Verification for Object Detection -- IBP IoU

• URL: http://arxiv.org/abs/2403.08788v1
• Date: Tue, 30 Jan 2024 09:05:38 GMT
• Title: Verification for Object Detection -- IBP IoU
• Abstract summary: We introduce a novel Interval Bound Propagation (IBP) approach for the formal verification of object detection models. The approach has been implemented in an open source code, named IBP IoU, compatible with popular abstract interpretation based verification tools.
• Score: 2.2291239762534145
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a novel Interval Bound Propagation (IBP) approach for the formal verification of object detection models, specifically targeting the Intersection over Union (IoU) metric. The approach has been implemented in an open source code, named IBP IoU, compatible with popular abstract interpretation based verification tools. The resulting verifier is evaluated on landing approach runway detection and handwritten digit recognition case studies. Comparisons against a baseline (Vanilla IBP IoU) highlight the superior performance of IBP IoU in ensuring accuracy and stability, contributing to more secure and robust machine learning applications.

Related papers

• IoUCert: Robustness Verification for Anchor-based Object Detectors [58.35703549470485]
  We introduce IoUCert, a novel formal verification framework designed specifically to overcome these bottlenecks in anchor-based object detection architectures.<n>We show that our method enables the robustness verification of realistic, anchor-based models including SSD, YOLOv2, and YOLOv3 variants against various input perturbations.
  arXiv  Detail & Related papers  (2026-03-03T14:36:46Z)
• Enhancing Object Detection with Privileged Information: A Model-Agnostic Teacher-Student Approach [2.1303542744717148]
  This paper investigates the integration of the Learning Using Privileged Information (LUPI) paradigm in object detection.<n>We introduce a general, model-agnostic methodology for injecting privileged information-such as bounding box masks-into deep learning-based object detectors.
  arXiv  Detail & Related papers  (2026-01-05T11:24:34Z)
• A Secured Intent-Based Networking (sIBN) with Data-Driven Time-Aware Intrusion Detection [2.7273279761148967]
  This study proposes a secured IBN (sIBN) system with data driven intrusion detection method designed to secure user intent from adversarial tampering.<n>The proposed intent intrusion detection system uses a ML model applied for network behavioral anomaly detection to reveal temporal patterns of intent tampering.
  arXiv  Detail & Related papers  (2025-11-07T10:28:01Z)
• Revisiting Logit Distributions for Reliable Out-of-Distribution Detection [73.9121001113687]
  Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning models in open-world applications.<n>LogitGap is a novel post-hoc OOD detection method that exploits the relationship between the maximum logit and the remaining logits.<n>We show that LogitGap consistently achieves state-of-the-art performance across diverse OOD detection scenarios and benchmarks.
  arXiv  Detail & Related papers  (2025-10-23T02:16:45Z)
• Source-Free Object Detection with Detection Transformer [59.33653163035064]
  Source-Free Object Detection (SFOD) enables knowledge transfer from a source domain to an unsupervised target domain for object detection without access to source data.<n>Most existing SFOD approaches are either confined to conventional object detection (OD) models like Faster R-CNN or designed as general solutions without tailored adaptations for novel OD architectures, especially Detection Transformer (DETR)<n>In this paper, we introduce Feature Reweighting ANd Contrastive Learning NetworK (FRANCK), a novel SFOD framework specifically designed to perform query-centric feature enhancement for DETRs.
  arXiv  Detail & Related papers  (2025-10-13T07:35:04Z)
• Individual Packet Features are a Risk to Model Generalisation in ML-Based Intrusion Detection [3.3772986620114387]
  Individual packet features (IPF) are attributes extracted from a single network packet, such as timing, size, and source-destination information. We identify the limitations of IPF, showing they can produce misleadingly high detection rates. Our findings emphasize the need for approaches that consider packet interactions for robust intrusion detection.
