Zobrazeno 1 - 10
of 497
pro vyhledávání: '"Gong, Yihong"'
Existing prompt learning methods in Vision-Language Models (VLM) have effectively enhanced the transfer capability of VLM to downstream tasks, but they suffer from a significant decline in generalization due to severe overfitting. To address this iss
Externí odkaz:
http://arxiv.org/abs/2410.10247
Non-exemplar class Incremental Learning (NECIL) enables models to continuously acquire new classes without retraining from scratch and storing old task exemplars, addressing privacy and storage issues. However, the absence of data from earlier tasks
Externí odkaz:
http://arxiv.org/abs/2409.14983
Diffusion models have revolutionized customized text-to-image generation, allowing for efficient synthesis of photos from personal data with textual descriptions. However, these advancements bring forth risks including privacy breaches and unauthoriz
Externí odkaz:
http://arxiv.org/abs/2408.10571
The problem of Rehearsal-Free Continual Learning (RFCL) aims to continually learn new knowledge while preventing forgetting of the old knowledge, without storing any old samples and prototypes. The latest methods leverage large-scale pre-trained mode
Externí odkaz:
http://arxiv.org/abs/2407.10281
This paper introduces the point-axis representation for oriented object detection, emphasizing its flexibility and geometrically intuitive nature with two key components: points and axes. 1) Points delineate the spatial extent and contours of objects
Externí odkaz:
http://arxiv.org/abs/2407.08489
Continual Novel Class Discovery (CNCD) aims to continually discover novel classes without labels while maintaining the recognition capability for previously learned classes. The main challenges faced by CNCD include the feature-discrepancy problem, t
Externí odkaz:
http://arxiv.org/abs/2405.06389
Online task-free continual learning (OTFCL) is a more challenging variant of continual learning which emphasizes the gradual shift of task boundaries and learns in an online mode. Existing methods rely on a memory buffer composed of old samples to pr
Externí odkaz:
http://arxiv.org/abs/2404.13576
Detecting anomaly patterns from images is a crucial artificial intelligence technique in industrial applications. Recent research in this domain has emphasized the necessity of a large volume of training data, overlooking the practical scenario where
Externí odkaz:
http://arxiv.org/abs/2403.18201
In real-world applications, dynamic scenarios require the models to possess the capability to learn new tasks continuously without forgetting the old knowledge. Experience-Replay methods store a subset of the old images for joint training. In the sce
Externí odkaz:
http://arxiv.org/abs/2403.06670
We present ARTrackV2, which integrates two pivotal aspects of tracking: determining where to look (localization) and how to describe (appearance analysis) the target object across video frames. Building on the foundation of its predecessor, ARTrackV2
Externí odkaz:
http://arxiv.org/abs/2312.17133