相关论文: Contrastive Learning for Cross-Domain Open World R…

In the era of big data and Artificial Intelligence, an emerging paradigm is to utilize contrastive self-supervised learning to model large-scale heterogeneous data. Many existing foundation models benefit from the generalization capability…

The thesis contributes in several important ways to the research area of 3D object category learning and recognition. To cope with the mentioned limitations, we look at human cognition, in particular at the fact that human beings learn to…

Neural networks have revolutionized various domains, exhibiting remarkable accuracy in tasks like natural language processing and computer vision. However, their vulnerability to slight alterations in input samples poses challenges,…

Semantic segmentation in autonomous driving predominantly focuses on learning from large-scale data with a closed set of known classes without considering unknown objects. Motivated by safety reasons, we address the video class agnostic…

Labeling videos at scale is impractical. Consequently, self-supervised visual representation learning is key for efficient video analysis. Recent success in learning image representations suggests contrastive learning is a promising…

Radio Frequency (RF) device fingerprinting has been recognized as a potential technology for enabling automated wireless device identification and classification. However, it faces a key challenge due to the domain shift that could arise…

In an effort to reduce annotation costs in action recognition, unsupervised video domain adaptation methods have been proposed that aim to adapt a predictive model from a labelled dataset (i.e., source domain) to an unlabelled dataset…

Cross-domain sentiment analysis aims to predict the sentiment of texts in the target domain using the model trained on the source domain to cope with the scarcity of labeled data. Previous studies are mostly cross-entropy-based methods for…

Robotic tasks such as manipulation with visual inputs require image features that capture the physical properties of the scene, e.g., the position and configuration of objects. Recently, it has been suggested to learn such features in an…

Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their…

Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. Such generality for transfer learning, however, sacrifices specificity if we are interested in a certain downstream…

The goal of contrastive learning based pre-training is to leverage large quantities of unlabeled data to produce a model that can be readily adapted downstream. Current approaches revolve around solving an image discrimination task: given…

How can you sample good negative examples for contrastive learning? We argue that, as with metric learning, contrastive learning of representations benefits from hard negative samples (i.e., points that are difficult to distinguish from an…

We propose Domain-Conditioned Meta-Contrastive Learning, a framework for improving the cross-domain generalization of vision-language models. While contrastive models such as CLIP achieve strong performance through large-scale training,…

We present Domain Contrast (DC), a simple yet effective approach inspired by contrastive learning for training domain adaptive detectors. DC is deduced from the error bound minimization perspective of a transferred model, and is implemented…

Deep neural networks (DNNs) have achieved remarkable success in computer vision tasks such as image classification, segmentation, and object detection. However, they are vulnerable to adversarial attacks, which can cause incorrect…

Current state-of-the-art object-centric models use slots and attention-based routing for binding. However, this class of models has several conceptual limitations: the number of slots is hardwired; all slots have equal capacity; training…

Recently,the detection transformer has gained substantial attention for its inherent minimal post-processing requirement.However,this paradigm relies on abundant training data,yet in the context of the cross-domain adaptation,insufficient…

Contrastive Learning has recently received interest due to its success in self-supervised representation learning in the computer vision domain. However, the origins of Contrastive Learning date as far back as the 1990s and its development…

We present a new approach to instill 4D dynamic object priors into learned 3D representations by unsupervised pre-training. We observe that dynamic movement of an object through an environment provides important cues about its objectness,…