PyTorchKR Papers

최신 논문

총 4,526편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2103.10000공식 코드 · Papers with Code

Human-Inspired Multi-Agent Navigation using Knowledge Distillation

Despite significant advancements in the field of multi-agent navigation, agents still lack the sophistication and intelligence that humans exhibit in multi-agent settings. In this paper, we propose a framework for learning a human-like general collision avoidance policy for agent-agent interactions in fully decentralized, multi-agent environments. Our approach uses knowledge distillation with reinforcement learning to shape the reward function based on expert policies extracted from human trajectory demonstrations through behavior cloning. We show that agents trained with our approach can take human-like trajectories in collision avoidance and goal-directed steering tasks not provided by the demonstrations, outperforming the experts as well as learning-based agents trained without knowledge distillation.

arXiv:2103.08809

Robustly Optimized and Distilled Training for Natural Language Understanding

In this paper, we explore multi-task learning (MTL) as a second pretraining step to learn enhanced universal language representation for transformer language models. We use the MTL enhanced representation across several natural language understanding tasks to improve performance and generalization. Moreover, we incorporate knowledge distillation (KD) in MTL to further boost performance and devise a KD variant that learns effectively from multiple teachers. By combining MTL and KD, we propose Robustly Optimized and Distilled (ROaD) modeling framework. We use ROaD together with the ELECTRA model to obtain state-of-the-art results for machine reading comprehension and natural language inference.

arXiv:2103.09154

Leveraging Recent Advances in Deep Learning for Audio-Visual Emotion Recognition

Emotional expressions are the behaviors that communicate our emotional state or attitude to others. They are expressed through verbal and non-verbal communication. Complex human behavior can be understood by studying physical features from multiple modalities; mainly facial, vocal and physical gestures. Recently, spontaneous multi-modal emotion recognition has been extensively studied for human behavior analysis. In this paper, we propose a new deep learning-based approach for audio-visual emotion recognition. Our approach leverages recent advances in deep learning like knowledge distillation and high-performing deep architectures. The deep feature representations of the audio and visual modalities are fused based on a model-level fusion strategy. A recurrent neural network is then used to capture the temporal dynamics. Our proposed approach substantially outperforms state-of-the-art approaches in predicting valence on the RECOLA dataset. Moreover, our proposed visual facial expression feature extraction network outperforms state-of-the-art results on the AffectNet and Google Facial Expression Comparison datasets.

arXiv:2103.08273공식 코드 · Papers with Code

Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation

Knowledge distillation is a method of transferring the knowledge from a pretrained complex teacher model to a student model, so a smaller network can replace a large teacher network at the deployment stage. To reduce the necessity of training a large teacher model, the recent literatures introduced a self-knowledge distillation, which trains a student network progressively to distill its own knowledge without a pretrained teacher network. While Self-knowledge distillation is largely divided into a data augmentation based approach and an auxiliary network based approach, the data augmentation approach looses its local information in the augmentation process, which hinders its applicability to diverse vision tasks, such as semantic segmentation. Moreover, these knowledge distillation approaches do not receive the refined feature maps, which are prevalent in the object detection and semantic segmentation community. This paper proposes a novel self-knowledge distillation method, Feature Refinement via Self-Knowledge Distillation (FRSKD), which utilizes an auxiliary self-teacher network to transfer a refined knowledge for the classifier network. Our proposed method, FRSKD, can utilize both soft label and feature-map distillations for the self-knowledge distillation. Therefore, FRSKD can be applied to classification, and semantic segmentation, which emphasize preserving the local information. We demonstrate the effectiveness of FRSKD by enumerating its performance improvements in diverse tasks and benchmark datasets. The implemented code is available at https://github.com/MingiJi/FRSKD.

