Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector

2024/02/05 by Yuqian Fu, Fu, Yuqian, Yu Wang +17 · 10 citations
Computer Science · Engineering · Neuroscience · #Advanced Neural Network Applications #Brain Tumor Detection and Classification #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Infrared Target Detection Methodologies #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2402.03094

openalex publication_date 2024/02/05 · openalex created_date 2024/02/08 · openalex updated_date 2026/07/28

Abstract

This paper studies the challenging cross-domain few-shot object detection (CD-FSOD), aiming to develop an accurate object detector for novel domains with minimal labeled examples. While transformer-based open-set detectors, such as DE-ViT, show promise in traditional few-shot object detection, their generalization to CD-FSOD remains unclear: 1) can such open-set detection methods easily generalize to CD-FSOD? 2) If not, how can models be enhanced when facing huge domain gaps? To answer the first question, we employ measures including style, inter-class variance (ICV), and indefinable boundaries (IB) to understand the domain gap. Based on these measures, we establish a new benchmark named CD-FSOD to evaluate object detection methods, revealing that most of the current approaches fail to generalize across domains. Technically, we observe that the performance decline is associated with our proposed measures: style, ICV, and IB. Consequently, we propose several novel modules to address these issues. First, the learnable instance features align initial fixed instances with target categories, enhancing feature distinctiveness. Second, the instance reweighting module assigns higher importance to high-quality instances with slight IB. Third, the domain prompter encourages features resilient to different styles by synthesizing imaginary domains without altering semantic contents. These techniques collectively contribute to the development of the Cross-Domain Vision Transformer for CD-FSOD (CD-ViTO), significantly improving upon the base DE-ViT. Experimental results validate the efficacy of our model.

Cited by

• Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts
• ReefNet: A Large scale, Taxonomically Enriched Dataset and Benchmark for Hard Coral Classification
• CoPRS: Learning Positional Prior from Chain-of-Thought for Reasoning Segmentation
• Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learning
• Exploring Single Domain Generalization of LiDAR-based Semantic Segmentation under Imperfect Labels
• EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark
• VFM-Guided Semi-Supervised Detection Transformer under Source-Free Constraints for Remote Sensing Object Detection
• EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering
• Zero Shot Domain Adaptive Semantic Segmentation by Synthetic Data Generation and Progressive Adaptation
• 3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection

Related

• CD-FSOD: A Benchmark for Cross-domain Few-shot Object Detection
• NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
• CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion
• Beyond Few-shot Object Detection: A Detailed Survey
• Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark