In this paper, we propose a feature transformation ensemble model with batch spectral regularization for the Cross-domain few-shot learning (CD-FSL) challenge. Specifically, we proposes to construct an ensemble prediction model by performing diverse feature transformations after a feature extraction network. On each branch prediction network of the model we use a batch spectral regularization term to suppress the singular values of the feature matrix during pre-training to improve the generalization ability of the model. The proposed model can then be fine tuned in the target domain to address few-shot classification. We also further apply label propagation, entropy minimization and data augmentation to mitigate the shortage of labeled data in target domains. Experiments are conducted on a number of CD-FSL benchmark tasks with four target domains and the results demonstrate the superiority of our proposed model.
In this paper, we present our proposed ensemble model with batch spectral regularization and data blending mechanisms for the Track 2 problem of the cross-domain few-shot learning (CD-FSL) challenge. We build a multi-branch ensemble framework by using diverse feature transformation matrices, while deploying batch spectral feature regularization on each branch to improve the model's transferability. Moreover, we propose a data blending method to exploit the unlabeled data and augment the sparse support set in the target domain. Our proposed model demonstrates effective performance on the CD-FSL…
L2 regularization for weights in neural networks is widely used as a standard training trick. However, L2 regularization for gamma, a trainable parameter of batch normalization, remains an undiscussed mystery and is applied in different ways depending on the library and practitioner. In this paper, we study whether L2 regularization for gamma is valid. To explore this issue, we consider two approaches: 1) variance control to make the residual network behave like identity mapping and 2) stable optimization through the improvement of effective learning rate. Through two analyses, we specify the …
OPPO Research Institute（OPPO研究院）；Shanghai Jiao Tong University（上海交通大学）
Knowledge distillation (KD) shows a bright promise as a powerful regularization strategy to boost generalization ability by leveraging learned sample-level soft targets. Yet, employing a complex pre-trained teacher network or an ensemble of peer students in existing KD is both time-consuming and computationally costly. Various self KD methods have been proposed to achieve higher distillation efficiency. However, they either require extra network architecture modification or are difficult to parallelize. To cope with these challenges, we propose an efficient and reliable self-distillation frame…
Chung-Ang University（中央大学）；University of California Los Angeles（加州大学洛杉矶分校）
We propose a first-order stochastic optimization algorithm incorporating adaptive regularization applicable to machine learning problems in deep learning framework. The adaptive regularization is imposed by stochastic process in determining batch size for each model parameter at each optimization iteration. The stochastic batch size is determined by the update probability of each parameter following a distribution of gradient norms in consideration of their local and global properties in the neural network architecture where the range of gradient norms may vary within and across layers. We emp…
The purpose of generative Zero-shot learning (ZSL) is to learning from seen classes, transfer the learned knowledge, and create samples of unseen classes from the description of these unseen categories. To achieve better ZSL accuracies, models need to better understand the descriptions of unseen classes. We introduce a novel form of regularization that encourages generative ZSL models to pay more attention to the description of each category. Our empirical results demonstrate improvements over the performance of multiple state-of-the-art models on the task of generalized zero-shot recognition …
Incremental few-shot learning has emerged as a new and challenging area in deep learning, whose objective is to train deep learning models using very few samples of new class data, and none of the old class data. In this work we tackle the problem of batch incremental few-shot road object detection using data from the India Driving Dataset (IDD). Our approach, DualFusion, combines object detectors in a manner that allows us to learn to detect rare objects with very limited data, all without severely degrading the performance of the detector on the abundant classes. In the IDD OpenSet increment…
This work focuses on learning deep visual representation models for retrieval by exploring the interplay between a new loss function, the batch size, and a new regularization approach. Direct optimization, by gradient descent, of an evaluation metric, is not possible when it is non-differentiable, which is the case for recall in retrieval. A differentiable surrogate loss for the recall is proposed in this work. Using an implementation that sidesteps the hardware constraints of the GPU memory, the method trains with a very large batch size, which is essential for metrics computed on the entire …
University of Waterloo（滑铁卢大学）；Vector Institute（向量研究所）