  arXiv  Detail & Related papers  (2024-06-07T21:05:33Z)
• EC-IoU: Orienting Safety for Object Detectors via Ego-Centric Intersection-over-Union [7.355977594790584]
  This paper presents safety-oriented object detection via a novel Ego-Centric Intersection-over-Union (EC-IoU) measure. We propose a weighting mechanism to refine the widely used IoU measure, allowing it to assign a higher score to a prediction that covers closer points of a ground-truth object from the ego agent's perspective.
  arXiv  Detail & Related papers  (2024-03-20T16:25:49Z)
• Physics Inspired Hybrid Attention for SAR Target Recognition [61.01086031364307]
  We propose a physics inspired hybrid attention (PIHA) mechanism and the once-for-all (OFA) evaluation protocol to address the issues. PIHA leverages the high-level semantics of physical information to activate and guide the feature group aware of local semantics of target. Our method outperforms other state-of-the-art approaches in 12 test scenarios with same ASC parameters.
  arXiv  Detail & Related papers  (2023-09-27T14:39:41Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning [64.78972193105443]
  This paper presents a novel AE detection framework, named trustworthy for predictions. performs the detection by distinguishing the AE's abnormal relation with its augmented versions. An off-the-shelf Self-Supervised Learning (SSL) model is used to extract the representation and predict the label.
  arXiv  Detail & Related papers  (2022-08-31T08:18:44Z)
• Neural Enhanced Belief Propagation for Data Assocation in Multiobject Tracking [8.228150100178983]
  Multiobject tracking (MOT) will create new services and applications in fields such as autonomous navigation and applied ocean sciences. Belief propagation (BP) is a state-of-the-art method for Bayesian MOT but fully relies on a statistical model and preprocessed sensor measurements. We establish a hybrid method for model-based and data-driven MOT. The proposed neural enhanced belief propagation (NEBP) approach complements BP by information learned from raw sensor data. We evaluate the performance of our NEBP approach for MOT on the nuScenes autonomous driving dataset and demonstrate that it can outperform state-of-
  arXiv  Detail & Related papers  (2022-03-17T00:12:48Z)
• Evaluating Federated Learning for Intrusion Detection in Internet of Things: Review and Challenges [0.0]
  Federated Learning (FL) has attracted a significant interest in different sectors, including healthcare and transport systems. We evaluate a FL-enabled IDS approach based on a multiclass classifier considering different data distributions for the detection of different attacks in an IoT scenario. We identify a set of challenges and future directions based on the existing literature and the analysis of our evaluation results.
  arXiv  Detail & Related papers  (2021-08-02T15:22:05Z)
• Federated Learning for Internet of Things: A Federated Learning Framework for On-device Anomaly Data Detection [10.232121085973782]
  We build a FedIoT platform that contains a synthesized dataset using N-BaIoT, FedDetect algorithm, and a system design for IoT devices. In a network of realistic IoT devices (PI), we evaluate FedIoT platform and FedDetect algorithm in both model and system performance.
  arXiv  Detail & Related papers  (2021-06-15T08:53:42Z)
• Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection [60.522877583407904]
  Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods. We present Pseudo-Intersection-over-Union(Pseudo-IoU): a simple metric that brings more standardized and accurate assignment rule into anchor-free object detection frameworks. Our method achieves comparable performance to other recent state-of-the-art anchor-free methods without bells and whistles.
  arXiv  Detail & Related papers  (2021-04-29T02:48:47Z)
• Personal Fixations-Based Object Segmentation with Object Localization and Boundary Preservation [60.41628937597989]
  We focus on Personal Fixations-based Object (PFOS) to address issues in previous studies. We propose a novel network based on Object Localization and Boundary Preservation (OLBP) to segment the gazed objects. OLBP is organized in the mixed bottom-up and top-down manner with multiple types of deep supervision.
  arXiv  Detail & Related papers  (2021-01-22T09:20:47Z)

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.