Zero-Shot Object Detection

TL;DR

This paper introduces a new approach to zero-shot object detection that enables models to identify unseen classes by leveraging visual-semantic embeddings and background-aware learning, with extensive experiments on standard datasets.

Contribution

It presents a novel zero-shot detection framework with background-aware methods and dense semantic sampling, advancing the ability to detect unseen object classes.

Findings

Effective detection of unseen classes demonstrated on MSCOCO and VisualGenome.

Background-aware approaches improve zero-shot detection robustness.

Dense semantic sampling enhances generalization to novel categories.

Abstract

We introduce and tackle the problem of zero-shot object detection (ZSD), which aims to detect object classes which are not observed during training. We work with a challenging set of object classes, not restricting ourselves to similar and/or fine-grained categories as in prior works on zero-shot classification. We present a principled approach by first adapting visual-semantic embeddings for ZSD. We then discuss the problems associated with selecting a background class and motivate two background-aware approaches for learning robust detectors. One of these models uses a fixed background class and the other is based on iterative latent assignments. We also outline the challenge associated with using a limited number of training classes and propose a solution based on dense sampling of the semantic label space using auxiliary data with a large number of categories. We propose novel splits of two standard detection datasets - MSCOCO and VisualGenome, and present extensive empirical results in both the traditional and generalized zero-shot settings to highlight the benefits of the proposed methods. We provide useful insights into the algorithm and conclude by posing some open questions to encourage further research.