PyTorchKR Papers

최신 논문

총 6,725편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2302.12028

Novel Class Discovery: an Introduction and Key Concepts

Novel Class Discovery (NCD) is a growing field where we are given during training a labeled set of known classes and an unlabeled set of different classes that must be discovered. In recent years, many methods have been proposed to address this problem, and the field has begun to mature. In this paper, we provide a comprehensive survey of the state-of-the-art NCD methods. We start by formally defining the NCD problem and introducing important notions. We then give an overview of the different families of approaches, organized by the way they transfer knowledge from the labeled set to the unlabeled set. We find that they either learn in two stages, by first extracting knowledge from the labeled data only and then applying it to the unlabeled data, or in one stage by conjointly learning on both sets. For each family, we describe their general principle and detail a few representative methods. Then, we briefly introduce some new related tasks inspired by the increasing number of NCD works. We also present some common tools and techniques used in NCD, such as pseudo labeling, self-supervised learning and contrastive learning. Finally, to help readers unfamiliar with the NCD problem differentiate it from other closely related domains, we summarize some of the closest areas of research and discuss their main differences.

arXiv:2302.12248공식 코드 · Papers with Code

Learning Visual Representations via Language-Guided Sampling

Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an alternative approach to visual representation learning: using language similarity to sample semantically similar image pairs for contrastive learning. Our approach diverges from image-based contrastive learning by sampling view pairs using language similarity instead of hand-crafted augmentations or learned clusters. Our approach also differs from image-text contrastive learning by relying on pre-trained language models to guide the learning rather than directly minimizing a cross-modal loss. Through a series of experiments, we show that language-guided learning yields better features than image-based and image-text representation learning approaches.

arXiv:2302.12052

Attention Mechanism for Contrastive Learning in GAN-based Image-to-Image Translation

Using real road testing to optimize autonomous driving algorithms is time-consuming and capital-intensive. To solve this problem, we propose a GAN-based model that is capable of generating high-quality images across different domains. We further leverage Contrastive Learning to train the model in a self-supervised way using image data acquired in the real world using real sensors and simulated images from 3D games. In this paper, we also apply an Attention Mechanism module to emphasize features that contain more information about the source domain according to their measurement of significance. Finally, the generated images are used as datasets to train neural networks to perform a variety of downstream tasks to verify that the approach can fill in the gaps between the virtual and real worlds.

arXiv:2302.12007

DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition

In this work, we propose a new Dual Min-Max Games (DMMG) based self-supervised skeleton action recognition method by augmenting unlabeled data in a contrastive learning framework. Our DMMG consists of a viewpoint variation min-max game and an edge perturbation min-max game. These two min-max games adopt an adversarial paradigm to perform data augmentation on the skeleton sequences and graph-structured body joints, respectively. Our viewpoint variation min-max game focuses on constructing various hard contrastive pairs by generating skeleton sequences from various viewpoints. These hard contrastive pairs help our model learn representative action features, thus facilitating model transfer to downstream tasks. Moreover, our edge perturbation min-max game specializes in building diverse hard contrastive samples through perturbing connectivity strength among graph-based body joints. The connectivity-strength varying contrastive pairs enable the model to capture minimal sufficient information of different actions, such as representative gestures for an action while preventing the model from overfitting. By fully exploiting the proposed DMMG, we can generate sufficient challenging contrastive pairs and thus achieve discriminative action feature representations from unlabeled skeleton data in a self-supervised manner. Extensive experiments demonstrate that our method achieves superior results under various evaluation protocols on widely-used NTU-RGB+D and NTU120-RGB+D datasets.

arXiv:2302.11705공식 코드 · Papers with Code

ACE: Zero-Shot Image to Image Translation via Pretrained Auto-Contrastive-Encoder

Image-to-image translation is a fundamental task in computer vision. It transforms images from one domain to images in another domain so that they have particular domain-specific characteristics. Most prior works train a generative model to learn the mapping from a source domain to a target domain. However, learning such mapping between domains is challenging because data from different domains can be highly unbalanced in terms of both quality and quantity. To address this problem, we propose a new approach to extract image features by learning the similarities and differences of samples within the same data distribution via a novel contrastive learning framework, which we call Auto-Contrastive-Encoder (ACE). ACE learns the content code as the similarity between samples with the same content information and different style perturbations. The design of ACE enables us to achieve zero-shot image-to-image translation with no training on image translation tasks for the first time. Moreover, our learning method can learn the style features of images on different domains effectively. Consequently, our model achieves competitive results on multimodal image translation tasks with zero-shot learning as well. Additionally, we demonstrate the potential of our method in transfer learning. With fine-tuning, the quality of translated images improves in unseen domains. Even though we use contrastive learning, all of our training can be performed on a single GPU with the batch size of 8.

