Polarity Loss for Zero-shot Object Detection

TL;DR

This paper introduces Polarity loss, a novel training objective that enhances zero-shot object detection by improving visual-semantic alignment and discrimination, leading to better recognition of unseen objects.

Contribution

It proposes Polarity loss, a new loss function that refines semantic embeddings and maximizes prediction gaps to improve zero-shot detection performance.

Findings

Significant improvements on MS-COCO and Pascal VOC datasets.

Enhanced alignment between visual features and semantic descriptions.

Better discrimination between seen, unseen, and background objects.

Abstract

Conventional object detection models require large amounts of training data. In comparison, humans can recognize previously unseen objects by merely knowing their semantic description. To mimic similar behaviour, zero-shot object detection aims to recognize and localize 'unseen' object instances by using only their semantic information. The model is first trained to learn the relationships between visual and semantic domains for seen objects, later transferring the acquired knowledge to totally unseen objects. This setting gives rise to the need for correct alignment between visual and semantic concepts, so that the unseen objects can be identified using only their semantic attributes. In this paper, we propose a novel loss function called 'Polarity loss', that promotes correct visual-semantic alignment for an improved zero-shot object detection. On one hand, it refines the noisy semantic embeddings via metric learning on a 'Semantic vocabulary' of related concepts to establish a better synergy between visual and semantic domains. On the other hand, it explicitly maximizes the gap between positive and negative predictions to achieve better discrimination between seen, unseen and background objects. Our approach is inspired by embodiment theories in cognitive science, that claim human semantic understanding to be grounded in past experiences (seen objects), related linguistic concepts (word vocabulary) and visual perception (seen/unseen object images). We conduct extensive evaluations on MS-COCO and Pascal VOC datasets, showing significant improvements over state of the art.