Pick-Object-Attack: Type-Specific Adversarial Attack for Object
Detection
- URL: http://arxiv.org/abs/2006.03184v3
- Date: Sun, 22 Aug 2021 02:46:12 GMT
- Title: Pick-Object-Attack: Type-Specific Adversarial Attack for Object
Detection
- Authors: Omid Mohamad Nezami, Akshay Chaturvedi, Mark Dras, Utpal Garain
- Abstract summary: We present the first type-specific approach to generating adversarial examples for object detection.
Pick-Object-Attack successfully adds perturbations only to bounding boxes for the targeted object.
For the first time, we examine the effect of adversarial attacks on object detection in terms of a downstream task, image captioning.
- Score: 9.581332581510184
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Many recent studies have shown that deep neural models are vulnerable to
adversarial samples: images with imperceptible perturbations, for example, can
fool image classifiers. In this paper, we present the first type-specific
approach to generating adversarial examples for object detection, which entails
detecting bounding boxes around multiple objects present in the image and
classifying them at the same time, making it a harder task than against image
classification. We specifically aim to attack the widely used Faster R-CNN by
changing the predicted label for a particular object in an image: where prior
work has targeted one specific object (a stop sign), we generalise to arbitrary
objects, with the key challenge being the need to change the labels of all
bounding boxes for all instances of that object type. To do so, we propose a
novel method, named Pick-Object-Attack. Pick-Object-Attack successfully adds
perturbations only to bounding boxes for the targeted object, preserving the
labels of other detected objects in the image. In terms of perceptibility, the
perturbations induced by the method are very small. Furthermore, for the first
time, we examine the effect of adversarial attacks on object detection in terms
of a downstream task, image captioning; we show that where a method that can
modify all object types leads to very obvious changes in captions, the changes
from our constrained attack are much less apparent.
Related papers
- Image Segmentation-based Unsupervised Multiple Objects Discovery [1.7674345486888503]
Unsupervised object discovery aims to localize objects in images.
We propose a fully unsupervised, bottom-up approach, for multiple objects discovery.
We provide state-of-the-art results for both unsupervised class-agnostic object detection and unsupervised image segmentation.
arXiv Detail & Related papers (2022-12-20T09:48:24Z) - Exploiting Unlabeled Data with Vision and Language Models for Object
Detection [64.94365501586118]
Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets.
We propose a novel method that leverages the rich semantics available in recent vision and language models to localize and classify objects in unlabeled images.
We demonstrate the value of the generated pseudo labels in two specific tasks, open-vocabulary detection and semi-supervised object detection.
arXiv Detail & Related papers (2022-07-18T21:47:15Z) - Context-Aware Transfer Attacks for Object Detection [51.65308857232767]
We present a new approach to generate context-aware attacks for object detectors.
We show that by using co-occurrence of objects and their relative locations and sizes as context information, we can successfully generate targeted mis-categorization attacks.
arXiv Detail & Related papers (2021-12-06T18:26:39Z) - Decoupled Adaptation for Cross-Domain Object Detection [69.5852335091519]
Cross-domain object detection is more challenging than object classification.
D-adapt achieves a state-of-the-art results on four cross-domain object detection tasks.
arXiv Detail & Related papers (2021-10-06T08:43:59Z) - A Simple and Effective Use of Object-Centric Images for Long-Tailed
Object Detection [56.82077636126353]
We take advantage of object-centric images to improve object detection in scene-centric images.
We present a simple yet surprisingly effective framework to do so.
Our approach can improve the object detection (and instance segmentation) accuracy of rare objects by 50% (and 33%) relatively.
arXiv Detail & Related papers (2021-02-17T17:27:21Z) - Synthesizing the Unseen for Zero-shot Object Detection [72.38031440014463]
We propose to synthesize visual features for unseen classes, so that the model learns both seen and unseen objects in the visual domain.
We use a novel generative model that uses class-semantics to not only generate the features but also to discriminatively separate them.
arXiv Detail & Related papers (2020-10-19T12:36:11Z) - Learning Object Detection from Captions via Textual Scene Attributes [70.90708863394902]
We argue that captions contain much richer information about the image, including attributes of objects and their relations.
We present a method that uses the attributes in this "textual scene graph" to train object detectors.
We empirically demonstrate that the resulting model achieves state-of-the-art results on several challenging object detection datasets.
arXiv Detail & Related papers (2020-09-30T10:59:20Z) - Cross-Supervised Object Detection [42.783400918552765]
We show how to build better object detectors from weakly labeled images of new categories by leveraging knowledge learned from fully labeled base categories.
We propose a unified framework that combines a detection head trained from instance-level annotations and a recognition head learned from image-level annotations.
arXiv Detail & Related papers (2020-06-26T15:33:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.