arXiv:2302.11205

Contrastive Representation Learning for Acoustic Parameter Estimation

A study is presented in which a contrastive learning approach is used to extract low-dimensional representations of the acoustic environment from single-channel, reverberant speech signals. Convolution of room impulse responses (RIRs) with anechoic source signals is leveraged as a data augmentation technique that offers considerable flexibility in the design of the upstream task. We evaluate the embeddings across three different downstream tasks, which include the regression of acoustic parameters reverberation time RT60 and clarity index C50, and the classification into small and large rooms. We demonstrate that the learned representations generalize well to unseen data and perform similarly to a fully-supervised baseline.

arXiv:2302.11084공식 코드 · Papers with Code

Test-Time Distribution Normalization for Contrastively Learned Vision-language Models

Advances in the field of vision-language contrastive learning have made it possible for many downstream applications to be carried out efficiently and accurately by simply taking the dot product between image and text representations. One of the most representative approaches proposed recently known as CLIP has garnered widespread adoption due to its effectiveness. CLIP is trained with an InfoNCE loss that takes into account both positive and negative samples to help learn a much more robust representation space. This paper reveals that the common downstream practice of taking a dot product is only a zeroth-order approximation of the optimization goal, resulting in a loss of information during test-time. Intuitively, since the model has been optimized based on the InfoNCE loss, test-time procedures should also be in alignment. The question lies in how one can retrieve any semblance of negative samples information during inference in a computationally efficient way. To this end, we propose Distribution Normalization (DN), where we approximate the mean representation of a batch of test samples and use such a mean to represent what would be analogous to negative samples in the InfoNCE loss. DN requires no retraining or fine-tuning and can be effortlessly applied during inference. Extensive experiments on a wide variety of downstream tasks exhibit a clear advantage of DN over the dot product on top of other existing test-time augmentation methods.

arXiv:2302.11557

K-Diag: Knowledge-enhanced Disease Diagnosis in Radiographic Imaging

In this paper, we consider the problem of disease diagnosis. Unlike the conventional learning paradigm that treats labels independently, we propose a knowledge-enhanced framework, that enables training visual representation with the guidance of medical domain knowledge. In particular, we make the following contributions: First, to explicitly incorporate experts' knowledge, we propose to learn a neural representation for the medical knowledge graph via contrastive learning, implicitly establishing relations between different medical concepts. Second, while training the visual encoder, we keep the parameters of the knowledge encoder frozen and propose to learn a set of prompt vectors for efficient adaptation. Third, we adopt a Transformer-based disease-query module for cross-model fusion, which naturally enables explainable diagnosis results via cross attention. To validate the effectiveness of our proposed framework, we conduct thorough experiments on three x-ray imaging datasets across different anatomy structures, showing our model is able to exploit the implicit relations between diseases/findings, thus is beneficial to the commonly encountered problem in the medical domain, namely, long-tailed and zero-shot recognition, which conventional methods either struggle or completely fail to realize.

arXiv:2302.11517공식 코드 · Papers with Code

A Global and Patch-wise Contrastive Loss for Accurate Automated Exudate Detection

Diabetic retinopathy (DR) is a leading global cause of blindness. Early detection of hard exudates plays a crucial role in identifying DR, which aids in treating diabetes and preventing vision loss. However, the unique characteristics of hard exudates, ranging from their inconsistent shapes to indistinct boundaries, pose significant challenges to existing segmentation techniques. To address these issues, we present a novel supervised contrastive learning framework to optimize hard exudate segmentation. Specifically, we introduce a patch-wise density contrasting scheme to distinguish between areas with varying lesion concentrations, and therefore improve the model's proficiency in segmenting small lesions. To handle the ambiguous boundaries, we develop a discriminative edge inspection module to dynamically analyze the pixels that lie around the boundaries and accurately delineate the exudates. Upon evaluation using the IDRiD dataset and comparison with state-of-the-art frameworks, our method exhibits its effectiveness and shows potential for computer-assisted hard exudate detection. The code to replicate experiments is available at github.com/wetang7/HECL/.

