PyTorchKR Papers

최신 논문

총 4,526편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2112.09445공식 코드 · Papers with Code

Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation

Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts than supervised "gold" labels. Previous works, such as CLIP, use InfoNCE loss to train a model to predict the pairing between images and text captions. CLIP, however, is data hungry and requires more than 400M image-text pairs for training. The inefficiency can be partially attributed to the fact that the image-text pairs are noisy. To address this, we propose OTTER (Optimal TransporT distillation for Efficient zero-shot Recognition), which uses online entropic optimal transport to find a soft image-text match as labels for contrastive learning. Based on pretrained image and text encoders, models trained with OTTER achieve strong performance with only 3M image text pairs. Compared with InfoNCE loss, label smoothing, and knowledge distillation, OTTER consistently outperforms these baselines in zero shot evaluation on Google Open Images (19,958 classes) and multi-labeled ImageNet 10K (10032 classes) from Tencent ML-Images. Over 42 evaluations on 7 different dataset/architecture settings x 6 metrics, OTTER outperforms (32) or ties (2) all baselines in 34 of them.

arXiv:2112.11447

Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrix

In the context of multi-modality knowledge distillation research, the existing methods was mainly focus on the problem of only learning teacher final output. Thus, there are still deep differences between the teacher network and the student network. It is necessary to force the student network to learn the modality relationship information of the teacher network. To effectively exploit transfering knowledge from teachers to students, a novel modality relation distillation paradigm by modeling the relationship information among different modality are adopted, that is learning the teacher modality-level Gram Matrix.

arXiv:2112.09532공식 코드 · Papers with Code

Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition

Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth and imaging equipment are related to the image size. Therefore, we propose Pixel Distillation that extends knowledge distillation into the input level while simultaneously breaking architecture constraints. Such a scheme can achieve flexible cost control for deployment, as it allows the system to adjust both network architecture and image quality according to the overall requirement of resources. Specifically, we first propose an input spatial representation distillation (ISRD) mechanism to transfer spatial knowledge from large images to student's input module, which can facilitate stable knowledge transfer between CNN and ViT. Then, a Teacher-Assistant-Student (TAS) framework is further established to disentangle pixel distillation into the model compression stage and input compression stage, which significantly reduces the overall complexity of pixel distillation and the difficulty of distilling intermediate knowledge. Finally, we adapt pixel distillation to object detection via an aligned feature for preservation (AFP) strategy for TAS, which aligns output dimensions of detectors at each stage by manipulating features and anchors of the assistant. Comprehensive experiments on image classification and object detection demonstrate the effectiveness of our method. Code is available at https://github.com/gyguo/PixelDistillation.

arXiv:2112.09459

Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching

Current weakly supervised semantic segmentation (WSSS) frameworks usually contain the separated mask-refinement model and the main semantic region mining model. These approaches would contain redundant feature extraction backbones and biased learning objectives, making them computational complex yet sub-optimal to addressing the WSSS task. To solve this problem, this paper establishes a compact learning framework that embeds the classification and mask-refinement components into a unified deep model. With the shared feature extraction backbone, our model is able to facilitate knowledge sharing between the two components while preserving a low computational complexity. To encourage high-quality knowledge interaction, we propose a novel alternative self-dual teaching (ASDT) mechanism. Unlike the conventional distillation strategy, the knowledge of the two teacher branches in our model is alternatively distilled to the student branch by a Pulse Width Modulation (PWM), which generates PW wave-like selection signal to guide the knowledge distillation process. In this way, the student branch can help prevent the model from falling into local minimum solutions caused by the imperfect knowledge provided of either teacher branch. Comprehensive experiments on the PASCAL VOC 2012 and COCO-Stuff 10K demonstrate the effectiveness of the proposed alternative self-dual teaching mechanism as well as the new state-of-the-art performance of our approach.

arXiv:2112.09448

Distillation of Human-Object Interaction Contexts for Action Recognition

Modeling spatial-temporal relations is imperative for recognizing human actions, especially when a human is interacting with objects, while multiple objects appear around the human differently over time. Most existing action recognition models focus on learning overall visual cues of a scene but disregard informative fine-grained features, which can be captured by learning human-object relationships and interactions. In this paper, we learn human-object relationships by exploiting the interaction of their local and global contexts. We hence propose the Global-Local Interaction Distillation Network (GLIDN), learning human and object interactions through space and time via knowledge distillation for fine-grained scene understanding. GLIDN encodes humans and objects into graph nodes and learns local and global relations via graph attention network. The local context graphs learn the relation between humans and objects at a frame level by capturing their co-occurrence at a specific time step. The global relation graph is constructed based on the video-level of human and object interactions, identifying their long-term relations throughout a video sequence. More importantly, we investigate how knowledge from these graphs can be distilled to their counterparts for improving human-object interaction (HOI) recognition. We evaluate our model by conducting comprehensive experiments on two datasets including Charades and CAD-120 datasets. We have achieved better results than the baselines and counterpart approaches.