The variational autoencoder is a well defined deep generative model that utilizes an encoder-decoder framework where an encoding neural network outputs a non-deterministic code for reconstructing an input. The encoder achieves this by sampling from a distribution for every input, instead of outputting a deterministic code per input. The great advantage of this process is that it allows the use of the network as a generative model for sampling from the data distribution beyond provided samples for training. We show in this work that utilizing batch normalization as a source for non-determinism …
Few-shot NeRF by Adaptive Rendering Loss Regularization
Nanyang Technological University（南洋理工大学）；Huazhong University of Science and Technology（华中科技大学）；Centre for Frontier AI Research（前沿人工智能研究中心）；A*STAR（新加坡科技研究局）
Although zero-shot learning (ZSL) has an inferential capability of recognizing new classes that have never been seen before, it always faces two fundamental challenges of the cross modality and crossdomain challenges. In order to alleviate these problems, we develop a generative network-based ZSL approach equipped with the proposed Cross Knowledge Learning (CKL) scheme and Taxonomy Regularization (TR). In our approach, the semantic features are taken as inputs, and the output is the synthesized visual features generated from the corresponding semantic features. CKL enables more relevant semant…
Smoothness Similarity Regularization for Few-Shot GAN Adaptation
Bosch Center for Artificial Intelligence（博世人工智能中心）；University of Bonn（波恩大学）；Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习与人工智能研究所）
Boosting Few-Shot Learning via Attentive Feature Regularization
University of Science and Technology of China（中国科学技术大学）；MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China（中国科学技术大学类脑智能技术与应用国家工程实验室）；Brain-Inspired Technology Co., Ltd.（类脑智能科技有限公司）
Duke University（杜克大学）；University of California, Los Angeles（加州大学洛杉矶分校）
Deep neural networks (DNNs) typically have enough capacity to fit random data by brute force even when conventional data-dependent regularizations focusing on the geometry of the features are imposed. We find out that the reason for this is the inconsistency between the enforced geometry and the standard softmax cross entropy loss. To resolve this, we propose a new framework for data-dependent DNN regularization, the Geometrically-Regularized-Self-Validating neural Networks (GRSVNet). During training, the geometry enforced on one batch of features is simultaneously validated on a separate batc…
Peking University（北京大学）；Deepwise Inc.（深度智视公司）；Fudan University（复旦大学）；AITrics Inc.（AITrics公司）；Hong Kong University of Science and Technology（香港科技大学）
It is one typical and general topic of learning a good embedding model to efficiently learn the representation coefficients between two spaces/subspaces. To solve this task, $L_{1}$ regularization is widely used for the pursuit of feature selection and avoiding overfitting, and yet the sparse estimation of features in $L_{1}$ regularization may cause the underfitting of training data. $L_{2}$ regularization is also frequently used, but it is a biased estimator. In this paper, we propose the idea that the features consist of three orthogonal parts, \emph{namely} sparse strong signals, dense wea…
RegBN: Batch Normalization of Multimodal Data with Regularization
Technical University of Munich (TUM)（慕尼黑工业大学（TUM））；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Lab for AI in Medical Imaging (AI-Med)（医学影像人工智能实验室）
Indian Institute of Technology, Ropar（印度理工学院罗巴尔分校）
Meta-learning (ML) has emerged as a promising direction in learning models under constrained resource settings like few-shot learning. The popular approaches for ML either learn a generalizable initial model or a generic parametric optimizer through episodic training. The former approaches leverage the knowledge from a batch of tasks to learn an optimal prior. In this work, we study the importance of a batch for ML. Specifically, we first incorporate a batch episodic training regimen to improve the learning of the generic parametric optimizer. We also hypothesize that the common assumption in …
Institute for Infocomm Research (I2R), the Agency for Science, Technology and Research (A*STAR)（资讯通信研究院（I2R），新加坡科技研究局（A*STAR））；Zhejiang University（浙江大学）
In industrial product quality assessment, it is essential to determine whether a product is defect-free and further analyze the severity of anomality. To this end, accurate defect segmentation on images of products provides an important functionality. In industrial inspection tasks, it is common to capture abundant defect-free image samples but very limited anomalous ones. Therefore, it is critical to develop automatic and accurate defect segmentation systems using only a small number of annotated anomalous training images. This paper tackles the challenging few-shot defect segmentation task w…
UC, Los Angeles（加州大学洛杉矶分校）；Nvidia Research（英伟达研究院）；Stanford University（斯坦福大学）
Novel view synthesis with sparse inputs is a challenging problem for neural radiance fields (NeRF). Recent efforts alleviate this challenge by introducing external supervision, such as pre-trained models and extra depth signals, and by non-trivial patch-based rendering. In this paper, we present Frequency regularized NeRF (FreeNeRF), a surprisingly simple baseline that outperforms previous methods with minimal modifications to the plain NeRF. We analyze the key challenges in few-shot neural rendering and find that frequency plays an important role in NeRF's training. Based on the analysis, we …
