Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Bang Jihwan"'
The customization of large language models (LLMs) for user-specified tasks gets important. However, maintaining all the customized LLMs on cloud servers incurs substantial memory and computational overheads, and uploading user data can also lead to p
Externí odkaz:
http://arxiv.org/abs/2406.07007
We propose a novel framework DropTop that suppresses the shortcut bias in online continual learning (OCL) while being adaptive to the varying degree of the shortcut bias incurred by continuously changing environment. By the observed high-attention pr
Externí odkaz:
http://arxiv.org/abs/2312.08677
Pre-trained Vision Language Models (VLMs) have demonstrated notable progress in various zero-shot tasks, such as classification and retrieval. Despite their performance, because improving performance on new tasks requires task-specific knowledge, the
Externí odkaz:
http://arxiv.org/abs/2311.11178
Autor:
Kim, Doyoung, Yoon, Susik, Park, Dongmin, Lee, Youngjun, Song, Hwanjun, Bang, Jihwan, Lee, Jae-Gil
In real-world continual learning (CL) scenarios, tasks often exhibit intricate and unpredictable semantic shifts, posing challenges for fixed prompt management strategies which are tailored to only handle semantic shifts of uniform degree (i.e., unif
Externí odkaz:
http://arxiv.org/abs/2311.12048
Autor:
Song, Hwanjun, Bang, Jihwan
Prompt-OVD is an efficient and effective framework for open-vocabulary object detection that utilizes class embeddings from CLIP as prompts, guiding the Transformer decoder to detect objects in both base and novel classes. Additionally, our novel RoI
Externí odkaz:
http://arxiv.org/abs/2303.14386
Unlabeled data examples awaiting annotations contain open-set noise inevitably. A few active learning studies have attempted to deal with this open-set noise for sample selection by filtering out the noisy examples. However, because focusing on the p
Externí odkaz:
http://arxiv.org/abs/2210.07805
Learning under a continuously changing data distribution with incorrect labels is a desirable real-world problem yet challenging. A large body of continual learning (CL) methods, however, assumes data streams with clean labels, and online learning sc
Externí odkaz:
http://arxiv.org/abs/2203.15355
Publikováno v:
In AJIC: American Journal of Infection Control August 2024 52(8):958-963
Continual learning is a realistic learning scenario for AI models. Prevalent scenario of continual learning, however, assumes disjoint sets of classes as tasks and is less realistic rather artificial. Instead, we focus on 'blurry' task boundary; wher
Externí odkaz:
http://arxiv.org/abs/2103.17230