arXiv:2112.08185공식 코드 · Papers with Code

Learning Cross-Lingual IR from an English Retriever

We present DR.DECR (Dense Retrieval with Distillation-Enhanced Cross-Lingual Representation), a new cross-lingual information retrieval (CLIR) system trained using multi-stage knowledge distillation (KD). The teacher of DR.DECR relies on a highly effective but computationally expensive two-stage inference process consisting of query translation and monolingual IR, while the student, DR.DECR, executes a single CLIR step. We teach DR.DECR powerful multilingual representations as well as CLIR by optimizing two corresponding KD objectives. Learning useful representations of non-English text from an English-only retriever is accomplished through a cross-lingual token alignment algorithm that relies on the representation capabilities of the underlying multilingual encoders. In both in-domain and zero-shot out-of-domain evaluation, DR.DECR demonstrates far superior accuracy over direct fine-tuning with labeled CLIR data. It is also the best single-model retriever on the XOR-TyDi benchmark at the time of this writing.

arXiv:2112.07648공식 코드 · Papers with Code

On the Use of External Data for Spoken Named Entity Recognition

Spoken language understanding (SLU) tasks involve mapping from speech audio signals to semantic labels. Given the complexity of such tasks, good performance might be expected to require large labeled datasets, which are difficult to collect for each new task and domain. However, recent advances in self-supervised speech representations have made it feasible to consider learning SLU models with limited labeled data. In this work we focus on low-resource spoken named entity recognition (NER) and address the question: Beyond self-supervised pre-training, how can we use external speech and/or text data that are not annotated for the task? We draw on a variety of approaches, including self-training, knowledge distillation, and transfer learning, and consider their applicability to both end-to-end models and pipeline (speech recognition followed by text NER model) approaches. We find that several of these approaches improve performance in resource-constrained settings beyond the benefits from pre-trained representations alone. Compared to prior work, we find improved F1 scores of up to 16%. While the best baseline model is a pipeline approach, the best performance when using external data is ultimately achieved by an end-to-end model. We provide detailed comparisons and analyses, showing for example that end-to-end models are able to focus on the more NER-specific words.

arXiv:2112.07074

Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text

In this paper, we explore the possibility of building a unified foundation model that can be adapted to both vision-only and text-only tasks. Starting from BERT and ViT, we design a unified transformer consisting of modality-specific tokenizers, a shared transformer encoder, and task-specific output heads. To efficiently pre-train the proposed model jointly on unpaired images and text, we propose two novel techniques: (i) We employ the separately-trained BERT and ViT models as teachers and apply knowledge distillation to provide additional, accurate supervision signals for the joint training; (ii) We propose a novel gradient masking strategy to balance the parameter updates from the image and text pre-training losses. We evaluate the jointly pre-trained transformer by fine-tuning it on image classification tasks and natural language understanding tasks, respectively. The experiments show that the resultant unified foundation transformer works surprisingly well on both the vision-only and text-only tasks, and the proposed knowledge distillation and gradient masking strategy can effectively lift the performance to approach the level of separately-trained models.

arXiv:2112.07252공식 코드 · Papers with Code

A Deep Knowledge Distillation framework for EEG assisted enhancement of single-lead ECG based sleep staging

Automatic Sleep Staging study is presently done with the help of Electroencephalogram (EEG) signals. Recently, Deep Learning (DL) based approaches have enabled significant progress in this area, allowing for near-human accuracy in automated sleep staging. However, EEG based sleep staging requires an extensive as well as an expensive clinical setup. Moreover, the requirement of an expert for setup and the added inconvenience to the subject under study renders it unfavourable in a point of care context. Electrocardiogram (ECG), an unobtrusive alternative to EEG, is more suitable, but its performance, unsurprisingly, remains sub-par compared to EEG-based sleep staging. Naturally, it would be helpful to transfer knowledge from EEG to ECG, ultimately enhancing the model's performance on ECG based inputs. Knowledge Distillation (KD) is a renowned concept in DL that looks to transfer knowledge from a better but potentially more cumbersome teacher model to a compact student model. Building on this concept, we propose a cross-modal KD framework to improve ECG-based sleep staging performance with assistance from features learned through models trained on EEG. Additionally, we also conducted multiple experiments on the individual components of the proposed model to get better insight into the distillation approach. Data of 200 subjects from the Montreal Archive of Sleep Studies (MASS) was utilized for our study. The proposed model showed a 14.3\% and 13.4\% increase in weighted-F1-score in 4-class and 3-class sleep staging, respectively. This demonstrates the viability of KD for performance improvement of single-channel ECG based sleep staging in 4-class(W-L-D-R) and 3-class(W-N-R) classification.