Batch normalization (BN) has become a de facto standard for training deep convolutional networks. However, BN accounts for a significant fraction of training run-time and is difficult to accelerate, since it is a memory-bandwidth bounded operation. Such a drawback of BN motivates us to explore recently proposed weight normalization algorithms (WN algorithms), i.e. weight normalization, normalization propagation and weight normalization with translated ReLU. These algorithms don't slow-down training iterations and were experimentally shown to outperform BN on relatively small networks and datas…
Alibaba Group（阿里巴巴集团）；Zhejiang University（浙江大学）；University of Bath（巴斯大学）
Few-shot image classification requires the classifier to robustly cope with unseen classes even if there are only a few samples for each class. Recent advances benefit from the meta-learning process where episodic tasks are formed to train a model that can adapt to class change. However, these task sare independent to each other and existing works mainly rely on limited samples of individual support set in a single meta task. This strategy leads to severe meta shift issues across multiple tasks, meaning the learned prototypes or class descriptors are not stable as each task only involves their…
National University of Singapore（新加坡国立大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Tianjin University（天津大学）
Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which only a few labeled samples are available. As deep neural networks (DNNs) tend to overfit using a few samples only, meta-learning typically uses shallow neural networks (SNNs), thus limiting its effectiveness. In this paper we propose a novel few-shot learning method called meta-transfer learning (MTL) which learns to adapt a deep NN for few shot learning tas…
In few-shot classification, the primary goal is to learn representations from a few samples that generalize well for novel classes. In this paper, we propose an efficient low displacement rank (LDR) regularization strategy termed Ortho-Shot; a technique that imposes orthogonal regularization on the convolutional layers of a few-shot classifier, which is based on the doubly-block toeplitz (DBT) matrix structure. The regularized convolutional layers of the few-shot classifier enhances model generalization and intra-class feature embeddings that are crucial for few-shot learning. Overfitting is a…
A key component of most neural network architectures is the use of normalization layers, such as Batch Normalization. Despite its common use and large utility in optimizing deep architectures, it has been challenging both to generically improve upon Batch Normalization and to understand the circumstances that lend themselves to other enhancements. In this paper, we identify four improvements to the generic form of Batch Normalization and the circumstances under which they work, yielding performance gains across all batch sizes while requiring no additional computation during training. These co…
Robust Model-Agnostic Meta-Learning (MAML) is usually adopted to train a meta-model which may fast adapt to novel classes with only a few exemplars and meanwhile remain robust to adversarial attacks. The conventional solution for robust MAML is to introduce robustness-promoting regularization during meta-training stage. With such a regularization, previous robust MAML methods simply follow the typical MAML practice that the number of training shots should match with the number of test shots to achieve an optimal adaptation performance. However, although the robustness can be largely improved, …
Stanford University（斯坦福大学）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Google Research（谷歌研究院）
In many domains, relationships between categories are encoded in the knowledge graph. Recently, promising results have been achieved by incorporating knowledge graph as side information in hard classification tasks with severely limited data. However, prior models consist of highly complex architectures with many sub-components that all seem to impact performance. In this paper, we present a comprehensive empirical study on graph embedded few-shot learning. We introduce a graph regularization approach that allows a deeper understanding of the impact of incorporating graph information between l…
On the Limits of Multi-modal Meta-Learning with Auxiliary Task Modulation Using Conditional Batch Normalization
University of Edinburgh（爱丁堡大学）；Université de Montréal（蒙特利尔大学）；Google Research（谷歌研究院）；Mila（米拉计算科学研究所）；McGill University（麦吉尔大学）；University of Calgary（卡尔加里大学）；CIFAR（加拿大高级研究所）
Center of AI, University of Technology Sydney（悉尼科技大学人工智能中心）
This paper focuses on regularizing the training of the convolutional neural network (CNN). We propose a new regularization approach named ``PatchShuffle`` that can be adopted in any classification-oriented CNN models. It is easy to implement: in each mini-batch, images or feature maps are randomly chosen to undergo a transformation such that pixels within each local patch are shuffled. Through generating images and feature maps with interior orderless patches, PatchShuffle creates rich local variations, reduces the risk of network overfitting, and can be viewed as a beneficial supplement to va…
The generalization power of the pre-trained model is the key for few-shot deep learning. Dropout is a regularization technique used in traditional deep learning methods. In this paper, we explore the power of dropout on few-shot learning and provide some insights about how to use it. Extensive experiments on the few-shot object detection and few-shot image classification datasets, i.e., Pascal VOC, MS COCO, CUB, and mini-ImageNet, validate the effectiveness of our method.
