Subspace Alignment Based Domain Adaptation for RCNN Detector

@inproceedings{Raj2015SubspaceAB,
  title={Subspace Alignment Based Domain Adaptation for RCNN Detector},
  author={Anant Raj and Vinay P. Namboodiri and Tinne Tuytelaars},
  booktitle={BMVC},
  year={2015}
}
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… 

Figures and Tables from this paper

A Robust Learning Approach to Domain Adaptive Object Detection
TLDR
A robust object detection framework that is resilient to noise in bounding box class labels, locations and size annotations is proposed that significantly improves the state-of-the-art on multiple domain adaptation scenarios on the SIM10K, Cityscapes and KITTI datasets.
Spatial Alignment for Unsupervised Domain Adaptive Single-Stage Object Detection
TLDR
A selective domain adaptation framework for the spatial alignment of a single-stage detector that can achieve domain feature alignment and reduce the influence of the background, enabling transfer between different domains.
Region Proposal Oriented Approach for Domain Adaptive Object Detection
TLDR
This work addresses the domain adaptation problem in the context of object detection in the case where no annotations are available in the target domain by adapting the region proposal sub-network leading to a residual domain shift.
Adapting Object Detectors via Selective Cross-Domain Alignment
TLDR
The key idea is to mine the discriminative regions, namely those that are directly pertinent to object detection, and focus on aligning them across both domains, and perform remarkably better than existing methods.
Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection
TLDR
This paper is the first to reveal that the region proposal network (RPN) and region proposal classifier~(RPC) in the endemic two-stage detectors demonstrate significantly different transferability when facing large domain gap.
Unsupervised domain adaptation of deep object detectors
TLDR
This paper adapts deep adaptation techniques for the Faster R-CNN framework based on Gradient Reversal and Maximum Mean Discrepancy (MMD) reduction based techniques and shows that the MK-MMD based method when used appropriately provides the best results.
Domain Adaptive Faster R-CNN for Object Detection in the Wild
TLDR
This work builds on the recent state-of-the-art Faster R-CNN model, and design two domain adaptation components, on image level and instance level, to reduce the domain discrepancy, based on $$-divergence theory.
SCL: TOWARDS ACCURATE DOMAIN ADAPTIVE OB-
  • Computer Science
  • 2019
TLDR
A gradient detach based stacked complementary losses (SCL) method that uses detection objective (Ren et al., 2015) as the primary objective, and cuts in several auxiliary losses in different network stages to utilize information from the complement data (target images) that can be effective in adapting model parameters to both source and target domains is proposed.
Learning a Domain Classifier Bank for Unsupervised Adaptive Object Detection
TLDR
A fine-grained domain alignment approach with a well-designed domain classifier bank that achieves the instance-level alignment respecting to their categories is developed and achieves the new remarkable state-of-the-arts.
SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses
TLDR
A gradient detach based stacked complementary losses (SCL) method that uses detection losses as the primary objective, and cuts in several auxiliary losses in different network stages accompanying with gradient detach training to learn more discriminative representations.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 21 REFERENCES
Domain adaptation for object recognition: An unsupervised approach
TLDR
This paper presents one of the first studies on unsupervised domain adaptation in the context of object recognition, where data has been labeled only from the source domain (and therefore do not have correspondences between object categories across domains).
Domain Adaptation of Deformable Part-Based Models
TLDR
This work introduces an adaptive structural SVM (A-SSVM) that adapts a pre-learned classifier between different domains that avoids accuracy drops as high as 15 points when comparing adapted and non-adapted detectors.
LSDA: Large Scale Detection through Adaptation
TLDR
This paper proposes Large Scale Detection through Adaptation (LSDA), an algorithm which learns the difference between the two tasks and transfers this knowledge to classifiers for categories without bounding box annotated data, turning them into detectors.
Domain adaptive object detection
TLDR
This work explores the problem of extreme class imbalance present when performing domain adaptation for object detection and proposes an initial approach to addressing this problem, which is applied to vehicle detection in a challenging urban surveillance dataset.
Unsupervised Visual Domain Adaptation Using Subspace Alignment
TLDR
This paper introduces a new domain adaptation algorithm where the source and target domains are represented by subspaces described by eigenvectors, and seeks a domain adaptation solution by learning a mapping function which aligns the source subspace with the target one.
Geodesic flow kernel for unsupervised domain adaptation
TLDR
This paper proposes a new kernel-based method that takes advantage of low-dimensional structures that are intrinsic to many vision datasets, and introduces a metric that reliably measures the adaptability between a pair of source and target domains.
Mind the Gap: Subspace based Hierarchical Domain Adaptation
TLDR
This work considers the hierarchical organization of the data and considers multiple subspaces for the source and target domain based on the hierarchy and observes that using different subspaced based onThe hierarchy yields consistent improvement over a non-hierarchical baseline.
Domain Adaptation for Visual Recognition
TLDR
This monograph provides a comprehensive view of domain adaptation solutions for visual recognition problems under uncertainty, analyzing the challenges posed by the realm of "big visual data", in terms of the generalization ability of adaptation algorithms to unconstrained data acquisition as well as issues related to their computational tractability.
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
Deep Transfer Network: Unsupervised Domain Adaptation
TLDR
This paper proposes a new domain adaptation framework named Deep Transfer Network (DTN), where the highly flexible deep neural networks are used to implement such a distribution matching process, and demonstrates that DTN improves significantly over former methods in both execution time and classification accuracy.
...
1
2
3
...