arXiv:2112.06460공식 코드 · Papers with Code

Improving Sequential Recommendations via Bidirectional Temporal Data Augmentation with Pre-training

Sequential recommendation systems are integral to discerning temporal user preferences. Yet, the task of learning from abbreviated user interaction sequences poses a notable challenge. Data augmentation has been identified as a potent strategy to enhance the informational richness of these sequences. Traditional augmentation techniques, such as item randomization, may disrupt the inherent temporal dynamics. Although recent advancements in reverse chronological pseudo-item generation have shown promise, they can introduce temporal discrepancies when assessed in a natural chronological context. In response, we introduce a sophisticated approach, Bidirectional temporal data Augmentation with pre-training (BARec). Our approach leverages bidirectional temporal augmentation and knowledge-enhanced fine-tuning to synthesize authentic pseudo-prior items that retain user preferences and capture deeper item semantic correlations, thus boosting the model's expressive power. Our comprehensive experimental analysis on five benchmark datasets confirms the superiority of BARec across both short and elongated sequence contexts. Moreover, theoretical examination and case study offer further insight into the model's logical processes and interpretability. The source code for our study is publicly available at https://github.com/juyongjiang/BARec.

arXiv:2112.06632

Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation

Unsupervised domain adaptive person re-identification (ReID) has been extensively investigated to mitigate the adverse effects of domain gaps. Those works assume the target domain data can be accessible all at once. However, for the real-world streaming data, this hinders the timely adaptation to changing data statistics and sufficient exploitation of increasing samples. In this paper, to address more practical scenarios, we propose a new task, Lifelong Unsupervised Domain Adaptive (LUDA) person ReID. This is challenging because it requires the model to continuously adapt to unlabeled data in the target environments while alleviating catastrophic forgetting for such a fine-grained person retrieval task. We design an effective scheme for this task, dubbed CLUDA-ReID, where the anti-forgetting is harmoniously coordinated with the adaptation. Specifically, a meta-based Coordinated Data Replay strategy is proposed to replay old data and update the network with a coordinated optimization direction for both adaptation and memorization. Moreover, we propose Relational Consistency Learning for old knowledge distillation/inheritance in line with the objective of retrieval-based tasks. We set up two evaluation settings to simulate the practical application scenarios. Extensive experiments demonstrate the effectiveness of our CLUDA-ReID for both scenarios with stationary target streams and scenarios with dynamic target streams.

arXiv:2112.06253공식 코드 · Papers with Code

Up to 100$\times$ Faster Data-free Knowledge Distillation

Data-free knowledge distillation (DFKD) has recently been attracting increasing attention from research communities, attributed to its capability to compress a model only using synthetic data. Despite the encouraging results achieved, state-of-the-art DFKD methods still suffer from the inefficiency of data synthesis, making the data-free training process extremely time-consuming and thus inapplicable for large-scale tasks. In this work, we introduce an efficacious scheme, termed as FastDFKD, that allows us to accelerate DFKD by a factor of orders of magnitude. At the heart of our approach is a novel strategy to reuse the shared common features in training data so as to synthesize different data instances. Unlike prior methods that optimize a set of data independently, we propose to learn a meta-synthesizer that seeks common features as the initialization for the fast data synthesis. As a result, FastDFKD achieves data synthesis within only a few steps, significantly enhancing the efficiency of data-free training. Experiments over CIFAR, NYUv2, and ImageNet demonstrate that the proposed FastDFKD achieves 10$\times$ and even 100$\times$ acceleration while preserving performances on par with state of the art. Code is available at \url{https://github.com/zju-vipa/Fast-Datafree}.