arXiv:2302.11461

Saliency Guided Contrastive Learning on Scene Images

Self-supervised learning holds promise in leveraging large numbers of unlabeled data. However, its success heavily relies on the highly-curated dataset, e.g., ImageNet, which still needs human cleaning. Directly learning representations from less-curated scene images is essential for pushing self-supervised learning to a higher level. Different from curated images which include simple and clear semantic information, scene images are more complex and mosaic because they often include complex scenes and multiple objects. Despite being feasible, recent works largely overlooked discovering the most discriminative regions for contrastive learning to object representations in scene images. In this work, we leverage the saliency map derived from the model's output during learning to highlight these discriminative regions and guide the whole contrastive learning. Specifically, the saliency map first guides the method to crop its discriminative regions as positive pairs and then reweighs the contrastive losses among different crops by its saliency scores. Our method significantly improves the performance of self-supervised learning on scene images by +1.1, +4.3, +2.2 Top1 accuracy in ImageNet linear evaluation, Semi-supervised learning with 1% and 10% ImageNet labels, respectively. We hope our insights on saliency maps can motivate future research on more general-purpose unsupervised representation learning from scene data.

arXiv:2302.10763

Contrastive Learning and the Emergence of Attributes Associations

In response to an object presentation, supervised learning schemes generally respond with a parsimonious label. Upon a similar presentation we humans respond again with a label, but are flooded, in addition, by a myriad of associations. A significant portion of these consist of the presented object attributes. Contrastive learning is a semi-supervised learning scheme based on the application of identity preserving transformations on the object input representations. It is conjectured in this work that these same applied transformations preserve, in addition to the identity of the presented object, also the identity of its semantically meaningful attributes. The corollary of this is that the output representations of such a contrastive learning scheme contain valuable information not only for the classification of the presented object, but also for the presence or absence decision of any attribute of interest. Simulation results which demonstrate this idea and the feasibility of this conjecture are presented.

arXiv:2302.10632공식 코드 · Papers with Code

Multi-Modal Self-Supervised Learning for Recommendation

The online emergence of multi-modal sharing platforms (eg, TikTok, Youtube) is powering personalized recommender systems to incorporate various modalities (eg, visual, textual and acoustic) into the latent user representations. While existing works on multi-modal recommendation exploit multimedia content features in enhancing item embeddings, their model representation capability is limited by heavy label reliance and weak robustness on sparse user behavior data. Inspired by the recent progress of self-supervised learning in alleviating label scarcity issue, we explore deriving self-supervision signals with effectively learning of modality-aware user preference and cross-modal dependencies. To this end, we propose a new Multi-Modal Self-Supervised Learning (MMSSL) method which tackles two key challenges. Specifically, to characterize the inter-dependency between the user-item collaborative view and item multi-modal semantic view, we design a modality-aware interactive structure learning paradigm via adversarial perturbations for data augmentation. In addition, to capture the effects that user's modality-aware interaction pattern would interweave with each other, a cross-modal contrastive learning approach is introduced to jointly preserve the inter-modal semantic commonality and user preference diversity. Experiments on real-world datasets verify the superiority of our method in offering great potential for multimedia recommendation over various state-of-the-art baselines. The implementation is released at: https://github.com/HKUDS/MMSSL.

arXiv:2302.10362공식 코드 · Papers with Code

Heterogeneous Social Event Detection via Hyperbolic Graph Representations

Social events reflect the dynamics of society and, here, natural disasters and emergencies receive significant attention. The timely detection of these events can provide organisations and individuals with valuable information to reduce or avoid losses. However, due to the complex heterogeneities of the content and structure of social media, existing models can only learn limited information; large amounts of semantic and structural information are ignored. In addition, due to high labour costs, it is rare for social media datasets to include high-quality labels, which also makes it challenging for models to learn information from social media. In this study, we propose two hyperbolic graph representation-based methods for detecting social events from heterogeneous social media environments. For cases where a dataset has labels, we designed a Hyperbolic Social Event Detection (HSED) model that converts complex social information into a unified social message graph. This model addresses the heterogeneity of social media, and, with this graph, the information in social media can be used to capture structural information based on the properties of hyperbolic space. For cases where the dataset is unlabelled, we designed an Unsupervised Hyperbolic Social Event Detection (UHSED). This model is based on the HSED model but includes graph contrastive learning to make it work in unlabelled scenarios. Extensive experiments demonstrate the superiority of the proposed approaches.

arXiv:2302.10305

Analyzing Multimodal Objectives Through the Lens of Generative Diffusion Guidance

Recent years have witnessed astonishing advances in the field of multimodal representation learning, with contrastive learning being the cornerstone for major breakthroughs. Latest works delivered further improvements by incorporating different objectives such as masked modeling and captioning into the frameworks, but our understanding on how these objectives facilitate learning remains vastly incomplete. In this paper, we leverage the fact that classifier-guided diffusion models generate images that reflect the semantic signals provided by the classifier to study the characteristics of multimodal learning objectives. Specifically, we compare contrastive, matching and captioning loss in terms of their semantic signals, and introduce a simple baseline that not only supports our analyses but also improves the quality of generative guidance in a straightforward manner.

