PyTorchKR Papers

최신 논문

총 4,526편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2308.02770공식 코드 · Papers with Code

One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer

Recognizing characters from low-resolution (LR) text images poses a significant challenge due to the information deficiency as well as the noise and blur in low-quality images. Current solutions for low-resolution text recognition (LTR) typically rely on a two-stage pipeline that involves super-resolution as the first stage followed by the second-stage recognition. Although this pipeline is straightforward and intuitive, it has to use an additional super-resolution network, which causes inefficiencies during training and testing. Moreover, the recognition accuracy of the second stage heavily depends on the reconstruction quality of the first stage, causing ineffectiveness. In this work, we attempt to address these challenges from a novel perspective: adapting the recognizer to low-resolution inputs by transferring the knowledge from the high-resolution. Guided by this idea, we propose an efficient and effective knowledge distillation framework to achieve multi-level knowledge transfer. Specifically, the visual focus loss is proposed to extract the character position knowledge with resolution gap reduction and character region focus, the semantic contrastive loss is employed to exploit the contextual semantic knowledge with contrastive learning, and the soft logits loss facilitates both local word-level and global sequence-level learning from the soft teacher label. Extensive experiments show that the proposed one-stage pipeline significantly outperforms super-resolution based two-stage frameworks in terms of effectiveness and efficiency, accompanied by favorable robustness. Code is available at https://github.com/csguoh/KD-LTR.

arXiv:2308.03725공식 코드 · Papers with Code

Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge Distillation

Temporal Sentence Grounding in Videos (TSGV) aims to detect the event timestamps described by the natural language query from untrimmed videos. This paper discusses the challenge of achieving efficient computation in TSGV models while maintaining high performance. Most existing approaches exquisitely design complex architectures to improve accuracy with extra layers and loss, suffering from inefficiency and heaviness. Although some works have noticed that, they only make an issue of feature fusion layers, which can hardly enjoy the highspeed merit in the whole clunky network. To tackle this problem, we propose a novel efficient multi-teacher model (EMTM) based on knowledge distillation to transfer diverse knowledge from both heterogeneous and isomorphic networks. Specifically, We first unify different outputs of the heterogeneous models into one single form. Next, a Knowledge Aggregation Unit (KAU) is built to acquire high-quality integrated soft labels from multiple teachers. After that, the KAU module leverages the multi-scale video and global query information to adaptively determine the weights of different teachers. A Shared Encoder strategy is then proposed to solve the problem that the student shallow layers hardly benefit from teachers, in which an isomorphic teacher is collaboratively trained with the student to align their hidden states. Extensive experimental results on three popular TSGV benchmarks demonstrate that our method is both effective and efficient without bells and whistles.

arXiv:2308.02019공식 코드 · Papers with Code

Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty

We present our submission to the BabyLM challenge, whose goal was to improve the sample efficiency of language models. We trained an ensemble consisting of a GPT-2 and small LLaMA models on the developmentally-plausible, 10M-word BabyLM dataset, then distilled it into a small, 58M-parameter LLaMA model, which exceeds in performance both of its teachers as well as a similar model trained without distillation. This suggests that distillation can not only retain the full performance of the teacher model when the latter is trained on a sufficiently small dataset; it can exceed it, and lead to significantly better performance than direct training.

arXiv:2308.02346

Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning

Deep Neural Network (DNN) has achieved great success on datasets of closed class set. However, new classes, like new categories of social media topics, are continuously added to the real world, making it necessary to incrementally learn. This is hard for DNN because it tends to focus on fitting to new classes while ignoring old classes, a phenomenon known as catastrophic forgetting. State-of-the-art methods rely on knowledge distillation and data replay techniques but still have limitations. In this work, we analyze the causes of catastrophic forgetting in class incremental learning, which owes to three factors: representation drift, representation confusion, and classifier distortion. Based on this view, we propose a two-stage learning framework with a fixed encoder and an incrementally updated prototype classifier. The encoder is trained with self-supervised learning to generate a feature space with high intrinsic dimensionality, thus improving its transferability and generality. The classifier incrementally learns new prototypes while retaining the prototypes of previously learned data, which is crucial in preserving the decision boundary.Our method does not rely on preserved samples of old classes, is thus a non-exemplar based CIL method. Experiments on public datasets show that our method can significantly outperform state-of-the-art exemplar-based methods when they reserved 5 examplers per class, under the incremental setting of 10 phases, by 18.24% on CIFAR-100 and 9.37% on ImageNet100.