arXiv:2112.05646공식 코드 · Papers with Code

Mask-invariant Face Recognition through Template-level Knowledge Distillation

The emergence of the global COVID-19 pandemic poses new challenges for biometrics. Not only are contactless biometric identification options becoming more important, but face recognition has also recently been confronted with the frequent wearing of masks. These masks affect the performance of previous face recognition systems, as they hide important identity information. In this paper, we propose a mask-invariant face recognition solution (MaskInv) that utilizes template-level knowledge distillation within a training paradigm that aims at producing embeddings of masked faces that are similar to those of non-masked faces of the same identities. In addition to the distilled knowledge, the student network benefits from additional guidance by margin-based identity classification loss, ElasticFace, using masked and non-masked faces. In a step-wise ablation study on two real masked face databases and five mainstream databases with synthetic masks, we prove the rationalization of our MaskInv approach. Our proposed solution outperforms previous state-of-the-art (SOTA) academic solutions in the recent MFRC-21 challenge in both scenarios, masked vs masked and masked vs non-masked, and also outperforms the previous solution on the MFR2 dataset. Furthermore, we demonstrate that the proposed model can still perform well on unmasked faces with only a minor loss in verification performance. The code, the trained models, as well as the evaluation protocol on the synthetically masked data are publicly available: https://github.com/fdbtrs/Masked-Face-Recognition-KD.

arXiv:2112.05638

DistilCSE: Effective Knowledge Distillation For Contrastive Sentence Embeddings

Large-scale contrastive learning models can learn very informative sentence embeddings, but are hard to serve online due to the huge model size. Therefore, they often play the role of "teacher", transferring abilities to small "student" models through knowledge distillation. However, knowledge distillation inevitably brings some drop in embedding effect. To tackle that, we propose an effective knowledge distillation framework for contrastive sentence embeddings, termed DistilCSE. It first applies knowledge distillation on a large amount of unlabeled data, and then fine-tunes student models through contrastive learning on limited labeled data. To achieve better distillation results, we further propose Contrastive Knowledge Distillation (CKD). CKD uses InfoNCE as the loss function in knowledge distillation, enhancing the objective consistency among teacher model training, knowledge distillation, and student model fine-tuning. Extensive experiments show that student models trained with the proposed DistilCSE and CKD suffer from little or even no performance decrease and consistently outperform the corresponding counterparts of the same parameter size. Impressively, our 110M student model outperforms the latest state-of-the-art model, i.e., Sentence-T5 (11B), with only 1% parameters and 0.25% unlabeled data.

arXiv:2112.05364공식 코드 · Papers with Code

Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation

The multi-head self-attention mechanism of the transformer model has been thoroughly investigated recently. In one vein of study, researchers are interested in understanding why and how transformers work. In another vein, researchers propose new attention augmentation methods to make transformers more accurate, efficient and interpretable. In this paper, we combine these two lines of research in a human-in-the-loop pipeline to first discover important task-specific attention patterns. Then those patterns are injected, not only to smaller models, but also to the original model. The benefits of our pipeline and discovered patterns are demonstrated in two case studies with extractive summarization and topic segmentation. After discovering interpretable patterns in BERT-based models fine-tuned for the two downstream tasks, experiments indicate that when we inject the patterns into attention heads, the models show considerable improvements in accuracy and efficiency.

arXiv:2112.04840

Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation

Knowledge Distillation (KD) is a widely-used technology to inherit information from cumbersome teacher models to compact student models, consequently realizing model compression and acceleration. Compared with image classification, object detection is a more complex task, and designing specific KD methods for object detection is non-trivial. In this work, we elaborately study the behaviour difference between the teacher and student detection models, and obtain two intriguing observations: First, the teacher and student rank their detected candidate boxes quite differently, which results in their precision discrepancy. Second, there is a considerable gap between the feature response differences and prediction differences between teacher and student, indicating that equally imitating all the feature maps of the teacher is the sub-optimal choice for improving the student's accuracy. Based on the two observations, we propose Rank Mimicking (RM) and Prediction-guided Feature Imitation (PFI) for distilling one-stage detectors, respectively. RM takes the rank of candidate boxes from teachers as a new form of knowledge to distill, which consistently outperforms the traditional soft label distillation. PFI attempts to correlate feature differences with prediction differences, making feature imitation directly help to improve the student's accuracy. On MS COCO and PASCAL VOC benchmarks, extensive experiments are conducted on various detectors with different backbones to validate the effectiveness of our method. Specifically, RetinaNet with ResNet50 achieves 40.4% mAP in MS COCO, which is 3.5% higher than its baseline, and also outperforms previous KD methods.