arXiv:2103.07668공식 코드 · Papers with Code

Robust Model Compression Using Deep Hypotheses

Machine Learning models should ideally be compact and robust. Compactness provides efficiency and comprehensibility whereas robustness provides resilience. Both topics have been studied in recent years but in isolation. Here we present a robust model compression scheme which is independent of model types: it can compress ensembles, neural networks and other types of models into diverse types of small models. The main building block is the notion of depth derived from robust statistics. Originally, depth was introduced as a measure of the centrality of a point in a sample such that the median is the deepest point. This concept was extended to classification functions which makes it possible to define the depth of a hypothesis and the median hypothesis. Algorithms have been suggested to approximate the median but they have been limited to binary classification. In this study, we present a new algorithm, the Multiclass Empirical Median Optimization (MEMO) algorithm that finds a deep hypothesis in multi-class tasks, and prove its correctness. This leads to our Compact Robust Estimated Median Belief Optimization (CREMBO) algorithm for robust model compression. We demonstrate the success of this algorithm empirically by compressing neural networks and random forests into small decision trees, which are interpretable models, and show that they are more accurate and robust than other comparable methods. In addition, our empirical study shows that our method outperforms Knowledge Distillation on DNN to DNN compression.

arXiv:2103.07350

A New Training Framework for Deep Neural Network

Knowledge distillation is the process of transferring the knowledge from a large model to a small model. In this process, the small model learns the generalization ability of the large model and retains the performance close to that of the large model. Knowledge distillation provides a training means to migrate the knowledge of models, facilitating model deployment and speeding up inference. However, previous distillation methods require pre-trained teacher models, which still bring computational and storage overheads. In this paper, a novel general training framework called Self Distillation (SD) is proposed. We demonstrate the effectiveness of our method by enumerating its performance improvements in diverse tasks and benchmark datasets.

arXiv:2103.05959공식 코드 · Papers with Code

Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones

Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the community and are proven to be of great potential in obtaining a powerful pre-trained model. However, these models require huge training costs (i.e., hundreds of millions of images or training iterations). In this paper, we propose to improve existing baseline networks via knowledge distillation from off-the-shelf pre-trained big powerful models. Different from existing knowledge distillation frameworks which require student model to be consistent with both soft-label generated by teacher model and hard-label annotated by humans, our solution performs distillation by only driving prediction of the student model consistent with that of the teacher model. Therefore, our distillation setting can get rid of manually labeled data and can be trained with extra unlabeled data to fully exploit capability of teacher model for better learning. We empirically find that such simple distillation settings perform extremely effective, for example, the top-1 accuracy on ImageNet-1k validation set of MobileNetV3-large and ResNet50-D can be significantly improved from 75.2% to 79% and 79.1% to 83%, respectively. We have also thoroughly analyzed what are dominant factors that affect the distillation performance and how they make a difference. Extensive downstream computer vision tasks, including transfer learning, object detection and semantic segmentation, can significantly benefit from the distilled pretrained models. All our experiments are implemented based on PaddlePaddle, codes and a series of improved pretrained models with ssld suffix are available in PaddleClas.

arXiv:2103.04062공식 코드 · Papers with Code

Adaptive Multi-Teacher Multi-level Knowledge Distillation

Knowledge distillation~(KD) is an effective learning paradigm for improving the performance of lightweight student networks by utilizing additional supervision knowledge distilled from teacher networks. Most pioneering studies either learn from only a single teacher in their distillation learning methods, neglecting the potential that a student can learn from multiple teachers simultaneously, or simply treat each teacher to be equally important, unable to reveal the different importance of teachers for specific examples. To bridge this gap, we propose a novel adaptive multi-teacher multi-level knowledge distillation learning framework~(AMTML-KD), which consists two novel insights: (i) associating each teacher with a latent representation to adaptively learn instance-level teacher importance weights which are leveraged for acquiring integrated soft-targets~(high-level knowledge) and (ii) enabling the intermediate-level hints~(intermediate-level knowledge) to be gathered from multiple teachers by the proposed multi-group hint strategy. As such, a student model can learn multi-level knowledge from multiple teachers through AMTML-KD. Extensive results on publicly available datasets demonstrate the proposed learning framework ensures student to achieve improved performance than strong competitors.

arXiv:2103.04059

Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning

Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner. Due to the limited number of examples for training, the techniques developed for standard incremental learning cannot be applied verbatim to FSCIL. In this work, we introduce a distillation algorithm to address the problem of FSCIL and propose to make use of semantic information during training. To this end, we make use of word embeddings as semantic information which is cheap to obtain and which facilitate the distillation process. Furthermore, we propose a method based on an attention mechanism on multiple parallel embeddings of visual data to align visual and semantic vectors, which reduces issues related to catastrophic forgetting. Via experiments on MiniImageNet, CUB200, and CIFAR100 dataset, we establish new state-of-the-art results by outperforming existing approaches.

