PyTorchKR Papers

최신 논문

총 4,526편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2211.06018공식 코드 · Papers with Code

MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation

Recent works have shown that optical flow can be learned by deep networks from unlabelled image pairs based on brightness constancy assumption and smoothness prior. Current approaches additionally impose an augmentation regularization term for continual self-supervision, which has been proved to be effective on difficult matching regions. However, this method also amplify the inevitable mismatch in unsupervised setting, blocking the learning process towards optimal solution. To break the dilemma, we propose a novel mutual distillation framework to transfer reliable knowledge back and forth between the teacher and student networks for alternate improvement. Concretely, taking estimation of off-the-shelf unsupervised approach as pseudo labels, our insight locates at defining a confidence selection mechanism to extract relative good matches, and then add diverse data augmentation for distilling adequate and reliable knowledge from teacher to student. Thanks to the decouple nature of our method, we can choose a stronger student architecture for sufficient learning. Finally, better student prediction is adopted to transfer knowledge back to the efficient teacher without additional costs in real deployment. Rather than formulating it as a supervised task, we find that introducing an extra unsupervised term for multi-target learning achieves best final results. Extensive experiments show that our approach, termed MDFlow, achieves state-of-the-art real-time accuracy and generalization ability on challenging benchmarks. Code is available at https://github.com/ltkong218/MDFlow.

arXiv:2211.05942공식 코드 · Papers with Code

Knowledge Distillation from Cross Teaching Teachers for Efficient Semi-Supervised Abdominal Organ Segmentation in CT

For more clinical applications of deep learning models for medical image segmentation, high demands on labeled data and computational resources must be addressed. This study proposes a coarse-to-fine framework with two teacher models and a student model that combines knowledge distillation and cross teaching, a consistency regularization based on pseudo-labels, for efficient semi-supervised learning. The proposed method is demonstrated on the abdominal multi-organ segmentation task in CT images under the MICCAI FLARE 2022 challenge, with mean Dice scores of 0.8429 and 0.8520 in the validation and test sets, respectively.

arXiv:2211.04772공식 코드 · Papers with Code

Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation

Audio Spectrogram Transformer models rule the field of Audio Tagging, outrunning previously dominating Convolutional Neural Networks (CNNs). Their superiority is based on the ability to scale up and exploit large-scale datasets such as AudioSet. However, Transformers are demanding in terms of model size and computational requirements compared to CNNs. We propose a training procedure for efficient CNNs based on offline Knowledge Distillation (KD) from high-performing yet complex transformers. The proposed training schema and the efficient CNN design based on MobileNetV3 results in models outperforming previous solutions in terms of parameter and computational efficiency and prediction performance. We provide models of different complexity levels, scaling from low-complexity models up to a new state-of-the-art performance of .483 mAP on AudioSet. Source Code available at: https://github.com/fschmid56/EfficientAT

arXiv:2211.04742

Knowledge Distillation for Federated Learning: a Practical Guide

Federated Learning (FL) enables the training of Deep Learning models without centrally collecting possibly sensitive raw data. This paves the way for stronger privacy guarantees when building predictive models. The most used algorithms for FL are parameter-averaging based schemes (e.g., Federated Averaging) that, however, have well known limits: (i) Clients must implement the same model architecture; (ii) Transmitting model weights and model updates implies high communication cost, which scales up with the number of model parameters; (iii) In presence of non-IID data distributions, parameter-averaging aggregation schemes perform poorly due to client model drifts. Federated adaptations of regular Knowledge Distillation (KD) can solve and/or mitigate the weaknesses of parameter-averaging FL algorithms while possibly introducing other trade-offs. In this article, we provide a review of KD-based algorithms tailored for specific FL issues.

arXiv:2211.04256

Bridging Fairness and Environmental Sustainability in Natural Language Processing