arXiv:2112.05005

Mutual Adversarial Training: Learning together is better than going alone

Recent studies have shown that robustness to adversarial attacks can be transferred across networks. In other words, we can make a weak model more robust with the help of a strong teacher model. We ask if instead of learning from a static teacher, can models "learn together" and "teach each other" to achieve better robustness? In this paper, we study how interactions among models affect robustness via knowledge distillation. We propose mutual adversarial training (MAT), in which multiple models are trained together and share the knowledge of adversarial examples to achieve improved robustness. MAT allows robust models to explore a larger space of adversarial samples, and find more robust feature spaces and decision boundaries. Through extensive experiments on CIFAR-10 and CIFAR-100, we demonstrate that MAT can effectively improve model robustness and outperform state-of-the-art methods under white-box attacks, bringing $\sim$8% accuracy gain to vanilla adversarial training (AT) under PGD-100 attacks. In addition, we show that MAT can also mitigate the robustness trade-off among different perturbation types, bringing as much as 13.1% accuracy gain to AT baselines against the union of $l_\infty$, $l_2$ and $l_1$ attacks. These results show the superiority of the proposed method and demonstrate that collaborative learning is an effective strategy for designing robust models.

arXiv:2112.04174

Boosting Contrastive Learning with Relation Knowledge Distillation

While self-supervised representation learning (SSL) has proved to be effective in the large model, there is still a huge gap between the SSL and supervised method in the lightweight model when following the same solution. We delve into this problem and find that the lightweight model is prone to collapse in semantic space when simply performing instance-wise contrast. To address this issue, we propose a relation-wise contrastive paradigm with Relation Knowledge Distillation (ReKD). We introduce a heterogeneous teacher to explicitly mine the semantic information and transferring a novel relation knowledge to the student (lightweight model). The theoretical analysis supports our main concern about instance-wise contrast and verify the effectiveness of our relation-wise contrastive learning. Extensive experimental results also demonstrate that our method achieves significant improvements on multiple lightweight models. Particularly, the linear evaluation on AlexNet obviously improves the current state-of-art from 44.7% to 50.1%, which is the first work to get close to the supervised 50.5%. Code will be made available.

arXiv:2112.04011공식 코드 · Papers with Code

Auxiliary Learning for Self-Supervised Video Representation via Similarity-based Knowledge Distillation

Despite the outstanding success of self-supervised pretraining methods for video representation learning, they generalise poorly when the unlabeled dataset for pretraining is small or the domain difference between unlabelled data in source task (pretraining) and labeled data in target task (finetuning) is significant. To mitigate these issues, we propose a novel approach to complement self-supervised pretraining via an auxiliary pretraining phase, based on knowledge similarity distillation, auxSKD, for better generalisation with a significantly smaller amount of video data, e.g. Kinetics-100 rather than Kinetics-400. Our method deploys a teacher network that iteratively distills its knowledge to the student model by capturing the similarity information between segments of unlabelled video data. The student model meanwhile solves a pretext task by exploiting this prior knowledge. We also introduce a novel pretext task, Video Segment Pace Prediction or VSPP, which requires our model to predict the playback speed of a randomly selected segment of the input video to provide more reliable self-supervised representations. Our experimental results show superior results to the state of the art on both UCF101 and HMDB51 datasets when pretraining on K100 in apple-to-apple comparisons. Additionally, we show that our auxiliary pretraining, auxSKD, when added as an extra pretraining phase to recent state of the art self-supervised methods (i.e. VCOP, VideoPace, and RSPNet), improves their results on UCF101 and HMDB51. Our code is available at https://github.com/Plrbear/auxSKD.

arXiv:2112.03473공식 코드 · Papers with Code

Improving Neural Cross-Lingual Summarization via Employing Optimal Transport Distance for Knowledge Distillation

Current state-of-the-art cross-lingual summarization models employ multi-task learning paradigm, which works on a shared vocabulary module and relies on the self-attention mechanism to attend among tokens in two languages. However, correlation learned by self-attention is often loose and implicit, inefficient in capturing crucial cross-lingual representations between languages. The matter worsens when performing on languages with separate morphological or structural features, making the cross-lingual alignment more challenging, resulting in the performance drop. To overcome this problem, we propose a novel Knowledge-Distillation-based framework for Cross-Lingual Summarization, seeking to explicitly construct cross-lingual correlation by distilling the knowledge of the monolingual summarization teacher into the cross-lingual summarization student. Since the representations of the teacher and the student lie on two different vector spaces, we further propose a Knowledge Distillation loss using Sinkhorn Divergence, an Optimal-Transport distance, to estimate the discrepancy between those teacher and student representations. Due to the intuitively geometric nature of Sinkhorn Divergence, the student model can productively learn to align its produced cross-lingual hidden states with monolingual hidden states, hence leading to a strong correlation between distant languages. Experiments on cross-lingual summarization datasets in pairs of distant languages demonstrate that our method outperforms state-of-the-art models under both high and low-resourced settings.