arXiv:2103.04559공식 코드 · Papers with Code

Parser-Free Virtual Try-on via Distilling Appearance Flows

Image virtual try-on aims to fit a garment image (target clothes) to a person image. Prior methods are heavily based on human parsing. However, slightly-wrong segmentation results would lead to unrealistic try-on images with large artifacts. Inaccurate parsing misleads parser-based methods to produce visually unrealistic results where artifacts usually occur. A recent pioneering work employed knowledge distillation to reduce the dependency of human parsing, where the try-on images produced by a parser-based method are used as supervisions to train a "student" network without relying on segmentation, making the student mimic the try-on ability of the parser-based model. However, the image quality of the student is bounded by the parser-based model. To address this problem, we propose a novel approach, "teacher-tutor-student" knowledge distillation, which is able to produce highly photo-realistic images without human parsing, possessing several appealing advantages compared to prior arts. (1) Unlike existing work, our approach treats the fake images produced by the parser-based method as "tutor knowledge", where the artifacts can be corrected by real "teacher knowledge", which is extracted from the real person images in a self-supervised way. (2) Other than using real images as supervisions, we formulate knowledge distillation in the try-on problem as distilling the appearance flows between the person image and the garment image, enabling us to find accurate dense correspondences between them to produce high-quality results. (3) Extensive evaluations show large superiority of our method (see Fig. 1).

arXiv:2103.03467공식 코드 · Papers with Code

Teachers Do More Than Teach: Compressing Image-to-Image Models

Generative Adversarial Networks (GANs) have achieved huge success in generating high-fidelity images, however, they suffer from low efficiency due to tremendous computational cost and bulky memory usage. Recent efforts on compression GANs show noticeable progress in obtaining smaller generators by sacrificing image quality or involving a time-consuming searching process. In this work, we aim to address these issues by introducing a teacher network that provides a search space in which efficient network architectures can be found, in addition to performing knowledge distillation. First, we revisit the search space of generative models, introducing an inception-based residual block into generators. Second, to achieve target computation cost, we propose a one-step pruning algorithm that searches a student architecture from the teacher model and substantially reduces searching cost. It requires no l1 sparsity regularization and its associated hyper-parameters, simplifying the training procedure. Finally, we propose to distill knowledge through maximizing feature similarity between teacher and student via an index named Global Kernel Alignment (GKA). Our compressed networks achieve similar or even better image fidelity (FID, mIoU) than the original models with much-reduced computational cost, e.g., MACs. Code will be released at https://github.com/snap-research/CAT.

arXiv:2103.03786공식 코드 · Papers with Code

Distributed Dynamic Map Fusion via Federated Learning for Intelligent Networked Vehicles

The technology of dynamic map fusion among networked vehicles has been developed to enlarge sensing ranges and improve sensing accuracies for individual vehicles. This paper proposes a federated learning (FL) based dynamic map fusion framework to achieve high map quality despite unknown numbers of objects in fields of view (FoVs), various sensing and model uncertainties, and missing data labels for online learning. The novelty of this work is threefold: (1) developing a three-stage fusion scheme to predict the number of objects effectively and to fuse multiple local maps with fidelity scores; (2) developing an FL algorithm which fine-tunes feature models (i.e., representation learning networks for feature extraction) distributively by aggregating model parameters; (3) developing a knowledge distillation method to generate FL training labels when data labels are unavailable. The proposed framework is implemented in the Car Learning to Act (CARLA) simulation platform. Extensive experimental results are provided to verify the superior performance and robustness of the developed map fusion and FL schemes.

