Related papers: Learning Causal Domain-Invariant Temporal Dynamics…

Cross-domain few-shot segmentation (CD-FSS) is proposed to pre-train the model on a source-domain dataset with sufficient samples, and then transfer the model to target-domain datasets where only a few samples are available for efficient…

Most existing multivariate time series forecasting methods adopt an all-to-all paradigm that feeds all variable histories into a unified model to predict their future values without distinguishing their individual roles. However, this…

Current video representations heavily rely on learning from manually annotated video datasets which are time-consuming and expensive to acquire. We observe videos are naturally accompanied by abundant text information such as YouTube titles…

In this paper, we describe a simple strategy for mitigating variability in temporal data series by shifting focus onto long-term, frequency domain features that are less susceptible to variability. We apply this method to the human action…

Continual Test Time Adaptation (CTTA) has emerged as a critical approach for bridging the domain gap between the controlled training environments and the real-world scenarios, enhancing model adaptability and robustness. Existing CTTA…

Cross-domain few-shot object detection (CD-FSOD) aims to adapt pretrained detectors from a source domain to target domains with limited annotations, suffering from severe domain shifts and data scarcity problems. In this work, we find a…

With the continuous development of natural language processing (NLP) technology, text classification tasks have been widely used in multiple application fields. However, obtaining labeled data is often expensive and difficult, especially in…

Iris presentation attack detection (PAD) has achieved remarkable success to ensure the reliability and security of iris recognition systems. Most existing methods exploit discriminative features in the spatial domain and report outstanding…

Imitation learning enables high-fidelity, vision-based learning of policies within rich, photorealistic environments. However, such techniques often rely on traditional discrete-time neural models and face difficulties in generalizing to…

Temporally causal representation learning aims to identify the latent causal process from time series observations, but most methods require the assumption that the latent causal processes do not have instantaneous relations. Although some…

Semi-supervised domain adaptation (SSDA) aims to solve tasks in target domain by utilizing transferable information learned from the available source domain and a few labeled target data. However, source data is not always accessible in…

Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance, deemed promising for next-generation image compression techniques. However, pre-trained LIC models usually suffer from significant performance…

Few-shot domain adaptation to multiple domains aims to learn a complex image distribution across multiple domains from a few training images. A na\"ive solution here is to train a separate model for each domain using few-shot domain…

Existing Unsupervised Domain Adaptation (UDA) literature adopts the covariate shift and conditional shift assumptions, which essentially encourage models to learn common features across domains. However, due to the lack of supervision in…

In real-world applications, it is important and desirable to learn a model that performs well on out-of-distribution (OOD) data. Recently, causality has become a powerful tool to tackle the OOD generalization problem, with the idea resting…

Unsupervised Domain Adaptation aims to learn a model on a source domain with labeled data in order to perform well on unlabeled data of a target domain. Current approaches focus on learning \textit{Domain Invariant Representations}. It…

Few-shot classification consists of learning a predictive model that is able to effectively adapt to a new class, given only a few annotated samples. To solve this challenging problem, meta-learning has become a popular paradigm that…

Cross-Domain Few-Shot Learning has witnessed great stride with the development of meta-learning. However, most existing methods pay more attention to learning domain-adaptive inductive bias (meta-knowledge) through feature-wise manipulation…

In this paper, we aim to adapt a model at test-time using a few unlabeled data to address distribution shifts. To tackle the challenges of extracting domain knowledge from a limited amount of data, it is crucial to utilize correlated…

Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…