Related papers: MoExDA: Domain Adaptation for Edge-based Action Re…

Domain adaptive detection aims to improve the generalization of detectors on target domain. To reduce discrepancy in feature distributions between two domains, recent approaches achieve domain adaption through feature alignment in different…

Unsupervised domain adaptation (UDA) has become increasingly prevalent in scene text recognition (STR), especially where training and testing data reside in different domains. The efficacy of existing UDA approaches tends to degrade when…

Recent deep learning methods for object detection rely on a large amount of bounding box annotations. Collecting these annotations is laborious and costly, yet supervised models do not generalize well when testing on images from a different…

Domain adaptation is critical for success in new, unseen environments. Adversarial adaptation models applied in feature spaces discover domain invariant representations, but are difficult to visualize and sometimes fail to capture…

In video action recognition, shortcut static features can interfere with the learning of motion features, resulting in poor out-of-distribution (OOD) generalization. The video background is clearly a source of static bias, but the video…

Deep motion forecasting models have achieved great success when trained on a massive amount of data. Yet, they often perform poorly when training data is limited. To address this challenge, we propose a transfer learning approach for…

While huge volumes of unlabeled data are generated and made available in many domains, the demand for automated understanding of visual data is higher than ever before. Most existing machine learning models typically rely on massive amounts…

We address multi-view pedestrian detection in a setting where labeled data is collected using a multi-camera setup different from the one used for testing. While recent multi-view pedestrian detectors perform well on the camera rig used for…

In precision agriculture, vision models often struggle with new, unseen fields where crops and weeds have been influenced by external factors, resulting in compositions and appearances that differ from the learned distribution. This paper…

In this paper, we propose a new method called Gradual Domain Osmosis, which aims to solve the problem of smooth knowledge migration from source domain to target domain in Gradual Domain Adaptation (GDA). Traditional Gradual Domain…

Scene recognition is one of the basic problems in computer vision research with extensive applications in robotics. When available, depth images provide helpful geometric cues that complement the RGB texture information and help to identify…

Multisource domain adaptation (MDA) aims to use multiple source datasets with available labels to infer labels on a target dataset without available labels for target supervision. Prior works on MDA in the literature is ad-hoc as the…

Recent face presentation attack detection (PAD) leverages domain adaptation (DA) and domain generalization (DG) techniques to address performance degradation on unknown domains. However, DA-based PAD methods require access to unlabeled…

Multi-modal unsupervised domain adaptation (MM-UDA) for 3D semantic segmentation is a practical solution to embed semantic understanding in autonomous systems without expensive point-wise annotations. While previous MM-UDA methods can…

We focus on bridging domain discrepancy in lane detection among different scenarios to greatly reduce extra annotation and re-training costs for autonomous driving. Critical factors hinder the performance improvement of cross-domain lane…

Recent works have demonstrated convolutional neural networks are vulnerable to adversarial examples, i.e., inputs to machine learning models that an attacker has intentionally designed to cause the models to make a mistake. To improve the…

Existing object detection models assume both the training and test data are sampled from the same source domain. This assumption does not hold true when these detectors are deployed in real-world applications, where they encounter new…

Real-time video analytics on edge devices for changing scenes remains a difficult task. As edge devices are usually resource-constrained, edge deep neural networks (DNNs) have fewer weights and shallower architectures than general DNNs. As…

Domain adaptation aims to leverage the supervision signal of source domain to obtain an accurate model for target domain, where the labels are not available. To leverage and adapt the label information from source domain, most existing…

This paper presents our proposed methods for domain adaptive pedestrian re-identification (Re-ID) task in Visual Domain Adaptation Challenge (VisDA-2020). Considering the large gap between the source domain and target domain, we focused on…