Fairness and environmental impact are important research directions for the sustainable development of artificial intelligence. However, while each topic is an active research area in natural language processing (NLP), there is a surprising lack of research on the interplay between the two fields. This lacuna is highly problematic, since there is increasing evidence that an exclusive focus on fairness can actually hinder environmental sustainability, and vice versa. In this work, we shed light on this crucial intersection in NLP by (1) investigating the efficiency of current fairness approaches through surveying example methods for reducing unfair stereotypical bias from the literature, and (2) evaluating a common technique to reduce energy consumption (and thus environmental impact) of English NLP models, knowledge distillation (KD), for its impact on fairness. In this case study, we evaluate the effect of important KD factors, including layer and dimensionality reduction, with respect to: (a) performance on the distillation task (natural language inference and semantic similarity prediction), and (b) multiple measures and dimensions of stereotypical bias (e.g., gender bias measured via the Word Embedding Association Test). Our results lead us to clarify current assumptions regarding the effect of KD on unfair bias: contrary to other findings, we show that KD can actually decrease model fairness.

arXiv:2211.03946공식 코드 · Papers with Code

Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study

Mixup is a popular data augmentation technique based on creating new samples by linear interpolation between two given data samples, to improve both the generalization and robustness of the trained model. Knowledge distillation (KD), on the other hand, is widely used for model compression and transfer learning, which involves using a larger network's implicit knowledge to guide the learning of a smaller network. At first glance, these two techniques seem very different, however, we found that "smoothness" is the connecting link between the two and is also a crucial attribute in understanding KD's interplay with mixup. Although many mixup variants and distillation methods have been proposed, much remains to be understood regarding the role of a mixup in knowledge distillation. In this paper, we present a detailed empirical study on various important dimensions of compatibility between mixup and knowledge distillation. We also scrutinize the behavior of the networks trained with a mixup in the light of knowledge distillation through extensive analysis, visualizations, and comprehensive experiments on image classification. Finally, based on our findings, we suggest improved strategies to guide the student network to enhance its effectiveness. Additionally, the findings of this study provide insightful suggestions to researchers and practitioners that commonly use techniques from KD. Our code is available at https://github.com/hchoi71/MIX-KD.

arXiv:2211.03876공식 코드 · Papers with Code

CoNMix for Source-free Single and Multi-target Domain Adaptation

This work introduces the novel task of Source-free Multi-target Domain Adaptation and proposes adaptation framework comprising of \textbf{Co}nsistency with \textbf{N}uclear-Norm Maximization and \textbf{Mix}Up knowledge distillation (\textit{CoNMix}) as a solution to this problem. The main motive of this work is to solve for Single and Multi target Domain Adaptation (SMTDA) for the source-free paradigm, which enforces a constraint where the labeled source data is not available during target adaptation due to various privacy-related restrictions on data sharing. The source-free approach leverages target pseudo labels, which can be noisy, to improve the target adaptation. We introduce consistency between label preserving augmentations and utilize pseudo label refinement methods to reduce noisy pseudo labels. Further, we propose novel MixUp Knowledge Distillation (MKD) for better generalization on multiple target domains using various source-free STDA models. We also show that the Vision Transformer (VT) backbone gives better feature representation with improved domain transferability and class discriminability. Our proposed framework achieves the state-of-the-art (SOTA) results in various paradigms of source-free STDA and MTDA settings on popular domain adaptation datasets like Office-Home, Office-Caltech, and DomainNet. Project Page: https://sites.google.com/view/conmix-vcl

arXiv:2211.03284

Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization

The CTC model has been widely applied to many application scenarios because of its simple structure, excellent performance, and fast inference speed. There are many peaks in the probability distribution predicted by the CTC models, and each peak represents a non-blank token. The recognition latency of CTC models can be reduced by encouraging the model to predict peaks earlier. Existing methods to reduce latency require modifying the transition relationship between tokens in the forward-backward algorithm, and the gradient calculation. Some of these methods even depend on the forced alignment results provided by other pretrained models. The above methods are complex to implement. To reduce the peak latency, we propose a simple and novel method named peak-first regularization, which utilizes a frame-wise knowledge distillation function to force the probability distribution of the CTC model to shift left along the time axis instead of directly modifying the calculation process of CTC loss and gradients. All the experiments are conducted on a Chinese Mandarin dataset AISHELL-1. We have verified the effectiveness of the proposed regularization on both streaming and non-streaming CTC models respectively. The results show that the proposed method can reduce the average peak latency by about 100 to 200 milliseconds with almost no degradation of recognition accuracy.

