Related papers: Learning Cross-modal Contrastive Features for Vide…
Recently the problem of cross-domain object detection has started drawing attention in the computer vision community. In this paper, we propose a novel unsupervised cross-domain detection model that exploits the annotated data in a source…
Domain adaptation aims to learn models on a supervised source domain that perform well on an unsupervised target. Prior work has examined domain adaptation in the context of stationary domain shifts, i.e. static data sets. However, with…
A basic assumption of statistical learning theory is that train and test data are drawn from the same underlying distribution. Unfortunately, this assumption doesn't hold in many applications. Instead, ample labeled data might exist in a…
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for medical image segmentation, yet need plenty of manual annotations for training. Semi-Supervised Learning (SSL) methods are promising to reduce the…
Understanding dark scenes based on multi-modal image data is challenging, as both the visible and auxiliary modalities provide limited semantic information for the task. Previous methods focus on fusing the two modalities but neglect the…
We propose a self-supervised method to learn feature representations from videos. A standard approach in traditional self-supervised methods uses positive-negative data pairs to train with contrastive learning strategy. In such a case,…
Domain adaptation (DA) aims to transfer discriminative features learned from source domain to target domain. Most of DA methods focus on enhancing feature transferability through domain-invariance learning. However, source-learned…
The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an unlabeled target domain, with a similar but different data distribution. Most deep learning approaches to…
The remarkable success of deep learning in various domains relies on the availability of large-scale annotated datasets. However, obtaining annotations is expensive and requires great effort, which is especially challenging for videos.…
Video semantic segmentation is an essential task for the analysis and understanding of videos. Recent efforts largely focus on supervised video segmentation by learning from fully annotated data, but the learnt models often experience clear…
Although deep convolutional networks have achieved great performance in face recognition tasks, the challenge of domain discrepancy still exists in real world applications. Lack of domain coverage of training data (source domain) makes the…
Temporal grounding, which localizes video moments related to a natural language query, is a core problem of vision-language learning and video understanding. To encode video moments of varying lengths, recent methods employ a multi-level…
Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching…
Domain Generalization (DG) aims to learn a model that can generalize well to unseen target domains from a set of source domains. With the idea of invariant causal mechanism, a lot of efforts have been put into learning robust causal effects…
Human behavior understanding in videos is a complex, still unsolved problem and requires to accurately model motion at both the local (pixel-wise dense prediction) and global (aggregation of motion cues) levels. Current approaches based on…
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…
Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain.…
People can recognize scenes across many different modalities beyond natural images. In this paper, we investigate how to learn cross-modal scene representations that transfer across modalities. To study this problem, we introduce a new…
This work presents a novel domain adaption paradigm for studying contrastive self-supervised representation learning and knowledge transfer using remote sensing satellite data. Major state-of-the-art remote sensing visual domain efforts…
Unsupervised domain adaptive segmentation aims to improve the segmentation accuracy of models on target domains without relying on labeled data from those domains. This approach is crucial when labeled target domain data is scarce or…