arXiv:2308.02177

Scene-aware Human Pose Generation using Transformer

Affordance learning considers the interaction opportunities for an actor in the scene and thus has wide application in scene understanding and intelligent robotics. In this paper, we focus on contextual affordance learning, i.e., using affordance as context to generate a reasonable human pose in a scene. Existing scene-aware human pose generation methods could be divided into two categories depending on whether using pose templates. Our proposed method belongs to the template-based category, which benefits from the representative pose templates. Moreover, inspired by recent transformer-based methods, we associate each query embedding with a pose template, and use the interaction between query embeddings and scene feature map to effectively predict the scale and offsets for each pose template. In addition, we employ knowledge distillation to facilitate the offset learning given the predicted scale. Comprehensive experiments on Sitcom dataset demonstrate the effectiveness of our method.

arXiv:2308.02117공식 코드 · Papers with Code

VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs

GNN-to-MLP distillation aims to utilize knowledge distillation (KD) to learn computationally-efficient multi-layer perceptron (student MLP) on graph data by mimicking the output representations of teacher GNN. Existing methods mainly make the MLP to mimic the GNN predictions over a few class labels. However, the class space may not be expressive enough for covering numerous diverse local graph structures, thus limiting the performance of knowledge transfer from GNN to MLP. To address this issue, we propose to learn a new powerful graph representation space by directly labeling nodes' diverse local structures for GNN-to-MLP distillation. Specifically, we propose a variant of VQ-VAE to learn a structure-aware tokenizer on graph data that can encode each node's local substructure as a discrete code. The discrete codes constitute a codebook as a new graph representation space that is able to identify different local graph structures of nodes with the corresponding code indices. Then, based on the learned codebook, we propose a new distillation target, namely soft code assignments, to directly transfer the structural knowledge of each node from GNN to MLP. The resulting framework VQGraph achieves new state-of-the-art performance on GNN-to-MLP distillation in both transductive and inductive settings across seven graph datasets. We show that VQGraph with better performance infers faster than GNNs by 828x, and also achieves accuracy improvement over GNNs and stand-alone MLPs by 3.90% and 28.05% on average, respectively. Code: https://github.com/YangLing0818/VQGraph.

arXiv:2308.01328

A vision transformer-based framework for knowledge transfer from multi-modal to mono-modal lymphoma subtyping models

Determining lymphoma subtypes is a crucial step for better patient treatment targeting to potentially increase their survival chances. In this context, the existing gold standard diagnosis method, which relies on gene expression technology, is highly expensive and time-consuming, making it less accessibility. Although alternative diagnosis methods based on IHC (immunohistochemistry) technologies exist (recommended by the WHO), they still suffer from similar limitations and are less accurate. Whole Slide Image (WSI) analysis using deep learning models has shown promising potential for cancer diagnosis, that could offer cost-effective and faster alternatives to existing methods. In this work, we propose a vision transformer-based framework for distinguishing DLBCL (Diffuse Large B-Cell Lymphoma) cancer subtypes from high-resolution WSIs. To this end, we introduce a multi-modal architecture to train a classifier model from various WSI modalities. We then leverage this model through a knowledge distillation process to efficiently guide the learning of a mono-modal classifier. Our experimental study conducted on a lymphoma dataset of 157 patients shows the promising performance of our mono-modal classification model, outperforming six recent state-of-the-art methods. In addition, the power-law curve, estimated on our experimental data, suggests that with more training data from a reasonable number of additional patients, our model could achieve competitive diagnosis accuracy with IHC technologies. Furthermore, the efficiency of our framework is confirmed through an additional experimental study on an external breast cancer dataset (BCI dataset).