South China University of Technology（华南理工大学）；Pazhou Lab（琶洲实验室）；JD Explore Academy at JD.com（京东探索研究院）
Existing part-aware person re-identification methods typically employ two separate steps: namely, body part detection and part-level feature extraction. However, part detection introduces an additional computational cost and is inherently challenging for low-quality images. Accordingly, in this work, we propose a simple framework named Batch Coherence-Driven Network (BCD-Net) that bypasses body part detection during both the training and testing phases while still learning semantically aligned part features. Our key observation is that the statistics in a batch of images are stable, and theref…
Few-shot class incremental learning -- the problem of updating a trained classifier to discriminate among an expanded set of classes with limited labeled data -- is a key challenge for machine learning systems deployed in non-stationary environments. Existing approaches to the problem rely on complex model architectures and training procedures that are difficult to tune and re-use. In this paper, we present an extremely simple approach that enables the use of ordinary logistic regression classifiers for few-shot incremental learning. The key to this approach is a new family of subspace regular…
Universitas Indonesia（印度尼西亚大学）；Agency for the Assessment and Application of Technology (BPPT)（印度尼西亚技术与应用评估局（BPPT））
This study uses remote sensing technology that can provide information about the condition of the earth's surface area, fast, and spatially. The study area was in Karawang District, lying in the Northern part of West Java-Indonesia. We address a paddy growth stages classification using LANDSAT 8 image data obtained from multi-sensor remote sensing image taken in October 2015 to August 2016. This study pursues a fast and accurate classification of paddy growth stages by employing multiple regularizations learning on some deep learning methods such as DNN (Deep Neural Networks) and 1-D CNN (1-D …
Tsinghua University（清华大学）；Yanqi Lake Beijing Institute of Mathematical Sciences and Applications（雁栖湖北京数学科学与应用研究院）
The non-line-of-sight imaging technique aims to reconstruct targets from multiply reflected light. For most existing methods, dense points on the relay surface are raster scanned to obtain high-quality reconstructions, which requires a long acquisition time. In this work, we propose a signal-surface collaborative regularization (SSCR) framework that provides noise-robust reconstructions with a minimal number of measurements. Using Bayesian inference, we design joint regularizations of the estimated signal, the 3D voxel-based representation of the objects, and the 2D surface-based description o…
OSRAM GmbH（欧司朗有限公司）；Sapienza University of Rome（罗马智慧大学）
Contrastive losses yield state-of-the-art performance for person re-identification, face verification and few shot learning. They have recently outperformed the cross-entropy loss on classification at the ImageNet scale and outperformed all self-supervision prior results by a large margin (SimCLR). Simple and effective regularization techniques such as label smoothing and self-distillation do not apply anymore, because they act on multinomial label distributions, adopted in cross-entropy losses, and not on tuple comparative terms, which characterize the contrastive losses. Here we propose a no…
Few-shot Class-Incremental Learning via Generative Co-Memory Regularization
Institute of Information Engineering（信息工程研究所）；Chinese Academy of Sciences（中国科学院）；School of Cyber Security（网络安全学院）；University of Chinese Academy of Sciences（中国科学院大学）；Department of Communication Engineering（通信工程系）
The role of semantics in zero-shot learning is considered. The effectiveness of previous approaches is analyzed according to the form of supervision provided. While some learn semantics independently, others only supervise the semantic subspace explained by training classes. Thus, the former is able to constrain the whole space but lacks the ability to model semantic correlations. The latter addresses this issue but leaves part of the semantic space unsupervised. This complementarity is exploited in a new convolutional neural network (CNN) framework, which proposes the use of semantics as cons…
Few-shot object detection (FSOD), with the aim to detect novel objects using very few training examples, has recently attracted great research interest in the community. Metric-learning based methods have been demonstrated to be effective for this task using a two-branch based siamese network, and calculate the similarity between image regions and few-shot examples for detection. However, in previous works, the interaction between the two branches is only restricted in the detection head, while leaving the remaining hundreds of layers for separate feature extraction. Inspired by the recent wor…
Institute for Infocomm Research, A*STAR（新加坡科技研究局信息通信研究所）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Centre for Frontier AI Research, A*STAR（新加坡科技研究局前沿人工智能研究中心）
Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data. Recent test-time adaptation methods update batch normalization layers of pre-trained source models deployed in new target environments with streaming data to mitigate such performance degradation. Although such methods can adapt on-the-fly without first collecting a large target domain dataset, their performance is dependent on streaming conditions such as mini-batch size and class-distribution, which can be unpredictable in practice. In this work, we propo…
Few-shot learning algorithms aim to learn model parameters capable of adapting to unseen classes with the help of only a few labeled examples. A recent regularization technique - Manifold Mixup focuses on learning a general-purpose representation, robust to small changes in the data distribution. Since the goal of few-shot learning is closely linked to robust representation learning, we study Manifold Mixup in this problem setting. Self-supervised learning is another technique that learns semantically meaningful features, using only the inherent structure of the data. This work investigates th…
