PyTorchKR Papers

최신 논문

총 1,512편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2108.06027공식 코드 · Papers with Code

PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval

Recently, dense passage retrieval has become a mainstream approach to finding relevant information in various natural language processing tasks. A number of studies have been devoted to improving the widely adopted dual-encoder architecture. However, most of the previous studies only consider query-centric similarity relation when learning the dual-encoder retriever. In order to capture more comprehensive similarity relations, we propose a novel approach that leverages both query-centric and PAssage-centric sImilarity Relations (called PAIR) for dense passage retrieval. To implement our approach, we make three major technical contributions by introducing formal formulations of the two kinds of similarity relations, generating high-quality pseudo labeled data via knowledge distillation, and designing an effective two-stage training procedure that incorporates passage-centric similarity relation constraint. Extensive experiments show that our approach significantly outperforms previous state-of-the-art models on both MSMARCO and Natural Questions datasets.

arXiv:2108.05507공식 코드 · Papers with Code

Distilling Holistic Knowledge with Graph Neural Networks

Knowledge Distillation (KD) aims at transferring knowledge from a larger well-optimized teacher network to a smaller learnable student network.Existing KD methods have mainly considered two types of knowledge, namely the individual knowledge and the relational knowledge. However, these two types of knowledge are usually modeled independently while the inherent correlations between them are largely ignored. It is critical for sufficient student network learning to integrate both individual knowledge and relational knowledge while reserving their inherent correlation. In this paper, we propose to distill the novel holistic knowledge based on an attributed graph constructed among instances. The holistic knowledge is represented as a unified graph-based embedding by aggregating individual knowledge from relational neighborhood samples with graph neural networks, the student network is learned by distilling the holistic knowledge in a contrastive manner. Extensive experiments and ablation studies are conducted on benchmark datasets, the results demonstrate the effectiveness of the proposed method. The code has been published in https://github.com/wyc-ruiker/HKD

arXiv:2108.05045공식 코드 · Papers with Code

Semi-Supervised Domain Generalizable Person Re-Identification

Existing person re-identification (re-id) methods are stuck when deployed to a new unseen scenario despite the success in cross-camera person matching. Recent efforts have been substantially devoted to domain adaptive person re-id where extensive unlabeled data in the new scenario are utilized in a transductive learning manner. However, for each scenario, it is required to first collect enough data and then train such a domain adaptive re-id model, thus restricting their practical application. Instead, we aim to explore multiple labeled datasets to learn generalized domain-invariant representations for person re-id, which is expected universally effective for each new-coming re-id scenario. To pursue practicability in real-world systems, we collect all the person re-id datasets (20 datasets) in this field and select the three most frequently used datasets (i.e., Market1501, DukeMTMC, and MSMT17) as unseen target domains. In addition, we develop DataHunter that collects over 300K+ weak annotated images named YouTube-Human from YouTube street-view videos, which joins 17 remaining full labeled datasets to form multiple source domains. On such a large and challenging benchmark called FastHuman (~440K+ labeled images), we further propose a simple yet effective Semi-Supervised Knowledge Distillation (SSKD) framework. SSKD effectively exploits the weakly annotated data by assigning soft pseudo labels to YouTube-Human to improve models' generalization ability. Experiments on several protocols verify the effectiveness of the proposed SSKD framework on domain generalizable person re-id, which is even comparable to supervised learning on the target domains. Lastly, but most importantly, we hope the proposed benchmark FastHuman could bring the next development of domain generalizable person re-id algorithms.

arXiv:2108.03084공식 코드 · Papers with Code

Transferring Knowledge Distillation for Multilingual Social Event Detection

Recently published graph neural networks (GNNs) show promising performance at social event detection tasks. However, most studies are oriented toward monolingual data in languages with abundant training samples. This has left the more common multilingual settings and lesser-spoken languages relatively unexplored. Thus, we present a GNN that incorporates cross-lingual word embeddings for detecting events in multilingual data streams. The first exploit is to make the GNN work with multilingual data. For this, we outline a construction strategy that aligns messages in different languages at both the node and semantic levels. Relationships between messages are established by merging entities that are the same but are referred to in different languages. Non-English message representations are converted into English semantic space via the cross-lingual word embeddings. The resulting message graph is then uniformly encoded by a GNN model. In special cases where a lesser-spoken language needs to be detected, a novel cross-lingual knowledge distillation framework, called CLKD, exploits prior knowledge learned from similar threads in English to make up for the paucity of annotated data. Experiments on both synthetic and real-world datasets show the framework to be highly effective at detection in both multilingual data and in languages where training samples are scarce.