arXiv:2308.01136

Leveraging Expert Models for Training Deep Neural Networks in Scarce Data Domains: Application to Offline Handwritten Signature Verification

This paper introduces a novel approach to leverage the knowledge of existing expert models for training new Convolutional Neural Networks, on domains where task-specific data are limited or unavailable. The presented scheme is applied in offline handwritten signature verification (OffSV) which, akin to other biometric applications, suffers from inherent data limitations due to regulatory restrictions. The proposed Student-Teacher (S-T) configuration utilizes feature-based knowledge distillation (FKD), combining graph-based similarity for local activations with global similarity measures to supervise student's training, using only handwritten text data. Remarkably, the models trained using this technique exhibit comparable, if not superior, performance to the teacher model across three popular signature datasets. More importantly, these results are attained without employing any signatures during the feature extraction training process. This study demonstrates the efficacy of leveraging existing expert models to overcome data scarcity challenges in OffSV and potentially other related domains.

arXiv:2308.01126공식 코드 · Papers with Code

Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Model

Current captioning approaches tend to generate correct but "generic" descriptions that lack real-world knowledge, e.g., named entities and contextual information. Considering that Vision-Language Pre-Training (VLP) models master massive such knowledge from large-scale web-harvested data, it is promising to utilize the generalizability of VLP models to incorporate knowledge into image descriptions. However, using VLP models faces challenges: zero-shot inference suffers from knowledge hallucination that leads to low-quality descriptions, but the generic bias in downstream task fine-tuning hinders the VLP model from expressing knowledge. To address these concerns, we propose a simple yet effective method called Knowledge-guided Replay (K-Replay), which enables the retention of pre-training knowledge during fine-tuning. Our approach consists of two parts: (1) a knowledge prediction task on automatically collected replay exemplars to continuously awaken the VLP model's memory about knowledge, thus preventing the model from collapsing into the generic pattern; (2) a knowledge distillation constraint to improve the faithfulness of generated descriptions hence alleviating the knowledge hallucination. To evaluate knowledge-enhanced descriptions, we construct a novel captioning benchmark KnowCap, containing knowledge of landmarks, famous brands, special foods and movie characters. Experimental results show that our approach effectively incorporates knowledge into descriptions, outperforming strong VLP baseline by 20.9 points (78.7->99.6) in CIDEr score and 20.5 percentage points (34.0%->54.5%) in knowledge recognition accuracy. Our code and data is available at https://github.com/njucckevin/KnowCap.

arXiv:2308.01098

Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search

Search query classification, as an effective way to understand user intents, is of great importance in real-world online ads systems. To ensure a lower latency, a shallow model (e.g. FastText) is widely used for efficient online inference. However, the representation ability of the FastText model is insufficient, resulting in poor classification performance, especially on some low-frequency queries and tailed categories. Using a deeper and more complex model (e.g. BERT) is an effective solution, but it will cause a higher online inference latency and more expensive computing costs. Thus, how to juggle both inference efficiency and classification performance is obviously of great practical importance. To overcome this challenge, in this paper, we propose knowledge condensation (KC), a simple yet effective knowledge distillation framework to boost the classification performance of the online FastText model under strict low latency constraints. Specifically, we propose to train an offline BERT model to retrieve more potentially relevant data. Benefiting from its powerful semantic representation, more relevant labels not exposed in the historical data will be added into the training set for better FastText model training. Moreover, a novel distribution-diverse multi-expert learning strategy is proposed to further improve the mining ability of relevant data. By training multiple BERT models from different data distributions, it can respectively perform better at high, middle, and low-frequency search queries. The model ensemble from multi-distribution makes its retrieval ability more powerful. We have deployed two versions of this framework in JD search, and both offline experiments and online A/B testing from multiple datasets have validated the effectiveness of the proposed approach.

