PrObeD: Proactive Object Detection Wrapper

TL;DR

PrObeD introduces a proactive wrapper that learns image-dependent signals to encrypt input images, improving object detection performance on various datasets by emphasizing relevant semantics.

Contribution

The paper proposes a novel encoder-decoder based wrapper that enhances object detection by learning optimal templates to encrypt images, a new approach to improve detector accuracy.

Findings

Improved detection accuracy on MS-COCO, CAMO, COD10K, NC4K datasets.

Enhancement observed across different object detectors.

Template-based encryption boosts semantic highlighting for better detection.

Abstract

Previous research in $2D$ object detection focuses on various tasks, including detecting objects in generic and camouflaged images. These works are regarded as passive works for object detection as they take the input image as is. However, convergence to global minima is not guaranteed to be optimal in neural networks; therefore, we argue that the trained weights in the object detector are not optimal. To rectify this problem, we propose a wrapper based on proactive schemes, PrObeD, which enhances the performance of these object detectors by learning a signal. PrObeD consists of an encoder-decoder architecture, where the encoder network generates an image-dependent signal termed templates to encrypt the input images, and the decoder recovers this template from the encrypted images. We propose that learning the optimum template results in an object detector with an improved detection performance. The template acts as a mask to the input images to highlight semantics useful for the object detector. Finetuning the object detector with these encrypted images enhances the detection performance for both generic and camouflaged. Our experiments on MS-COCO, CAMO, COD$10$K, and NC$4$K datasets show improvement over different detectors after applying PrObeD. Our models/codes are available at https://github.com/vishal3477/Proactive-Object-Detection.