Learning Cascaded Detection Tasks with Weakly-Supervised Domain Adaptation

by   Niklas Hanselmann, et al.

In order to handle the challenges of autonomous driving, deep learning has proven to be crucial in tackling increasingly complex tasks, such as 3D detection or instance segmentation. State-of-the-art approaches for image-based detection tasks tackle this complexity by operating in a cascaded fashion: they first extract a 2D bounding box based on which additional attributes, e.g. instance masks, are inferred. While these methods perform well, a key challenge remains the lack of accurate and cheap annotations for the growing variety of tasks. Synthetic data presents a promising solution but, despite the effort in domain adaptation research, the gap between synthetic and real data remains an open problem. In this work, we propose a weakly supervised domain adaptation setting which exploits the structure of cascaded detection tasks. In particular, we learn to infer the attributes solely from the source domain while leveraging 2D bounding boxes as weak labels in both domains to explain the domain shift. We further encourage domain-invariant features through class-wise feature alignment using ground-truth class information, which is not available in the unsupervised setting. As our experiments demonstrate, the approach is competitive with fully supervised settings while outperforming unsupervised adaptation approaches by a large margin.


page 1

page 4

page 6

page 7


Box-Adapt: Domain-Adaptive Medical Image Segmentation using Bounding BoxSupervision

Deep learning has achieved remarkable success in medicalimage segmentati...

WUDA: Unsupervised Domain Adaptation Based on Weak Source Domain Labels

Unsupervised domain adaptation (UDA) for semantic segmentation addresses...

Simple Does It: Weakly Supervised Instance and Semantic Segmentation

Semantic labelling and instance segmentation are two tasks that require ...

Cross-Modality Domain Adaptation for Freespace Detection: A Simple yet Effective Baseline

As one of the fundamental functions of autonomous driving system, freesp...

Domain Adaptation-based Augmentation for Weakly Supervised Nuclei Detection

The detection of nuclei is one of the most fundamental components of com...

What Synthesis is Missing: Depth Adaptation Integrated with Weak Supervision for Indoor Scene Parsing

Scene Parsing is a crucial step to enable autonomous systems to understa...

ShoeRinsics: Shoeprint Prediction for Forensics with Intrinsic Decomposition

Shoe tread impressions are one of the most common types of evidence left...

Please sign up or login with your details

Forgot password? Click here to reset