arXiv:2308.01097공식 코드 · Papers with Code

Spatio-Temporal Branching for Motion Prediction using Motion Increments

Human motion prediction (HMP) has emerged as a popular research topic due to its diverse applications, but it remains a challenging task due to the stochastic and aperiodic nature of future poses. Traditional methods rely on hand-crafted features and machine learning techniques, which often struggle to model the complex dynamics of human motion. Recent deep learning-based methods have achieved success by learning spatio-temporal representations of motion, but these models often overlook the reliability of motion data. Additionally, the temporal and spatial dependencies of skeleton nodes are distinct. The temporal relationship captures motion information over time, while the spatial relationship describes body structure and the relationships between different nodes. In this paper, we propose a novel spatio-temporal branching network using incremental information for HMP, which decouples the learning of temporal-domain and spatial-domain features, extracts more motion information, and achieves complementary cross-domain knowledge learning through knowledge distillation. Our approach effectively reduces noise interference and provides more expressive information for characterizing motion by separately extracting temporal and spatial features. We evaluate our approach on standard HMP benchmarks and outperform state-of-the-art methods in terms of prediction accuracy.

arXiv:2308.00729

Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment

Video quality assessment (VQA) has attracted growing attention in recent years. While the great expense of annotating large-scale VQA datasets has become the main obstacle for current deep-learning methods. To surmount the constraint of insufficient training data, in this paper, we first consider the complete range of video distribution diversity (\ie content, distortion, motion) and employ diverse pretrained models (\eg architecture, pretext task, pre-training dataset) to benefit quality representation. An Adaptive Diverse Quality-aware feature Acquisition (Ada-DQA) framework is proposed to capture desired quality-related features generated by these frozen pretrained models. By leveraging the Quality-aware Acquisition Module (QAM), the framework is able to extract more essential and relevant features to represent quality. Finally, the learned quality representation is utilized as supplementary supervisory information, along with the supervision of the labeled quality score, to guide the training of a relatively lightweight VQA model in a knowledge distillation manner, which largely reduces the computational cost during inference. Experimental results on three mainstream no-reference VQA benchmarks clearly show the superior performance of Ada-DQA in comparison with current state-of-the-art approaches without using extra training data of VQA.

arXiv:2308.00155

Federated Learning for Data and Model Heterogeneity in Medical Imaging

Federated Learning (FL) is an evolving machine learning method in which multiple clients participate in collaborative learning without sharing their data with each other and the central server. In real-world applications such as hospitals and industries, FL counters the challenges of data heterogeneity and model heterogeneity as an inevitable part of the collaborative training. More specifically, different organizations, such as hospitals, have their own private data and customized models for local training. To the best of our knowledge, the existing methods do not effectively address both problems of model heterogeneity and data heterogeneity in FL. In this paper, we exploit the data and model heterogeneity simultaneously, and propose a method, MDH-FL (Exploiting Model and Data Heterogeneity in FL) to solve such problems to enhance the efficiency of the global model in FL. We use knowledge distillation and a symmetric loss to minimize the heterogeneity and its impact on the model performance. Knowledge distillation is used to solve the problem of model heterogeneity, and symmetric loss tackles with the data and label heterogeneity. We evaluate our method on the medical datasets to conform the real-world scenario of hospitals, and compare with the existing methods. The experimental results demonstrate the superiority of the proposed approach over the other existing methods.