arXiv:2211.02944

Breaking the trade-off in personalized speech enhancement with cross-task knowledge distillation

Personalized speech enhancement (PSE) models achieve promising results compared with unconditional speech enhancement models due to their ability to remove interfering speech in addition to background noise. Unlike unconditional speech enhancement, causal PSE models may occasionally remove the target speech by mistake. The PSE models also tend to leak interfering speech when the target speaker is silent for an extended period. We show that existing PSE methods suffer from a trade-off between speech over-suppression and interference leakage by addressing one problem at the expense of the other. We propose a new PSE model training framework using cross-task knowledge distillation to mitigate this trade-off. Specifically, we utilize a personalized voice activity detector (pVAD) during training to exclude the non-target speech frames that are wrongly identified as containing the target speaker with hard or soft classification. This prevents the PSE model from being too aggressive while still allowing the model to learn to suppress the input speech when it is likely to be spoken by interfering speakers. Comprehensive evaluation results are presented, covering various PSE usage scenarios.

arXiv:2211.03457

Closing the Gap between Client and Global Model Performance in Heterogeneous Federated Learning

The heterogeneity of hardware and data is a well-known and studied problem in the community of Federated Learning (FL) as running under heterogeneous settings. Recently, custom-size client models trained with Knowledge Distillation (KD) has emerged as a viable strategy for tackling the heterogeneity challenge. However, previous efforts in this direction are aimed at client model tuning rather than their impact onto the knowledge aggregation of the global model. Despite performance of global models being the primary objective of FL systems, under heterogeneous settings client models have received more attention. Here, we provide more insights into how the chosen approach for training custom client models has an impact on the global model, which is essential for any FL application. We show the global model can fully leverage the strength of KD with heterogeneous data. Driven by empirical observations, we further propose a new approach that combines KD and Learning without Forgetting (LwoF) to produce improved personalised models. We bring heterogeneous FL on pair with the mighty FedAvg of homogeneous FL, in realistic deployment scenarios with dropping clients.

arXiv:2211.03375공식 코드 · Papers with Code

AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time

Accurate whole-body multi-person pose estimation and tracking is an important yet challenging topic in computer vision. To capture the subtle actions of humans for complex behavior analysis, whole-body pose estimation including the face, body, hand and foot is essential over conventional body-only pose estimation. In this paper, we present AlphaPose, a system that can perform accurate whole-body pose estimation and tracking jointly while running in realtime. To this end, we propose several new techniques: Symmetric Integral Keypoint Regression (SIKR) for fast and fine localization, Parametric Pose Non-Maximum-Suppression (P-NMS) for eliminating redundant human detections and Pose Aware Identity Embedding for jointly pose estimation and tracking. During training, we resort to Part-Guided Proposal Generator (PGPG) and multi-domain knowledge distillation to further improve the accuracy. Our method is able to localize whole-body keypoints accurately and tracks humans simultaneously given inaccurate bounding boxes and redundant detections. We show a significant improvement over current state-of-the-art methods in both speed and accuracy on COCO-wholebody, COCO, PoseTrack, and our proposed Halpe-FullBody pose estimation dataset. Our model, source codes and dataset are made publicly available at https://github.com/MVIG-SJTU/AlphaPose.

arXiv:2211.02638공식 코드 · Papers with Code

A Knowledge Distillation Framework For Enhancing Ear-EEG Based Sleep Staging With Scalp-EEG Data

Sleep plays a crucial role in the well-being of human lives. Traditional sleep studies using Polysomnography are associated with discomfort and often lower sleep quality caused by the acquisition setup. Previous works have focused on developing less obtrusive methods to conduct high-quality sleep studies, and ear-EEG is among popular alternatives. However, the performance of sleep staging based on ear-EEG is still inferior to scalp-EEG based sleep staging. In order to address the performance gap between scalp-EEG and ear-EEG based sleep staging, we propose a cross-modal knowledge distillation strategy, which is a domain adaptation approach. Our experiments and analysis validate the effectiveness of the proposed approach with existing architectures, where it enhances the accuracy of the ear-EEG based sleep staging by 3.46% and Cohen's kappa coefficient by a margin of 0.038.

