Related papers: CODA: A Continuous Online Evolve Framework for Dep…
Continuous Domain Adaptation (CDA) effectively bridges significant domain shifts by progressively adapting from the source domain through intermediate domains to the target domain. However, selecting intermediate domains without explicit…
Modeling implicit feature interaction patterns is of significant importance to object detection tasks. However, in the two-stage detectors, due to the excessive use of hand-crafted components, it is very difficult to reason about the…
Continuous-time models are a natural choice for irregular and asynchronous data. A central design choice is how to embed discrete observations into continuous time. Interpolation- and imputation-based embeddings reconstruct a continuous…
Continual Test-Time Adaptation (CTTA) aims to adapt a source pre-trained model to continually changing target domains during inference. As a fundamental principle, an ideal CTTA method should rapidly adapt to new domains (exploration) while…
On-the-Fly Category Discovery (OCD) requires a model, trained on an offline support set, to recognize known classes while discovering new ones from an online streaming sequence. Existing methods focus heavily on offline training. They aim…
Multi-source Domain Adaptation (MDA) seeks to adapt models trained on data from multiple labeled source domains to perform effectively on an unlabeled target domain data, assuming access to sources data. To address the challenges of model…
Domain adaptation (DA) tackles the issue of distribution shift by learning a model from a source domain that generalizes to a target domain. However, most existing DA methods are designed for scenarios where the source and target domain…
With the advancement of mobile device capabilities, deploying reranking models directly on devices has become feasible, enabling real-time contextual recommendations. When migrating models from cloud to devices, resource heterogeneity…
In the era of data explosion, a growing number of data-intensive computing frameworks, such as Apache Hadoop and Spark, have been proposed to handle the massive volume of unstructured data in parallel. Since programming models provided by…
Test-time adaptation (TTA) aims to address distributional shifts between training and testing data using only unlabeled test data streams for continual model adaptation. However, most TTA methods assume benign test streams, while test…
Continuous Video Domain Adaptation (CVDA) is a scenario where a source model is required to adapt to a series of individually available changing target domains continuously without source data or target supervision. It has wide…
Test-time adaptation (TTA) is a technique used to reduce distribution gaps between the training and testing sets by leveraging unlabeled test data during inference. In this work, we expand TTA to a more practical scenario, where the test…
Foundation models have transformed language, vision, and time series data analysis, yet progress on dynamic predictions for physical systems remains limited. Given the complexity of physical constraints, two challenges stand out. $(i)$…
Offline reinforcement learning (RL) enables policy learning from pre-collected offline datasets, relaxing the need to interact directly with the environment. However, limited by the quality of offline datasets, it generally fails to learn…
This paper introduces ReservoirTTA, a novel plug-in framework designed for prolonged test-time adaptation (TTA) in scenarios where the test domain continuously shifts over time, including cases where domains recur or evolve gradually. At…
Open-Vocabulary Temporal Action Detection (OV-TAD) aims to classify and localize action segments in untrimmed videos for unseen categories. Previous methods rely solely on global alignment between label-level semantics and visual features,…
Online learning is a powerful tool for analyzing iterative algorithms. However, the classic adversarial setup sometimes fails to capture certain regularity in online problems in practice. Motivated by this, we establish a new setup, called…
Active learning aims to improve the performance of task model by selecting the most informative samples with a limited budget. Unlike most recent works that focused on applying active learning for image classification, we propose an…
Modern data workflows are inherently adaptive, repeatedly querying the same dataset to refine and validate sequential decisions, but such adaptivity can lead to overfitting and invalid statistical inference. Adaptive Data Analysis (ADA)…
Multiple object tracking has been a challenging field, mainly due to noisy detection sets and identity switch caused by occlusion and similar appearance among nearby targets. Previous works rely on appearance models built on individual or…