arXiv:2308.00301공식 코드 · Papers with Code

Online Prototype Learning for Online Continual Learning

Online continual learning (CL) studies the problem of learning continuously from a single-pass data stream while adapting to new data and mitigating catastrophic forgetting. Recently, by storing a small subset of old data, replay-based methods have shown promising performance. Unlike previous methods that focus on sample storage or knowledge distillation against catastrophic forgetting, this paper aims to understand why the online learning models fail to generalize well from a new perspective of shortcut learning. We identify shortcut learning as the key limiting factor for online CL, where the learned features may be biased, not generalizable to new tasks, and may have an adverse impact on knowledge distillation. To tackle this issue, we present the online prototype learning (OnPro) framework for online CL. First, we propose online prototype equilibrium to learn representative features against shortcut learning and discriminative features to avoid class confusion, ultimately achieving an equilibrium status that separates all seen classes well while learning new classes. Second, with the feedback of online prototypes, we devise a novel adaptive prototypical feedback mechanism to sense the classes that are easily misclassified and then enhance their boundaries. Extensive experimental results on widely-used benchmark datasets demonstrate the superior performance of OnPro over the state-of-the-art baseline methods. Source code is available at https://github.com/weilllllls/OnPro.

arXiv:2308.00520공식 코드 · Papers with Code

NormKD: Normalized Logits for Knowledge Distillation

Logit based knowledge distillation gets less attention in recent years since feature based methods perform better in most cases. Nevertheless, we find it still has untapped potential when we re-investigate the temperature, which is a crucial hyper-parameter to soften the logit outputs. For most of the previous works, it was set as a fixed value for the entire distillation procedure. However, as the logits from different samples are distributed quite variously, it is not feasible to soften all of them to an equal degree by just a single temperature, which may make the previous work transfer the knowledge of each sample inadequately. In this paper, we restudy the hyper-parameter temperature and figure out its incapability to distill the knowledge from each sample sufficiently when it is a single value. To address this issue, we propose Normalized Knowledge Distillation (NormKD), with the purpose of customizing the temperature for each sample according to the characteristic of the sample's logit distribution. Compared to the vanilla KD, NormKD barely has extra computation or storage cost but performs significantly better on CIRAR-100 and ImageNet for image classification. Furthermore, NormKD can be easily applied to the other logit based methods and achieve better performance which can be closer to or even better than the feature based method.

arXiv:2307.16601

Sampling to Distill: Knowledge Transfer from Open-World Data

Data-Free Knowledge Distillation (DFKD) is a novel task that aims to train high-performance student models using only the pre-trained teacher network without original training data. Most of the existing DFKD methods rely heavily on additional generation modules to synthesize the substitution data resulting in high computational costs and ignoring the massive amounts of easily accessible, low-cost, unlabeled open-world data. Meanwhile, existing methods ignore the domain shift issue between the substitution data and the original data, resulting in knowledge from teachers not always trustworthy and structured knowledge from data becoming a crucial supplement. To tackle the issue, we propose a novel Open-world Data Sampling Distillation (ODSD) method for the DFKD task without the redundant generation process. First, we try to sample open-world data close to the original data's distribution by an adaptive sampling module and introduce a low-noise representation to alleviate the domain shift issue. Then, we build structured relationships of multiple data examples to exploit data knowledge through the student model itself and the teacher's structured representation. Extensive experiments on CIFAR-10, CIFAR-100, NYUv2, and ImageNet show that our ODSD method achieves state-of-the-art performance with lower FLOPs and parameters. Especially, we improve 1.50\%-9.59\% accuracy on the ImageNet dataset and avoid training the separate generator for each class.

arXiv:2307.15880공식 코드 · Papers with Code

Effective Whole-body Pose Estimation with Two-stages Distillation

Whole-body pose estimation localizes the human body, hand, face, and foot keypoints in an image. This task is challenging due to multi-scale body parts, fine-grained localization for low-resolution regions, and data scarcity. Meanwhile, applying a highly efficient and accurate pose estimator to widely human-centric understanding and generation tasks is urgent. In this work, we present a two-stage pose \textbf{D}istillation for \textbf{W}hole-body \textbf{P}ose estimators, named \textbf{DWPose}, to improve their effectiveness and efficiency. The first-stage distillation designs a weight-decay strategy while utilizing a teacher's intermediate feature and final logits with both visible and invisible keypoints to supervise the student from scratch. The second stage distills the student model itself to further improve performance. Different from the previous self-knowledge distillation, this stage finetunes the student's head with only 20% training time as a plug-and-play training strategy. For data limitations, we explore the UBody dataset that contains diverse facial expressions and hand gestures for real-life applications. Comprehensive experiments show the superiority of our proposed simple yet effective methods. We achieve new state-of-the-art performance on COCO-WholeBody, significantly boosting the whole-body AP of RTMPose-l from 64.8% to 66.5%, even surpassing RTMPose-x teacher with 65.3% AP. We release a series of models with different sizes, from tiny to large, for satisfying various downstream tasks. Our codes and models are available at https://github.com/IDEA-Research/DWPose.

