相关论文: Smoothness Similarity Regularization for Few-Shot …

Transfer learning based approaches have recently achieved promising results on the few-shot detection task. These approaches however suffer from ``catastrophic forgetting'' issue due to finetuning of base detector, leading to sub-optimal…

Vision-language foundation models have been incredibly successful in a wide range of downstream computer vision tasks using adaptation methods. However, due to the high cost of obtaining pre-training datasets, pairs with weak image-text…

Adapting a model to perform well on unforeseen data outside its training set is a common problem that continues to motivate new approaches. We demonstrate that application of batch normalization in the output layer, prior to softmax…

Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are…

We propose a smooth regularization technique that instills a strong temporal inductive bias in video recognition models, particularly benefiting lightweight architectures. Our method encourages smoothness in the intermediate-layer…

Current state of the art methods in Domain Adaptation follow adversarial approaches, making training a challenge. Existing non-adversarial methods learn mappings between the source and target domains, to achieve reasonable performance.…

Most of the existing deep neural nets on automatic facial expression recognition focus on a set of predefined emotion classes, where the amount of training data has the biggest impact on performance. However, in the standard setting…

Producing agents that can generalize to a wide range of visually different environments is a significant challenge in reinforcement learning. One method for overcoming this issue is visual domain randomization, whereby at the start of each…

Unsupervised domain adaptation aims to transfer and adapt knowledge learned from a labeled source domain to an unlabeled target domain. Key components of unsupervised domain adaptation include: (a) maximizing performance on the target, and…

Domain Adaptation is an actively researched problem in Computer Vision. In this work, we propose an approach that leverages unsupervised data to bring the source and target distributions closer in a learned joint feature space. We…

It has been known for a while that the problem of multi-source domain adaptation can be regarded as a single source domain adaptation task where the source domain corresponds to a mixture of the original source domains. Nonetheless, how to…

Sharpness-Aware Minimization (SAM) has proven highly effective in improving model generalization in machine learning tasks. However, SAM employs a fixed hyperparameter associated with the regularization to characterize the sharpness of the…

Unsupervised Graph Domain Adaptation (UGDA) seeks to bridge distribution shifts between domains by transferring knowledge from labeled source graphs to given unlabeled target graphs. Existing UGDA methods primarily focus on aligning…

We study few-shot learning in natural language domains. Compared to many existing works that apply either metric-based or optimization-based meta-learning to image domain with low inter-task variance, we consider a more realistic setting,…

Unsupervised domain adaptation seeks to mitigate the distribution discrepancy between source and target domains, given labeled samples of the source domain and unlabeled samples of the target domain. Generative adversarial networks (GANs)…

Human beings can quickly adapt to environmental changes by leveraging learning experience. However, the poor ability of adapting to dynamic environments remains a major challenge for AI models. To better understand this issue, we study the…

Generative Adversarial Networks (GANs) based semi-supervised learning (SSL) approaches are shown to improve classification performance by utilizing a large number of unlabeled samples in conjunction with limited labeled samples. However,…

Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available…

We develop a novel approach to conformal prediction when the target task has limited data available for training. Conformal prediction identifies a small set of promising output candidates in place of a single prediction, with guarantees…

Batch Normalization (BN) is an important preprocessing step to many deep learning applications. Since it is a data-dependent process, for some homogeneous datasets it is a redundant or even a performance-degrading process. In this paper, we…