Zobrazeno 1 - 10
of 111
pro vyhledávání: '"Martinez, Brais"'
Data point selection (DPS) is becoming a critical topic in deep learning due to the ease of acquiring uncurated training data compared to the difficulty of obtaining curated or processed data. Existing approaches to DPS are predominantly based on a b
Externí odkaz:
http://arxiv.org/abs/2411.03768
Autor:
Tan, Fuwen, Lee, Royson, Dudziak, Łukasz, Hu, Shell Xu, Bhattacharya, Sourav, Hospedales, Timothy, Tzimiropoulos, Georgios, Martinez, Brais
Large language models (LLMs) have revolutionized language processing, delivering outstanding results across multiple applications. However, deploying LLMs on edge devices poses several challenges with respect to memory, energy, and compute costs, lim
Externí odkaz:
http://arxiv.org/abs/2408.13933
Despite recent successes, LVLMs or Large Vision Language Models are prone to hallucinating details like objects and their properties or relations, limiting their real-world deployment. To address this and improve their robustness, we present CLIP-DPO
Externí odkaz:
http://arxiv.org/abs/2408.10433
In this paper, we introduce YONOS-SR, a novel stable diffusion-based approach for image super-resolution that yields state-of-the-art results using only a single DDIM step. We propose a novel scale distillation approach to train our SR model. Instead
Externí odkaz:
http://arxiv.org/abs/2401.17258
Autor:
Pham, Hai X., Hadji, Isma, Xu, Xinnuo, Degutyte, Ziedune, Rainey, Jay, Kazakos, Evangelos, Fazly, Afsaneh, Tzimiropoulos, Georgios, Martinez, Brais
In this paper, we focus on task-specific question answering (QA). To this end, we introduce a method for generating exhaustive and high-quality training data, which allows us to train compact (e.g., run on a mobile device), task-specific QA models th
Externí odkaz:
http://arxiv.org/abs/2401.13594
Autor:
Metaxas, Ioannis Maniadis, Bulat, Adrian, Patras, Ioannis, Martinez, Brais, Tzimiropoulos, Georgios
The unsupervised pretraining of object detectors has recently become a key component of object detector training, as it leads to improved performance and faster convergence during the supervised fine-tuning stage. Existing unsupervised pretraining me
Externí odkaz:
http://arxiv.org/abs/2307.15697
Vision-Language (V-L) models trained with contrastive learning to align the visual and language modalities have been shown to be strong few-shot learners. Soft prompt learning is the method of choice for few-shot downstream adaptation aiming to bridg
Externí odkaz:
http://arxiv.org/abs/2304.01752
Autor:
Dvornik, Nikita, Hadji, Isma, Pham, Hai, Bhatt, Dhaivat, Martinez, Brais, Fazly, Afsaneh, Jepson, Allan D.
Publikováno v:
ECCV 2022
In this work, we consider the problem of weakly-supervised multi-step localization in instructional videos. An established approach to this problem is to rely on a given list of steps. However, in reality, there is often more than one way to execute
Externí odkaz:
http://arxiv.org/abs/2210.04996
This paper is on Few-Shot Object Detection (FSOD), where given a few templates (examples) depicting a novel class (not seen during training), the goal is to detect all of its occurrences within a set of images. From a practical perspective, an FSOD s
Externí odkaz:
http://arxiv.org/abs/2210.04845
Despite the impressive progress of self-supervised learning (SSL), its applicability to low-compute networks has received limited attention. Reported performance has trailed behind standard supervised pre-training by a large margin, barring self-supe
Externí odkaz:
http://arxiv.org/abs/2210.02808