arXiv:2108.02598공식 코드 · Papers with Code

Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification

End-to-end intent classification using speech has numerous advantages compared to the conventional pipeline approach using automatic speech recognition (ASR), followed by natural language processing modules. It attempts to predict intent from speech without using an intermediate ASR module. However, such end-to-end framework suffers from the unavailability of large speech resources with higher acoustic variation in spoken language understanding. In this work, we exploit the scope of the transformer distillation method that is specifically designed for knowledge distillation from a transformer based language model to a transformer based speech model. In this regard, we leverage the reliable and widely used bidirectional encoder representations from transformers (BERT) model as a language model and transfer the knowledge to build an acoustic model for intent classification using the speech. In particular, a multilevel transformer based teacher-student model is designed, and knowledge distillation is performed across attention and hidden sub-layers of different transformer layers of the student and teacher models. We achieve an intent classification accuracy of 99.10% and 88.79% for Fluent speech corpus and ATIS database, respectively. Further, the proposed method demonstrates better performance and robustness in acoustically degraded condition compared to the baseline method.

arXiv:2108.02092공식 코드 · Papers with Code

Online Knowledge Distillation for Efficient Pose Estimation

Existing state-of-the-art human pose estimation methods require heavy computational resources for accurate predictions. One promising technique to obtain an accurate yet lightweight pose estimator is knowledge distillation, which distills the pose knowledge from a powerful teacher model to a less-parameterized student model. However, existing pose distillation works rely on a heavy pre-trained estimator to perform knowledge transfer and require a complex two-stage learning procedure. In this work, we investigate a novel Online Knowledge Distillation framework by distilling Human Pose structure knowledge in a one-stage manner to guarantee the distillation efficiency, termed OKDHP. Specifically, OKDHP trains a single multi-branch network and acquires the predicted heatmaps from each, which are then assembled by a Feature Aggregation Unit (FAU) as the target heatmaps to teach each branch in reverse. Instead of simply averaging the heatmaps, FAU which consists of multiple parallel transformations with different receptive fields, leverages the multi-scale information, thus obtains target heatmaps with higher-quality. Specifically, the pixel-wise Kullback-Leibler (KL) divergence is utilized to minimize the discrepancy between the target heatmaps and the predicted ones, which enables the student network to learn the implicit keypoint relationship. Besides, an unbalanced OKDHP scheme is introduced to customize the student networks with different compression rates. The effectiveness of our approach is demonstrated by extensive experiments on two common benchmark datasets, MPII and COCO.

arXiv:2108.01958공식 코드 · Papers with Code

Learning Compatible Embeddings

Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. Previous related works usually leverage losses used in knowledge distillation which can cause performance degradations or not guarantee compatibility. To address these issues, we propose a general framework called Learning Compatible Embeddings (LCE) which is applicable for both cross model compatibility and compatible training in direct/forward/backward manners. Our compatibility is achieved by aligning class centers between models directly or via a transformation, and restricting more compact intra-class distributions for the new model. Experiments are conducted in extensive scenarios such as changes of training dataset, loss functions, network architectures as well as feature dimensions, and demonstrate that LCE efficiently enables model compatibility with marginal sacrifices of accuracies. The code will be available at https://github.com/IrvingMeng/LCE.

arXiv:2107.13715공식 코드 · Papers with Code

Hierarchical Self-supervised Augmented Knowledge Distillation

Knowledge distillation often involves how to define and transfer knowledge from teacher to student effectively. Although recent self-supervised contrastive knowledge achieves the best performance, forcing the network to learn such knowledge may damage the representation learning of the original class recognition task. We therefore adopt an alternative self-supervised augmented task to guide the network to learn the joint distribution of the original recognition task and self-supervised auxiliary task. It is demonstrated as a richer knowledge to improve the representation power without losing the normal classification capability. Moreover, it is incomplete that previous methods only transfer the probabilistic knowledge between the final layers. We propose to append several auxiliary classifiers to hierarchical intermediate feature maps to generate diverse self-supervised knowledge and perform the one-to-one transfer to teach the student network thoroughly. Our method significantly surpasses the previous SOTA SSKD with an average improvement of 2.56\% on CIFAR-100 and an improvement of 0.77\% on ImageNet across widely used network pairs. Codes are available at https://github.com/winycg/HSAKD.

