversarial Temporal Attentive Network (PATAN)

A Novel Method and A New Benchmark Dataset for Partial Video-based Domain Adaptation (PVDA)

Download

alt text

Abstract

Partial Domain Adaptation (PDA) is a practical and general domain adaptation scenario, which relaxes the fully shared label space assumption such that the source label space subsumes the target one. The key challenge of PDA is the issue of negative transfer caused by source-only classes. For videos, such negative transfer could be triggered by both spatial and temporal features, which leads to a more challenging Partial Video Domain Adaptation (PVDA) problem. In this paper, we propose a novel Partial Adversarial Temporal Attentive Network (PATAN) to address the PVDA problem by utilizing both spatial and temporal features for filtering source-only classes. Besides, PATAN constructs effective overall temporal features by attending to local temporal features that contribute more toward the class filtration process. We further introduce new benchmarks to facilitate research on PVDA problems, covering a wide range of PVDA scenarios. Empirical results demonstrate the state-of-the-art performance of our proposed PATAN across the multiple PVDA benchmarks.

Structure of PATAN

The structure of PATAN is as follows:

alt text

Benchmark Datasets for PVDA

There are very limited cross-domain benchmark datasets for VUDA. Current cross-domain VUDA datasets are designed for the standard VUDA tasks, with the source label space constraint to be the same as target label space. To further facilitate PVDA research, we propose three sets of benchmarks, UCF-HMDBpartial, MiniKinetics-UCF, and HMDB-ARIDpartial, which cover a wide range of PVDA scenarios and provide adequate baseline environment with distinct domain shift to facilitate PVDA research.

Sampled frames from UCF-HMDBpartial:

alt text

Sampled frames from UCF-HMDBpartial:

alt text

Sampled frames from UCF-HMDBpartial:

alt text

Benchmark Results

We tested our proposed PATAN on the three benchmark datasets as introduced above, while comparing with previous (partial) domain adaptation methods. The results are as follows:

alt text

We further compared the learnt class weights on two settings, U-14->H-7 and H-10->A-5, with the results shown as follows:

alt text

Papers, Notes and Download

CC BY 4.0

Back to Project Page