Zobrazeno 1 - 10
of 135
pro vyhledávání: '"Gou, Liang"'
The emergence of large-scale pre-trained models has heightened their application in various downstream tasks, yet deployment is a challenge in environments with limited computational resources. Knowledge distillation has emerged as a solution in such
Externí odkaz:
http://arxiv.org/abs/2406.17838
Autor:
Wang, Xiaoqi, He, Wenbin, Xuan, Xiwei, Sebastian, Clint, Ono, Jorge Piazentin, Li, Xin, Behpour, Sima, Doan, Thang, Gou, Liang, Shen, Han Wei, Ren, Liu
The open-vocabulary image segmentation task involves partitioning images into semantically meaningful segments and classifying them with flexible text-defined categories. The recent vision-based foundation models such as the Segment Anything Model (S
Externí odkaz:
http://arxiv.org/abs/2406.05271
Despite demonstrating robust capabilities in performing tasks related to general-domain data-operation tasks, Large Language Models (LLMs) may exhibit shortcomings when applied to domain-specific tasks. We consider the design of domain-specific AI-po
Externí odkaz:
http://arxiv.org/abs/2405.05548
Few-shot Class-Incremental Learning (FSCIL) poses the challenge of retaining prior knowledge while learning from limited new data streams, all without overfitting. The rise of Vision-Language models (VLMs) has unlocked numerous applications, leveragi
Externí odkaz:
http://arxiv.org/abs/2403.06295
Data slice finding is an emerging technique for validating machine learning (ML) models by identifying and analyzing subgroups in a dataset that exhibit poor performance, often characterized by distinct feature sets or descriptive metadata. However,
Externí odkaz:
http://arxiv.org/abs/2401.06462
Deep learning models are widely used in critical applications, highlighting the need for pre-deployment model understanding and improvement. Visual concept-based methods, while increasingly used for this purpose, face challenges: (1) most concepts la
Externí odkaz:
http://arxiv.org/abs/2311.03547
Detecting out-of-distribution (OOD) data is crucial for ensuring the safe deployment of machine learning models in real-world applications. However, existing OOD detection approaches primarily rely on the feature maps or the full gradient space infor
Externí odkaz:
http://arxiv.org/abs/2308.00310
In this study, we investigate the task of data pre-selection, which aims to select instances for labeling from an unlabeled dataset through a single pass, thereby optimizing performance for undefined downstream tasks with a limited annotation budget.
Externí odkaz:
http://arxiv.org/abs/2307.11227
Open World Object Detection (OWOD) is a challenging and realistic task that extends beyond the scope of standard Object Detection task. It involves detecting both known and unknown objects while integrating learned knowledge for future tasks. However
Externí odkaz:
http://arxiv.org/abs/2306.14291
Existing semantic segmentation approaches are often limited by costly pixel-wise annotations and predefined classes. In this work, we present CLIP-S$^4$ that leverages self-supervised pixel representation learning and vision-language models to enable
Externí odkaz:
http://arxiv.org/abs/2305.01040