arXiv:2107.11789공식 코드 · Papers with Code

ROD: Reception-aware Online Distillation for Sparse Graphs

Graph neural networks (GNNs) have been widely used in many graph-based tasks such as node classification, link prediction, and node clustering. However, GNNs gain their performance benefits mainly from performing the feature propagation and smoothing across the edges of the graph, thus requiring sufficient connectivity and label information for effective propagation. Unfortunately, many real-world networks are sparse in terms of both edges and labels, leading to sub-optimal performance of GNNs. Recent interest in this sparse problem has focused on the self-training approach, which expands supervised signals with pseudo labels. Nevertheless, the self-training approach inherently cannot realize the full potential of refining the learning performance on sparse graphs due to the unsatisfactory quality and quantity of pseudo labels. In this paper, we propose ROD, a novel reception-aware online knowledge distillation approach for sparse graph learning. We design three supervision signals for ROD: multi-scale reception-aware graph knowledge, task-based supervision, and rich distilled knowledge, allowing online knowledge transfer in a peer-teaching manner. To extract knowledge concealed in the multi-scale reception fields, ROD explicitly requires individual student models to preserve different levels of locality information. For a given task, each student would predict based on its reception-scale knowledge, while simultaneously a strong teacher is established on-the-fly by combining multi-scale knowledge. Our approach has been extensively evaluated on 9 datasets and a variety of graph-based tasks, including node classification, link prediction, and node clustering. The result demonstrates that ROD achieves state-of-art performance and is more robust for the graph sparsity.

arXiv:2107.05377공식 코드 · Papers with Code

A Flexible Multi-Task Model for BERT Serving

In this demonstration, we present an efficient BERT-based multi-task (MT) framework that is particularly suitable for iterative and incremental development of the tasks. The proposed framework is based on the idea of partial fine-tuning, i.e. only fine-tune some top layers of BERT while keep the other layers frozen. For each task, we train independently a single-task (ST) model using partial fine-tuning. Then we compress the task-specific layers in each ST model using knowledge distillation. Those compressed ST models are finally merged into one MT model so that the frozen layers of the former are shared across the tasks. We exemplify our approach on eight GLUE tasks, demonstrating that it is able to achieve both strong performance and efficiency. We have implemented our method in the utterance understanding system of XiaoAI, a commercial AI assistant developed by Xiaomi. We estimate that our model reduces the overall serving cost by 86%.

arXiv:2107.04746공식 코드 · Papers with Code

Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy Annotations

Presence of noise in the labels of large scale facial expression datasets has been a key challenge towards Facial Expression Recognition (FER) in the wild. During early learning stage, deep networks fit on clean data. Then, eventually, they start overfitting on noisy labels due to their memorization ability, which limits FER performance. This work proposes an effective training strategy in the presence of noisy labels, called as Consensual Collaborative Training (CCT) framework. CCT co-trains three networks jointly using a convex combination of supervision loss and consistency loss, without making any assumption about the noise distribution. A dynamic transition mechanism is used to move from supervision loss in early learning to consistency loss for consensus of predictions among networks in the later stage. Inference is done using a single network based on a simple knowledge distillation scheme. Effectiveness of the proposed framework is demonstrated on synthetic as well as real noisy FER datasets. In addition, a large test subset of around 5K images is annotated from the FEC dataset using crowd wisdom of 16 different annotators and reliable labels are inferred. CCT is also validated on it. State-of-the-art performance is reported on the benchmark FER datasets RAFDB (90.84%) FERPlus (89.99%) and AffectNet (66%). Our codes are available at https://github.com/1980x/CCT.

arXiv:2107.03225공식 코드 · Papers with Code

Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image Classification

The amount of medical images for training deep classification models is typically very scarce, making these deep models prone to overfit the training data. Studies showed that knowledge distillation (KD), especially the mean-teacher framework which is more robust to perturbations, can help mitigate the over-fitting effect. However, directly transferring KD from computer vision to medical image classification yields inferior performance as medical images suffer from higher intra-class variance and class imbalance. To address these issues, we propose a novel Categorical Relation-preserving Contrastive Knowledge Distillation (CRCKD) algorithm, which takes the commonly used mean-teacher model as the supervisor. Specifically, we propose a novel Class-guided Contrastive Distillation (CCD) module to pull closer positive image pairs from the same class in the teacher and student models, while pushing apart negative image pairs from different classes. With this regularization, the feature distribution of the student model shows higher intra-class similarity and inter-class variance. Besides, we propose a Categorical Relation Preserving (CRP) loss to distill the teacher's relational knowledge in a robust and class-balanced manner. With the contribution of the CCD and CRP, our CRCKD algorithm can distill the relational knowledge more comprehensively. Extensive experiments on the HAM10000 and APTOS datasets demonstrate the superiority of the proposed CRCKD method.

