Subspace Alignment Based Domain Adaptation for RCNN Detector

By Anant Raj, Vinay P. Namboodiri, Tinne Tuytelaars. 2015

74 citations recorded by the source corpus.

In this paper, we propose subspace alignment based domain adaptation of the state of the art RCNN based object detector. The aim is to be able to achieve high quality object detection in novel, real world target scenarios without requiring labels from the target domain. While, unsupervised domain adaptation has been studied in the case of object classification, for object detection it has been relatively unexplored. In subspace based domain adaptation for objects, we need access to source and target subspaces for the bounding box features. The absence of supervision (labels and bounding boxes are absent) makes the task challenging. In this paper, we show that we can still adapt sub- spaces that are localized to the object by obtaining detections from the RCNN detector trained on source and applied on target. Then we form localized subspaces from the detections and show that subspace alignment based adaptation between these subspaces yields improved object detection. This evaluation is done by considering challenging real world datasets of PASCAL VOC as source and validation set of Microsoft COCO dataset as target for various categories.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Luc Van Gool
2. Jiashi Feng
3. Dengxin Dai
4. Gabriella Csurka
5. Wen Li
6. Dahua Lin
7. Yuhua Chen
8. Li Yuan

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Jiashi Feng
4. Ming-Hsuan Yang
5. Trevor Darrell
6. Xiaogang Wang
7. Yi Yang
8. Andrew Zisserman

Citations in the corpus

• Recognition in Terra Incognita (2018, methodology): “, [53] demonstrated a subspace-based detection method for domain adaptation from PASCAL to COCO.”
• Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “ounding boxes. The advantage of this model is that it generalizes well even for localization of classes for which there were no bounding box annotations during the training phase. Instead fine-tuning, [219] uses Subspace Alignment [19] to adjust class specific representations of bounding boxes (BB) be”
• Domain Adaptive Faster R-CNN for Object Detection in the Wild (2018, methodology): “In a recent work [47], they use R-CNN model as feature extractor, then the features are aligned with the subspace alignment method.”
• Exploring Object Relation in Mean Teacher for Cross-Domain Detection (2019, methodology): “, object detection [4, 35] and semantic segmentation [5, 16, 53].”
• Adapting Object Detectors via Selective Cross-Domain Alignment (2019, methodology): “[35] tried to adapt classspecific R-CNN detectors by subspace alignment.”
• Few-Shot Adaptive Faster R-CNN (2019, methodology): “[34] developed subspace alignment based domain adaptation for the R-CNN model.”