Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset

TL;DR

This paper introduces the SSW60 dataset for fine-grained audiovisual bird species classification across images, audio, and video, and benchmarks state-of-the-art methods to advance research in multimodal fine-grained categorization.

Contribution

The paper presents a new comprehensive dataset, SSW60, enabling research on audiovisual fine-grained categorization across three modalities with baseline benchmarks.

Findings

Audiovisual fusion improves classification performance over single modalities.

State-of-the-art transformer methods achieve strong results on SSW60.

Modality transfer experiments reveal potential for cross-modal learning.

Abstract

We present a new benchmark dataset, Sapsucker Woods 60 (SSW60), for advancing research on audiovisual fine-grained categorization. While our community has made great strides in fine-grained visual categorization on images, the counterparts in audio and video fine-grained categorization are relatively unexplored. To encourage advancements in this space, we have carefully constructed the SSW60 dataset to enable researchers to experiment with classifying the same set of categories in three different modalities: images, audio, and video. The dataset covers 60 species of birds and is comprised of images from existing datasets, and brand new, expert-curated audio and video datasets. We thoroughly benchmark audiovisual classification performance and modality fusion experiments through the use of state-of-the-art transformer methods. Our findings show that performance of audiovisual fusion methods is better than using exclusively image or audio based methods for the task of video classification. We also present interesting modality transfer experiments, enabled by the unique construction of SSW60 to encompass three different modalities. We hope the SSW60 dataset and accompanying baselines spur research in this fascinating area.