Part Detector Discovery in Deep Convolutional Neural Networks

TL;DR

This paper introduces a method called PDD that leverages pre-trained CNNs to discover and localize object parts efficiently without additional training, enabling joint detection and classification in fine-grained tasks.

Contribution

The paper presents a novel approach for object part discovery using gradient map analysis of pre-trained CNNs, eliminating the need for part annotations during training.

Findings

Achieves excellent performance on CUB200-2011 dataset

Enables joint detection and classification without bounding box annotations

Utilizes gradient maps for robust part localization

Abstract

Current fine-grained classification approaches often rely on a robust localization of object parts to extract localized feature representations suitable for discrimination. However, part localization is a challenging task due to the large variation of appearance and pose. In this paper, we show how pre-trained convolutional neural networks can be used for robust and efficient object part discovery and localization without the necessity to actually train the network on the current dataset. Our approach called "part detector discovery" (PDD) is based on analyzing the gradient maps of the network outputs and finding activation centers spatially related to annotated semantic parts or bounding boxes. This allows us not just to obtain excellent performance on the CUB200-2011 dataset, but in contrast to previous approaches also to perform detection and bird classification jointly without requiring a given bounding box annotation during testing and ground-truth parts during training. The code is available at http://www.inf-cv.uni-jena.de/part_discovery and https://github.com/cvjena/PartDetectorDisovery.