arXiv:2211.02213공식 코드 · Papers with Code

SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object Detection

Domain adaptive object detection (DAOD) aims to alleviate transfer performance degradation caused by the cross-domain discrepancy. However, most existing DAOD methods are dominated by outdated and computationally intensive two-stage Faster R-CNN, which is not the first choice for industrial applications. In this paper, we propose a novel semi-supervised domain adaptive YOLO (SSDA-YOLO) based method to improve cross-domain detection performance by integrating the compact one-stage stronger detector YOLOv5 with domain adaptation. Specifically, we adapt the knowledge distillation framework with the Mean Teacher model to assist the student model in obtaining instance-level features of the unlabeled target domain. We also utilize the scene style transfer to cross-generate pseudo images in different domains for remedying image-level differences. In addition, an intuitive consistency loss is proposed to further align cross-domain predictions. We evaluate SSDA-YOLO on public benchmarks including PascalVOC, Clipart1k, Cityscapes, and Foggy Cityscapes. Moreover, to verify its generalization, we conduct experiments on yawning detection datasets collected from various real classrooms. The results show considerable improvements of our method in these DAOD tasks, which reveals both the effectiveness of proposed adaptive modules and the urgency of applying more advanced detectors in DAOD. Our code is available on \url{https://github.com/hnuzhy/SSDA-YOLO}.

arXiv:2211.01452공식 코드 · Papers with Code

MPCFormer: fast, performant and private Transformer inference with MPC

Enabling private inference is crucial for many cloud inference services that are based on Transformer models. However, existing private inference solutions can increase the inference latency by more than 60x or significantly compromise the inference quality. In this paper, we design the framework MPCFORMER as a practical solution, using Secure Multi-Party Computation (MPC) and Knowledge Distillation (KD). Through extensive evaluations, we show that MPCFORMER significantly speeds up Transformer inference in MPC settings while achieving similar ML performance to the input model. On the IMDb dataset, it achieves similar performance to BERTBASE, while being 5.3x faster. On the GLUE benchmark, it achieves 97% performance of BERTBASE with a 2.2x speedup. MPCFORMER remains effective with different trained Transformer weights such as ROBERTABASE and larger models including BERTLarge. Code is available at https://github.com/MccRee177/MPCFormer.

arXiv:2211.01200

Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model

Pre-trained multilingual language models play an important role in cross-lingual natural language understanding tasks. However, existing methods did not focus on learning the semantic structure of representation, and thus could not optimize their performance. In this paper, we propose Multi-level Multilingual Knowledge Distillation (MMKD), a novel method for improving multilingual language models. Specifically, we employ a teacher-student framework to adopt rich semantic representation knowledge in English BERT. We propose token-, word-, sentence-, and structure-level alignment objectives to encourage multiple levels of consistency between source-target pairs and correlation similarity between teacher and student models. We conduct experiments on cross-lingual evaluation benchmarks including XNLI, PAWS-X, and XQuAD. Experimental results show that MMKD outperforms other baseline models of similar size on XNLI and XQuAD and obtains comparable performance on PAWS-X. Especially, MMKD obtains significant performance gains on low-resource languages.

arXiv:2211.01071공식 코드 · Papers with Code

Gradient Knowledge Distillation for Pre-trained Language Models

Knowledge distillation (KD) is an effective framework to transfer knowledge from a large-scale teacher to a compact yet well-performing student. Previous KD practices for pre-trained language models mainly transfer knowledge by aligning instance-wise outputs between the teacher and student, while neglecting an important knowledge source, i.e., the gradient of the teacher. The gradient characterizes how the teacher responds to changes in inputs, which we assume is beneficial for the student to better approximate the underlying mapping function of the teacher. Therefore, we propose Gradient Knowledge Distillation (GKD) to incorporate the gradient alignment objective into the distillation process. Experimental results show that GKD outperforms previous KD methods regarding student performance. Further analysis shows that incorporating gradient knowledge makes the student behave more consistently with the teacher, improving the interpretability greatly.