arXiv:2107.02681공식 코드 · Papers with Code

VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer

Since visual perception can give rich information beyond text descriptions for world understanding, there has been increasing interest in leveraging visual grounding for language learning. Recently, vokenization (Tan and Bansal, 2020) has attracted attention by using the predictions of a text-to-image retrieval model as labels for language model supervision. Despite its success, the method suffers from approximation error of using finite image labels and the lack of vocabulary diversity of a small image-text dataset. To overcome these limitations, we present VidLanKD, a video-language knowledge distillation method for improving language understanding. We train a multi-modal teacher model on a video-text dataset, and then transfer its knowledge to a student language model with a text dataset. To avoid approximation error, we propose to use different knowledge distillation objectives. In addition, the use of a large-scale video-text dataset helps learn diverse and richer vocabularies. In our experiments, VidLanKD achieves consistent improvements over text-only language models and vokenization models, on several downstream language understanding tasks including GLUE, SQuAD, and SWAG. We also demonstrate the improved world knowledge, physical reasoning, and temporal reasoning capabilities of our model by evaluating on the GLUE-diagnostics, PIQA, and TRACIE datasets. Lastly, we present comprehensive ablation studies as well as visualizations of the learned text-to-video grounding results of our teacher and student language models. Our code and models are available at: https://github.com/zinengtang/VidLanKD

arXiv:2107.01776공식 코드 · Papers with Code

Continual Contrastive Learning for Image Classification

Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are suffering from a catastrophic forgetting problem, which is not studied extensively. In this paper, we make the first attempt to tackle the catastrophic forgetting problem in the mainstream self-supervised methods, i.e., contrastive learning methods. Specifically, we first develop a rehearsal-based framework combined with a novel sampling strategy and a self-supervised knowledge distillation to transfer information over time efficiently. Then, we propose an extra sample queue to help the network separate the feature representations of old and new data in the embedding space. Experimental results show that compared with the naive self-supervised baseline, which learns tasks one by one without taking any technique, we improve the image classification accuracy by 1.60% on CIFAR-100, 2.86% on ImageNet-Sub, and 1.29% on ImageNet-Full under 10 incremental steps setting. Our code will be available at https://github.com/VDIGPKU/ContinualContrastiveLearning.

arXiv:2107.01354공식 코드 · Papers with Code

Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural Networks

In spite of the great success of deep learning technologies, training and delivery of a practically serviceable model is still a highly time-consuming process. Furthermore, a resulting model is usually too generic and heavyweight, and hence essentially goes through another expensive model compression phase to fit in a resource-limited device like embedded systems. Inspired by the fact that a machine learning task specifically requested by mobile users is often much simpler than it is supported by a massive generic model, this paper proposes a framework, called Pool of Experts (PoE), that instantly builds a lightweight and task-specific model without any training process. For a realtime model querying service, PoE first extracts a pool of primitive components, called experts, from a well-trained and sufficiently generic network by exploiting a novel conditional knowledge distillation method, and then performs our train-free knowledge consolidation to quickly combine necessary experts into a lightweight network for a target task. Thanks to this train-free property, in our thorough empirical study, PoE can build a fairly accurate yet compact model in a realtime manner, whereas it takes a few minutes per query for the other training methods to achieve a similar level of the accuracy.

arXiv:2107.01349공식 코드 · Papers with Code

Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Network

Continual learning has been a major problem in the deep learning community, where the main challenge is how to effectively learn a series of newly arriving tasks without forgetting the knowledge of previous tasks. Initiated by Learning without Forgetting (LwF), many of the existing works report that knowledge distillation is effective to preserve the previous knowledge, and hence they commonly use a soft label for the old task, namely a knowledge distillation (KD) loss, together with a class label for the new task, namely a cross entropy (CE) loss, to form a composite loss for a single neural network. However, this approach suffers from learning the knowledge by a CE loss as a KD loss often more strongly influences the objective function when they are in a competitive situation within a single network. This could be a critical problem particularly in a class incremental scenario, where the knowledge across tasks as well as within the new task, both of which can only be acquired by a CE loss, is essentially learned due to the existence of a unified classifier. In this paper, we propose a novel continual learning method, called Split-and-Bridge, which can successfully address the above problem by partially splitting a neural network into two partitions for training the new task separated from the old task and re-connecting them for learning the knowledge across tasks. In our thorough experimental analysis, our Split-and-Bridge method outperforms the state-of-the-art competitors in KD-based continual learning.