arXiv:2103.02885공식 코드 · Papers with Code

Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework

Semi-supervised learning on graphs is an important problem in the machine learning area. In recent years, state-of-the-art classification methods based on graph neural networks (GNNs) have shown their superiority over traditional ones such as label propagation. However, the sophisticated architectures of these neural models will lead to a complex prediction mechanism, which could not make full use of valuable prior knowledge lying in the data, e.g., structurally correlated nodes tend to have the same class. In this paper, we propose a framework based on knowledge distillation to address the above issues. Our framework extracts the knowledge of an arbitrary learned GNN model (teacher model), and injects it into a well-designed student model. The student model is built with two simple prediction mechanisms, i.e., label propagation and feature transformation, which naturally preserves structure-based and feature-based prior knowledge, respectively. In specific, we design the student model as a trainable combination of parameterized label propagation and feature transformation modules. As a result, the learned student can benefit from both prior knowledge and the knowledge in GNN teachers for more effective predictions. Moreover, the learned student model has a more interpretable prediction process than GNNs. We conduct experiments on five public benchmark datasets and employ seven GNN models including GCN, GAT, APPNP, SAGE, SGC, GCNII and GLP as the teacher models. Experimental results show that the learned student model can consistently outperform its corresponding teacher model by 1.4% - 4.7% on average. Code and data are available at https://github.com/BUPT-GAMMA/CPF

arXiv:2103.02340공식 코드 · Papers with Code

General Instance Distillation for Object Detection

In recent years, knowledge distillation has been proved to be an effective solution for model compression. This approach can make lightweight student models acquire the knowledge extracted from cumbersome teacher models. However, previous distillation methods of detection have weak generalization for different detection frameworks and rely heavily on ground truth (GT), ignoring the valuable relation information between instances. Thus, we propose a novel distillation method for detection tasks based on discriminative instances without considering the positive or negative distinguished by GT, which is called general instance distillation (GID). Our approach contains a general instance selection module (GISM) to make full use of feature-based, relation-based and response-based knowledge for distillation. Extensive results demonstrate that the student model achieves significant AP improvement and even outperforms the teacher in various detection frameworks. Specifically, RetinaNet with ResNet-50 achieves 39.1% in mAP with GID on COCO dataset, which surpasses the baseline 36.2% by 2.9%, and even better than the ResNet-101 based teacher model with 38.1% AP.

arXiv:2103.01315공식 코드 · Papers with Code

Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning

In many real-world problems, collecting a large number of labeled samples is infeasible. Few-shot learning (FSL) is the dominant approach to address this issue, where the objective is to quickly adapt to novel categories in presence of a limited number of samples. FSL tasks have been predominantly solved by leveraging the ideas from gradient-based meta-learning and metric learning approaches. However, recent works have demonstrated the significance of powerful feature representations with a simple embedding network that can outperform existing sophisticated FSL algorithms. In this work, we build on this insight and propose a novel training mechanism that simultaneously enforces equivariance and invariance to a general set of geometric transformations. Equivariance or invariance has been employed standalone in the previous works; however, to the best of our knowledge, they have not been used jointly. Simultaneous optimization for both of these contrasting objectives allows the model to jointly learn features that are not only independent of the input transformation but also the features that encode the structure of geometric transformations. These complementary sets of features help generalize well to novel classes with only a few data samples. We achieve additional improvements by incorporating a novel self-supervised distillation objective. Our extensive experimentation shows that even without knowledge distillation our proposed method can outperform current state-of-the-art FSL methods on five popular benchmark datasets.

arXiv:2103.01524

Feature-Align Network with Knowledge Distillation for Efficient Denoising

We propose an efficient neural network for RAW image denoising. Although neural network-based denoising has been extensively studied for image restoration, little attention has been given to efficient denoising for compute limited and power sensitive devices, such as smartphones and smartwatches. In this paper, we present a novel architecture and a suite of training techniques for high quality denoising in mobile devices. Our work is distinguished by three main contributions. (1) Feature-Align layer that modulates the activations of an encoder-decoder architecture with the input noisy images. The auto modulation layer enforces attention to spatially varying noise that tend to be "washed away" by successive application of convolutions and non-linearity. (2) A novel Feature Matching Loss that allows knowledge distillation from large denoising networks in the form of a perceptual content loss. (3) Empirical analysis of our efficient model trained to specialize on different noise subranges. This opens additional avenue for model size reduction by sacrificing memory for compute. Extensive experimental validation shows that our efficient model produces high quality denoising results that compete with state-of-the-art large networks, while using significantly fewer parameters and MACs. On the Darmstadt Noise Dataset benchmark, we achieve a PSNR of 48.28dB, while using 263 times fewer MACs, and 17.6 times fewer parameters than the state-of-the-art network, which achieves 49.12dB.