arXiv:2211.00899

LightVessel: Exploring Lightweight Coronary Artery Vessel Segmentation via Similarity Knowledge Distillation

In recent years, deep convolution neural networks (DCNNs) have achieved great prospects in coronary artery vessel segmentation. However, it is difficult to deploy complicated models in clinical scenarios since high-performance approaches have excessive parameters and high computation costs. To tackle this problem, we propose \textbf{LightVessel}, a Similarity Knowledge Distillation Framework, for lightweight coronary artery vessel segmentation. Primarily, we propose a Feature-wise Similarity Distillation (FSD) module for semantic-shift modeling. Specifically, we calculate the feature similarity between the symmetric layers from the encoder and decoder. Then the similarity is transferred as knowledge from a cumbersome teacher network to a non-trained lightweight student network. Meanwhile, for encouraging the student model to learn more pixel-wise semantic information, we introduce the Adversarial Similarity Distillation (ASD) module. Concretely, the ASD module aims to construct the spatial adversarial correlation between the annotation and prediction from the teacher and student models, respectively. Through the ASD module, the student model obtains fined-grained subtle edge segmented results of the coronary artery vessel. Extensive experiments conducted on Clinical Coronary Artery Vessel Dataset demonstrate that LightVessel outperforms various knowledge distillation counterparts.

arXiv:2211.00748

Maximum Likelihood Distillation for Robust Modulation Classification

Deep Neural Networks are being extensively used in communication systems and Automatic Modulation Classification (AMC) in particular. However, they are very susceptible to small adversarial perturbations that are carefully crafted to change the network decision. In this work, we build on knowledge distillation ideas and adversarial training in order to build more robust AMC systems. We first outline the importance of the quality of the training data in terms of accuracy and robustness of the model. We then propose to use the Maximum Likelihood function, which could solve the AMC problem in offline settings, to generate better training labels. Those labels teach the model to be uncertain in challenging conditions, which permits to increase the accuracy, as well as the robustness of the model when combined with adversarial training. Interestingly, we observe that this increase in performance transfers to online settings, where the Maximum Likelihood function cannot be used in practice. Overall, this work highlights the potential of learning to be uncertain in difficult scenarios, compared to directly removing label noise.

arXiv:2211.00508공식 코드 · Papers with Code

Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation

Knowledge distillation(KD) is a common approach to improve model performance in automatic speech recognition (ASR), where a student model is trained to imitate the output behaviour of a teacher model. However, traditional KD methods suffer from teacher label storage issue, especially when the training corpora are large. Although on-the-fly teacher label generation tackles this issue, the training speed is significantly slower as the teacher model has to be evaluated every batch. In this paper, we reformulate the generation of teacher label as a codec problem. We propose a novel Multi-codebook Vector Quantization (MVQ) approach that compresses teacher embeddings to codebook indexes (CI). Based on this, a KD training framework (MVQ-KD) is proposed where a student model predicts the CI generated from the embeddings of a self-supervised pre-trained teacher model. Experiments on the LibriSpeech clean-100 hour show that MVQ-KD framework achieves comparable performance as traditional KD methods (l1, l2), while requiring 256 times less storage. When the full LibriSpeech dataset is used, MVQ-KD framework results in 13.8% and 8.2% relative word error rate reductions (WERRs) for non -streaming transducer on test-clean and test-other and 4.0% and 4.9% for streaming transducer. The implementation of this work is already released as a part of the open-source project icefall.

arXiv:2211.00239

ARDIR: Improving Robustness using Knowledge Distillation of Internal Representation

Adversarial training is the most promising method for learning robust models against adversarial examples. A recent study has shown that knowledge distillation between the same architectures is effective in improving the performance of adversarial training. Exploiting knowledge distillation is a new approach to improve adversarial training and has attracted much attention. However, its performance is still insufficient. Therefore, we propose Adversarial Robust Distillation with Internal Representation~(ARDIR) to utilize knowledge distillation even more effectively. In addition to the output of the teacher model, ARDIR uses the internal representation of the teacher model as a label for adversarial training. This enables the student model to be trained with richer, more informative labels. As a result, ARDIR can learn more robust student models. We show that ARDIR outperforms previous methods in our experiments.