paper-with-me

홈 › Papers

Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts

2024-04-01 · Prakash Chandra Chhipa, Kanjar De, Meenakshi Subhash Chippa, Rajkumar Saini, Marcus Liwicki

The challenge of Out-Of-Distribution (OOD) robustness remains a critical hurdle towards deploying deep vision models. Vision-Language Models (VLMs) have recently achieved groundbreaking results. VLM-based open-vocabulary object detection extends the capabilities of traditional object detection frameworks, enabling the recognition and classification of objects beyond predefined categories. Investigating OOD robustness in recent open-vocabulary object detection is essential to increase the trustworthiness of these models. This study presents a comprehensive robustness evaluation of the zero-shot capabilities of three recent open-vocabulary (OV) foundation object detection models: OWL-ViT, YOLO World, and Grounding DINO. Experiments carried out on the robustness benchmarks COCO-O, COCO-DC, and COCO-C encompassing distribution shifts due to information loss, corruption, adversarial attacks, and geometrical deformation, highlighting the challenges of the model's robustness to foster the research for achieving robustness. Project page: https://prakashchhipa.github.io/projects/ovod_robustness

📄 PDF Abstract BibTeX arXiv:2405.14874

Code (0)

등록된 구현이 없습니다.

Tasks

Objectobject-detectionObject DetectionOpen-vocabulary object detectionOpen Vocabulary Object Detection

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Boosting Open-Vocabulary Object Detection by Handling Background Samples

2024-10-11 · Ruizhe Zeng, Lu Zhang, Xu Yang, Zhiyong Liu

Open-vocabulary object detection is the task of accurately detecting objects from a candidate vocabulary list that includes both base and novel categories. Currently, numerous open-vocabulary detectors have achieved succ…

object-detectionObject DetectionOpen-vocabulary object detectionOpen Vocabulary Object Detection+1

MQADet: A Plug-and-Play Paradigm for Enhancing Open-Vocabulary Object Detection via Multimodal Question Answering

2025-02-23 · Caixiong Li, Xiongwei Zhao, Jinhang Zhang, Xing Zhang 외

Open-vocabulary detection (OVD) is a challenging task to detect and classify objects from an unrestricted set of categories, including those unseen during training. Existing open-vocabulary detectors are limited by compl…

Objectobject-detectionObject DetectionOpen-vocabulary object detection+2

Fine-Grained Open-Vocabulary Object Detection with Fined-Grained Prompts: Task, Dataset and Benchmark

2025-03-19 · Ying Liu, Yijing Hua, Haojiang Chai, Yanbo Wang 외

Open-vocabulary detectors are proposed to locate and recognize objects in novel classes. However, variations in vision-aware language vocabulary data used for open-vocabulary learning can lead to unfair and unreliable ev…

Objectobject-detectionObject DetectionOpen-vocabulary object detection+1

Training an Open-Vocabulary Monocular 3D Object Detection Model without 3D Data

2024-11-23 · Rui Huang, Henry Zheng, Yan Wang, Zhuofan Xia 외

Open-vocabulary 3D object detection has recently attracted considerable attention due to its broad applications in autonomous driving and robotics, which aims to effectively recognize novel classes in previously unseen d…

3D Object DetectionAutonomous DrivingMonocular 3D Object Detectionobject-detection+1

Robust Onion: Peeling Open Vocab Object Detectors Under Noise

2026-06-25 · Priyank Pathak, Mukilan Karuppasamy, Aaditya Baranwal, Shruti Vyas 외 arxiv

The impact of real-world noise on Open Vocabulary Object Detectors (OV-ODs) remains poorly understood due to their architectural complexity. We present our comprehensive analysis Robust Onion, an empirical study that use…