Neural Architecture Search (NAS) has gained attraction due to superior classification performance. Differential Architecture Search (DARTS) is a computationally light method. To limit computational resources DARTS makes numerous approximations. These approximations result in inferior performance. We propose to fine-tune DARTS using fixed operations as they are independent of these approximations. Our method offers a good trade-off between the number of parameters and classification accuracy. Our approach improves the top-1 accuracy on Fashion-MNIST, CompCars, and MIO-TCD datasets by 0.56%, 0.50%, and 0.39%, respectively compared to the state-of-the-art approaches. Our approach performs better than DARTS, improving the accuracy by 0.28%, 1.64%, 0.34%, 4.5%, and 3.27% compared to DARTS, on CIFAR-10, CIFAR-100, Fashion-MNIST, CompCars, and MIO-TCD datasets, respectively.
University of Waterloo（滑铁卢大学）；University of New Brunswick（新不伦瑞克大学）；Sunnybrook Health Science Center（桑尼布鲁克健康科学中心）；Kingston Health Sciences Center（金斯顿健康科学中心）；St. Michaels Hospital（圣迈克尔医院）；Huron Digital Pathology（休伦数字病理公司）；University of Toronto（多伦多大学）
AI technology has made remarkable achievements in computational pathology (CPath), especially with the help of deep neural networks. However, the network performance is highly related to architecture design, which commonly requires human experts with domain knowledge. In this paper, we combat this challenge with the recent advance in neural architecture search (NAS) to find an optimal network for CPath applications. In particular, we use differentiable architecture search (DARTS) for its efficiency. We first adopt a probing metric to show that the original DARTS lacks proper hyperparameter tun…
Vision-Language Model Fine-Tuning via Simple Parameter-Efficient Modification
The University of Tokyo（东京大学）；University of Southern California（南加州大学）；The Chinese University of Hong Kong（香港中文大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）
We study a practical setting of continual learning: fine-tuning on a pre-trained model continually. Previous work has found that, when training on new tasks, the features (penultimate layer representations) of previous data will change, called representational shift. Besides the shift of features, we reveal that the intermediate layers' representational shift (IRS) also matters since it disrupts batch normalization, which is another crucial cause of catastrophic forgetting. Motivated by this, we propose ConFiT, a fine-tuning method incorporating two components, cross-convolution batch normaliz…
Seoul National University（首尔国立大学）；Samsung SDS（三星SDS）
Existing fine-tuning methods use a single learning rate over all layers. In this paper, first, we discuss that trends of layer-wise weight variations by fine-tuning using a single learning rate do not match the well-known notion that lower-level layers extract general features and higher-level layers extract specific features. Based on our discussion, we propose an algorithm that improves fine-tuning performance and reduces network complexity through layer-wise pruning and auto-tuning of layer-wise learning rates. The proposed algorithm has verified the effectiveness by achieving state-of-the-…
When transferring a pretrained model to a downstream task, two popular methods are full fine-tuning (updating all the model parameters) and linear probing (updating only the last linear layer -- the "head"). It is well known that fine-tuning leads to better accuracy in-distribution (ID). However, in this paper, we find that fine-tuning can achieve worse accuracy than linear probing out-of-distribution (OOD) when the pretrained features are good and the distribution shift is large. On 10 distribution shift datasets (Breeds-Living17, Breeds-Entity30, DomainNet, CIFAR $\to$ STL, CIFAR10.1, FMoW, …
National University of Singapore（新加坡国立大学）；Chinese Academy of Sciences（中国科学院）；SEA AI Lab（SEA AI实验室）
Contrastive self-supervised learning (CSL) has attracted increasing attention for model pre-training via unlabeled data. The resulted CSL models provide instance-discriminative visual features that are uniformly scattered in the feature space. During deployment, the common practice is to directly fine-tune CSL models with cross-entropy, which however may not be the best strategy in practice. Although cross-entropy tends to separate inter-class features, the resulting models still have limited capability for reducing intra-class feature scattering that exists in CSL models. In this paper, we in…
Amazon Web Services（亚马逊云科技）；University of Pennsylvania（宾夕法尼亚大学）；University of California, Los Angeles（加州大学洛杉矶分校）
Fine-tuning from pre-trained ImageNet models has become the de-facto standard for various computer vision tasks. Current practices for fine-tuning typically involve selecting an ad-hoc choice of hyperparameters and keeping them fixed to values normally used for training from scratch. This paper re-examines several common practices of setting hyperparameters for fine-tuning. Our findings are based on extensive empirical evaluation for fine-tuning on various transfer learning benchmarks. (1) While prior works have thoroughly investigated learning rate and batch size, momentum for fine-tuning is …
University of Washington（华盛顿大学）；OpenAI；Columbia University（哥伦比亚大学）；Google Research（谷歌研究院）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Toyota Research Institute（丰田研究院）
Large pre-trained models such as CLIP or ALIGN offer consistent accuracy across a range of data distributions when performing zero-shot inference (i.e., without fine-tuning on a specific dataset). Although existing fine-tuning methods substantially improve accuracy on a given target distribution, they often reduce robustness to distribution shifts. We address this tension by introducing a simple and effective method for improving robustness while fine-tuning: ensembling the weights of the zero-shot and fine-tuned models (WiSE-FT). Compared to standard fine-tuning, WiSE-FT provides large accura…
CNNs have made an undeniable impact on computer vision through the ability to learn high-capacity models with large annotated training sets. One of their remarkable properties is the ability to transfer knowledge from a large source dataset to a (typically smaller) target dataset. This is usually accomplished through fine-tuning a fixed-size network on new target data. Indeed, virtually every contemporary visual recognition system makes use of fine-tuning to transfer knowledge from ImageNet. In this work, we analyze what components and parameters change during fine-tuning, and discover that in…
SenseTime Research（商汤科技研究院）；Shanghai AI Lab（上海人工智能实验室）；University of New South Wales（新南威尔士大学）；The Australian National University（澳大利亚国立大学）；Curtin University（科廷大学）
Fine-tuning is widely applied in image classification tasks as a transfer learning approach. It re-uses the knowledge from a source task to learn and obtain a high performance in target tasks. Fine-tuning is able to alleviate the challenge of insufficient training data and expensive labelling of new data. However, standard fine-tuning has limited performance in complex data distributions. To address this issue, we propose the Adaptable Multi-tuning method, which adaptively determines each data sample's fine-tuning strategy. In this framework, multiple fine-tuning settings and one policy networ…
Nanjing University of Science and Technology（南京理工大学）；Baidu（百度）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Freezing the pre-trained backbone has become a standard paradigm to avoid overfitting in few-shot segmentation. In this paper, we rethink the paradigm and explore a new regime: {\em fine-tuning a small part of parameters in the backbone}. We present a solution to overcome the overfitting problem, leading to better model generalization on learning novel classes. Our method decomposes backbone parameters into three successive matrices via the Singular Value Decomposition (SVD), then {\em only fine-tunes the singular values} and keeps others frozen. The above design allows the model to adjust fea…
Convolutional neural networks require numerous data for training. Considering the difficulties in data collection and labeling in some specific tasks, existing approaches generally use models pre-trained on a large source domain (e.g. ImageNet), and then fine-tune them on these tasks. However, the datasets from source domain are simply discarded in the fine-tuning process. We argue that the source datasets could be better utilized and benefit fine-tuning. This paper firstly introduces the concept of general discrimination to describe ability of a network to distinguish untrained patterns, and …
