DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection

Authors: Haochen Li, Rui Zhang, Hantao Yao, Xin Zhang, Yifan Hao, Xinkai Song, Xiaqing Li, Yongwei Zhao, Yunji Chen, Ling Li

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Comprehensive experiments over multiple DAOD tasks show that DA-Ada can efficiently infer a domain-aware visual encoder for boosting domain adaptive object detection.
Researcher Affiliation Academia 1Intelligent Software Research Center, Institute of Software, CAS, Beijing, China 2State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China 3 State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China 4 University of Chinese Academy of Sciences, Beijing, China
Pseudocode No The paper provides block diagrams and mathematical equations in Figure 2, but does not present pseudocode or a clearly labeled algorithm block.
Open Source Code Yes Our code is available at https://github.com/Therock90421/DA-Ada.
Open Datasets Yes Cityscapes [9] contains diverse street scenes captured by a mobile camera in daylight. The regular partition consists of 2,975 training and 500 validation images annotated with eight classes. Foggy Cityscapes [54] simulates three distinct densities of fog on Cityscapes, containing 8,925 training images and 1,500 validation images.
Dataset Splits Yes Cityscapes [9] contains diverse street scenes captured by a mobile camera in daylight. The regular partition consists of 2,975 training and 500 validation images annotated with eight classes. Foggy Cityscapes [54] simulates three distinct densities of fog on Cityscapes, containing 8,925 training images and 1,500 validation images.
Hardware Specification Yes All experiments are deployed on 8 Tesla V100 GPUs.
Software Dependencies No The paper mentions using Region CLIP (ResNet-50) and Faster-RCNN, and the SGD optimizer, but does not provide specific version numbers for software libraries or programming languages used (e.g., Python, PyTorch, CUDA versions).
Experiment Setup Yes The hyperparameter λdia, λdita, λdec is set to 0.1, 1.0 and 0.1, respectively. We set the batch size of each domain to 8 and use the SGD optimizer with a warm-up learning rate. Mean Average Precision (m AP) with a threshold of 0.5 is taken as the evaluation metric.