arXiv:2307.16419공식 코드 · Papers with Code

Subspace Distillation for Continual Learning

An ultimate objective in continual learning is to preserve knowledge learned in preceding tasks while learning new tasks. To mitigate forgetting prior knowledge, we propose a novel knowledge distillation technique that takes into the account the manifold structure of the latent/output space of a neural network in learning novel tasks. To achieve this, we propose to approximate the data manifold up-to its first order, hence benefiting from linear subspaces to model the structure and maintain the knowledge of a neural network while learning novel concepts. We demonstrate that the modeling with subspaces provides several intriguing properties, including robustness to noise and therefore effective for mitigating Catastrophic Forgetting in continual learning. We also discuss and show how our proposed method can be adopted to address both classification and segmentation problems. Empirically, we observe that our proposed method outperforms various continual learning methods on several challenging datasets including Pascal VOC, and Tiny-Imagenet. Furthermore, we show how the proposed method can be seamlessly combined with existing learning approaches to improve their performances. The codes of this article will be available at https://github.com/csiro-robotics/SDCL.

arXiv:2307.16363공식 코드 · Papers with Code

BearingPGA-Net: A Lightweight and Deployable Bearing Fault Diagnosis Network via Decoupled Knowledge Distillation and FPGA Acceleration

Deep learning has achieved remarkable success in the field of bearing fault diagnosis. However, this success comes with larger models and more complex computations, which cannot be transferred into industrial fields requiring models to be of high speed, strong portability, and low power consumption. In this paper, we propose a lightweight and deployable model for bearing fault diagnosis, referred to as BearingPGA-Net, to address these challenges. Firstly, aided by a well-trained large model, we train BearingPGA-Net via decoupled knowledge distillation. Despite its small size, our model demonstrates excellent fault diagnosis performance compared to other lightweight state-of-the-art methods. Secondly, we design an FPGA acceleration scheme for BearingPGA-Net using Verilog. This scheme involves the customized quantization and designing programmable logic gates for each layer of BearingPGA-Net on the FPGA, with an emphasis on parallel computing and module reuse to enhance the computational speed. To the best of our knowledge, this is the first instance of deploying a CNN-based bearing fault diagnosis model on an FPGA. Experimental results reveal that our deployment scheme achieves over 200 times faster diagnosis speed compared to CPU, while achieving a lower-than-0.4\% performance drop in terms of F1, Recall, and Precision score on our independently-collected bearing dataset. Our code is available at \url{https://github.com/asdvfghg/BearingPGA-Net}.

arXiv:2307.15994

UPFL: Unsupervised Personalized Federated Learning towards New Clients

Personalized federated learning has gained significant attention as a promising approach to address the challenge of data heterogeneity. In this paper, we address a relatively unexplored problem in federated learning. When a federated model has been trained and deployed, and an unlabeled new client joins, providing a personalized model for the new client becomes a highly challenging task. To address this challenge, we extend the adaptive risk minimization technique into the unsupervised personalized federated learning setting and propose our method, FedTTA. We further improve FedTTA with two simple yet effective optimization strategies: enhancing the training of the adaptation model with proxy regularization and early-stopping the adaptation through entropy. Moreover, we propose a knowledge distillation loss specifically designed for FedTTA to address the device heterogeneity. Extensive experiments on five datasets against eleven baselines demonstrate the effectiveness of our proposed FedTTA and its variants. The code is available at: https://github.com/anonymous-federated-learning/code.