Generalization to unseen data remains poorly understood for deep learning classification and foundation models, especially in the open set scenario. How can one assess the ability of networks to adapt to new or extended versions of their input space in the spirit of few-shot learning, out-of-distribution generalization, domain adaptation, and category discovery? Which layers of a network are likely to generalize best? We provide a new method for evaluating the capacity of networks to represent a sampled domain, regardless of whether the network has been trained on all classes in that domain. Our approach is the following: after fine-tuning state-of-the-art pre-trained models for visual classification on a particular domain, we assess their performance on data from related but distinct variations in that domain. Generalization power is quantified as a function of the latent embeddings of unseen data from intermediate layers for both unsupervised and supervised settings. Working throughout all stages of the network, we find that (i) high classification accuracy does not imply high generalizability; and (ii) deeper layers in a model do not always generalize the best, which has implications for pruning. Since the trends observed across datasets are largely consistent, we conclude that our approach reveals (a function of) the intrinsic capacity of the different layers of a model to generalize. Our code is available at https://github.com/dyballa/generalization
Transitive Vision-Language Prompt Learning for Domain Generalization
Xiamen University(厦门大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)(广东省人工智能与数字经济实验室(深圳))
What Are We Really Measuring? Rethinking Dataset Bias in Web-Scale Natural Image Collections via Unsupervised Semantic Clustering
School of Electrical Engineering, Iran University of Science and Technology (IUST)(伊朗科学技术大学电气工程学院);Okinawa Institute of Science and Technology (OIST)(冲绳科学技术大学院大学)
Technical Report: Quantifying and Analyzing the Generalization Power of a DNN
University of Electronic Science and Technology of China(电子科技大学);Shanghai Jiao Tong University(上海交通大学);Institute of Artificial Intelligence, China Telecom(中国电信人工智能研究院)
Cross-Fusion Distance: A Novel Metric for Measuring Fusion and Separability Between Data Groups in Representation Space
CEDAR, Knight Cancer Institute, Oregon Health and Science University, OR, USA(CEDAR、骑士癌症研究所、俄勒冈健康与科学大学,俄勒冈州,美国);Brenden-Colson Center for Pancreatic Care, Oregon Health and Science University, OR, USA(布伦登-科尔森胰腺护理中心、俄勒冈健康与科学大学,俄勒冈州,美国)
OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization
Shanghai Jiao Tong University(上海交通大学);Huawei Noah’s Ark Lab(华为诺亚方舟实验室);Hong Kong University of Science and Technology(香港科技大学);Tsinghua University(清华大学)
深度学习在独立同分布(independent and identical distributed,i.i.d.)数据然而,神经网络的性能通常在遇到分布外(OoD)数据时急剧退化,即,当训练和测试数据从不同的分布中采样时。虽然已经提出了过多的算法用于OoD泛化,但我们对用于训练和评估这些算法的数据的理解仍然停滞不前。在这项工作中,我们首先确定和测量两种不同的分布偏移,是普遍存在于各种数据集。接下来,通过大量的实验,我们比较OoD泛化算法在两组基准测试,每个占主导地位的分布偏移,揭示他们的优势,以及对其他移动的限制。总的来说,我们将来自不同研究领域的现有数据集和算法定位为同一个连贯的图像。它可以作为一个立足点,可以诉诸未来的面向对象的泛化研究。我们的代码可在www.example.com上获得。
Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons
RIKEN AIP(日本学术振兴会先进研究所);The University of Hong Kong(香港大学);National University of Singapore(新加坡国立大学);The University of New South Wales(新南威尔士大学);University of Tokyo(东京大学)
Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness
Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);University of Chinese Academy of Sciences(中国科学院大学);Brown University(布朗大学)
Quantifying Overfitting: Evaluating Neural Network Performance through Analysis of Null Space
Iran University of Science and Technology(伊朗科技大学);Okinawa Institute of Science and Technology(冲绳科学技术研究所);Institute For Research In Fundamental Sciences(基础科学研究所)