arXiv:2103.00053

PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation

One of the most efficient methods for model compression is hint distillation, where the student model is injected with information (hints) from several different layers of the teacher model. Although the selection of hint points can drastically alter the compression performance, conventional distillation approaches overlook this fact and use the same hint points as in the early studies. Therefore, we propose a clustering based hint selection methodology, where the layers of teacher model are clustered with respect to several metrics and the cluster centers are used as the hint points. Our method is applicable for any student network, once it is applied on a chosen teacher network. The proposed approach is validated in CIFAR-100 and ImageNet datasets, using various teacher-student pairs and numerous hint distillation methods. Our results show that hint points selected by our algorithm results in superior compression performance compared to state-of-the-art knowledge distillation algorithms on the same student models and datasets.

arXiv:2103.00793

Embedded Knowledge Distillation in Depth-Level Dynamic Neural Network

In real applications, different computation-resource devices need different-depth networks (e.g., ResNet-18/34/50) with high-accuracy. Usually, existing methods either design multiple networks and train them independently, or construct depth-level/width-level dynamic neural networks which is hard to prove the accuracy of each sub-net. In this article, we propose an elegant Depth-Level Dynamic Neural Network (DDNN) integrated different-depth sub-nets of similar architectures. To improve the generalization of sub-nets, we design the Embedded-Knowledge-Distillation (EKD) training mechanism for the DDNN to implement knowledge transfer from the teacher (full-net) to multiple students (sub-nets). Specifically, the Kullback-Leibler (KL) divergence is introduced to constrain the posterior class probability consistency between full-net and sub-nets, and self-attention distillation on the same resolution feature of different depth is addressed to drive more abundant feature representations of sub-nets. Thus, we can obtain multiple high-accuracy sub-nets simultaneously in a DDNN via the online knowledge distillation in each training iteration without extra computation cost. Extensive experiments on CIFAR-10/100, and ImageNet datasets demonstrate that sub-nets in DDNN with EKD training achieve better performance than individually training networks while preserving the original performance of full-nets.

arXiv:2103.00497공식 코드 · Papers with Code

Distilling Knowledge via Intermediate Classifiers

The crux of knowledge distillation is to effectively train a resource-limited student model with the guide of a pre-trained larger teacher model. However, when there is a large difference between the model complexities of teacher and student (i.e., capacity gap), knowledge distillation loses its strength in transferring knowledge from the teacher to the student, thus training a weaker student. To mitigate the impact of the capacity gap, we introduce knowledge distillation via intermediate heads. By extending the intermediate layers of the teacher (at various depths) with classifier heads, we cheaply acquire a cohort of heterogeneous pre-trained teachers. The intermediate classifier heads can all together be efficiently learned while freezing the backbone of the pre-trained teacher. The cohort of teachers (including the original teacher) co-teach the student simultaneously. Our experiments on various teacher-student pairs and datasets have demonstrated that the proposed approach outperforms the canonical knowledge distillation approach and its extensions.

arXiv:2103.00430공식 코드 · Papers with Code

Training Generative Adversarial Networks in One Stage

Generative Adversarial Networks (GANs) have demonstrated unprecedented success in various image generation tasks. The encouraging results, however, come at the price of a cumbersome training process, during which the generator and discriminator are alternately updated in two stages. In this paper, we investigate a general training scheme that enables training GANs efficiently in only one stage. Based on the adversarial losses of the generator and discriminator, we categorize GANs into two classes, Symmetric GANs and Asymmetric GANs, and introduce a novel gradient decomposition method to unify the two, allowing us to train both classes in one stage and hence alleviate the training effort. We also computationally analyze the efficiency of the proposed method, and empirically demonstrate that, the proposed method yields a solid $1.5\times$ acceleration across various datasets and network architectures. Furthermore, we show that the proposed method is readily applicable to other adversarial-training scenarios, such as data-free knowledge distillation. The code is available at https://github.com/zju-vipa/OSGAN.