arXiv:2107.00411공식 코드 · Papers with Code

Knowledge Distillation for Quality Estimation

Quality Estimation (QE) is the task of automatically predicting Machine Translation quality in the absence of reference translations, making it applicable in real-time settings, such as translating online social media conversations. Recent success in QE stems from the use of multilingual pre-trained representations, where very large models lead to impressive results. However, the inference time, disk and memory requirements of such models do not allow for wide usage in the real world. Models trained on distilled pre-trained representations remain prohibitively large for many usage scenarios. We instead propose to directly transfer knowledge from a strong QE teacher model to a much smaller model with a different, shallower architecture. We show that this approach, in combination with data augmentation, leads to light-weight QE models that perform competitively with distilled pre-trained representations with 8x fewer parameters.

arXiv:2107.00181공식 코드 · Papers with Code

Revisiting Knowledge Distillation: An Inheritance and Exploration Framework

Knowledge Distillation (KD) is a popular technique to transfer knowledge from a teacher model or ensemble to a student model. Its success is generally attributed to the privileged information on similarities/consistency between the class distributions or intermediate feature representations of the teacher model and the student model. However, directly pushing the student model to mimic the probabilities/features of the teacher model to a large extent limits the student model in learning undiscovered knowledge/features. In this paper, we propose a novel inheritance and exploration knowledge distillation framework (IE-KD), in which a student model is split into two parts - inheritance and exploration. The inheritance part is learned with a similarity loss to transfer the existing learned knowledge from the teacher model to the student model, while the exploration part is encouraged to learn representations different from the inherited ones with a dis-similarity loss. Our IE-KD framework is generic and can be easily combined with existing distillation or mutual learning methods for training deep neural networks. Extensive experiments demonstrate that these two parts can jointly push the student model to learn more diversified and effective representations, and our IE-KD can be a general technique to improve the student network to achieve SOTA performance. Furthermore, by applying our IE-KD to the training of two networks, the performance of both can be improved w.r.t. deep mutual learning. The code and models of IE-KD will be make publicly available at https://github.com/yellowtownhz/IE-KD.

arXiv:2106.14275공식 코드 · Papers with Code

Learning without Forgetting for 3D Point Cloud Objects

When we fine-tune a well-trained deep learning model for a new set of classes, the network learns new concepts but gradually forgets the knowledge of old training. In some real-life applications, we may be interested in learning new classes without forgetting the capability of previous experience. Such learning without forgetting problem is often investigated using 2D image recognition tasks. In this paper, considering the growth of depth camera technology, we address the same problem for the 3D point cloud object data. This problem becomes more challenging in the 3D domain than 2D because of the unavailability of large datasets and powerful pretrained backbone models. We investigate knowledge distillation techniques on 3D data to reduce catastrophic forgetting of the previous training. Moreover, we improve the distillation process by using semantic word vectors of object classes. We observe that exploring the interrelation of old and new knowledge during training helps to learn new concepts without forgetting old ones. Experimenting on three 3D point cloud recognition backbones (PointNet, DGCNN, and PointConv) and synthetic (ModelNet40, ModelNet10) and real scanned (ScanObjectNN) datasets, we establish new baseline results on learning without forgetting for 3D data. This research will instigate many future works in this area.

arXiv:2106.13266공식 코드 · Papers with Code

DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval

In this paper, we address the problem of high performance and computationally efficient content-based video retrieval in large-scale datasets. Current methods typically propose either: (i) fine-grained approaches employing spatio-temporal representations and similarity calculations, achieving high performance at a high computational cost or (ii) coarse-grained approaches representing/indexing videos as global vectors, where the spatio-temporal structure is lost, providing low performance but also having low computational cost. In this work, we propose a Knowledge Distillation framework, called Distill-and-Select (DnS), that starting from a well-performing fine-grained Teacher Network learns: a) Student Networks at different retrieval performance and computational efficiency trade-offs and b) a Selector Network that at test time rapidly directs samples to the appropriate student to maintain both high retrieval performance and high computational efficiency. We train several students with different architectures and arrive at different trade-offs of performance and efficiency, i.e., speed and storage requirements, including fine-grained students that store/index videos using binary representations. Importantly, the proposed scheme allows Knowledge Distillation in large, unlabelled datasets -- this leads to good students. We evaluate DnS on five public datasets on three different video retrieval tasks and demonstrate a) that our students achieve state-of-the-art performance in several cases and b) that the DnS framework provides an excellent trade-off between retrieval performance, computational speed, and storage space. In specific configurations, the proposed method achieves similar mAP with the teacher but is 20 times faster and requires 240 times less storage space. The collected dataset and implementation are publicly available: https://github.com/mever-team/distill-and-select.