arXiv:2302.10835

A General-Purpose Transferable Predictor for Neural Architecture Search

Understanding and modelling the performance of neural architectures is key to Neural Architecture Search (NAS). Performance predictors have seen widespread use in low-cost NAS and achieve high ranking correlations between predicted and ground truth performance in several NAS benchmarks. However, existing predictors are often designed based on network encodings specific to a predefined search space and are therefore not generalizable to other search spaces or new architecture families. In this paper, we propose a general-purpose neural predictor for NAS that can transfer across search spaces, by representing any given candidate Convolutional Neural Network (CNN) with a Computation Graph (CG) that consists of primitive operators. We further combine our CG network representation with Contrastive Learning (CL) and propose a graph representation learning procedure that leverages the structural information of unlabeled architectures from multiple families to train CG embeddings for our performance predictor. Experimental results on NAS-Bench-101, 201 and 301 demonstrate the efficacy of our scheme as we achieve strong positive Spearman Rank Correlation Coefficient (SRCC) on every search space, outperforming several Zero-Cost Proxies, including Synflow and Jacov, which are also generalizable predictors across search spaces. Moreover, when using our proposed general-purpose predictor in an evolutionary neural architecture search algorithm, we can find high-performance architectures on NAS-Bench-101 and find a MobileNetV3 architecture that attains 79.2% top-1 accuracy on ImageNet.

arXiv:2302.10698

Unpaired Translation from Semantic Label Maps to Images by Leveraging Domain-Specific Simulations

Photorealistic image generation from simulated label maps are necessitated in several contexts, such as for medical training in virtual reality. With conventional deep learning methods, this task requires images that are paired with semantic annotations, which typically are unavailable. We introduce a contrastive learning framework for generating photorealistic images from simulated label maps, by learning from unpaired sets of both. Due to potentially large scene differences between real images and label maps, existing unpaired image translation methods lead to artifacts of scene modification in synthesized images. We utilize simulated images as surrogate targets for a contrastive loss, while ensuring consistency by utilizing features from a reverse translation network. Our method enables bidirectional label-image translations, which is demonstrated in a variety of scenarios and datasets, including laparoscopy, ultrasound, and driving scenes. By comparing with state-of-the-art unpaired translation methods, our proposed method is shown to generate realistic and scene-accurate translations.

arXiv:2302.10633

Generalization Bounds for Adversarial Contrastive Learning

Deep networks are well-known to be fragile to adversarial attacks, and adversarial training is one of the most popular methods used to train a robust model. To take advantage of unlabeled data, recent works have applied adversarial training to contrastive learning (Adversarial Contrastive Learning; ACL for short) and obtain promising robust performance. However, the theory of ACL is not well understood. To fill this gap, we leverage the Rademacher complexity to analyze the generalization performance of ACL, with a particular focus on linear models and multi-layer neural networks under $\ell_p$ attack ($p \ge 1$). Our theory shows that the average adversarial risk of the downstream tasks can be upper bounded by the adversarial unsupervised risk of the upstream task. The experimental results validate our theory.

arXiv:2302.10501

Few-Shot Point Cloud Semantic Segmentation via Contrastive Self-Supervision and Multi-Resolution Attention

This paper presents an effective few-shot point cloud semantic segmentation approach for real-world applications. Existing few-shot segmentation methods on point cloud heavily rely on the fully-supervised pretrain with large annotated datasets, which causes the learned feature extraction bias to those pretrained classes. However, as the purpose of few-shot learning is to handle unknown/unseen classes, such class-specific feature extraction in pretrain is not ideal to generalize into new classes for few-shot learning. Moreover, point cloud datasets hardly have a large number of classes due to the annotation difficulty. To address these issues, we propose a contrastive self-supervision framework for few-shot learning pretrain, which aims to eliminate the feature extraction bias through class-agnostic contrastive supervision. Specifically, we implement a novel contrastive learning approach with a learnable augmentor for a 3D point cloud to achieve point-wise differentiation, so that to enhance the pretrain with managed overfitting through the self-supervision. Furthermore, we develop a multi-resolution attention module using both the nearest and farthest points to extract the local and global point information more effectively, and a center-concentrated multi-prototype is adopted to mitigate the intra-class sparsity. Comprehensive experiments are conducted to evaluate the proposed approach, which shows our approach achieves state-of-the-art performance. Moreover, a case study on practical CAM/CAD segmentation is presented to demonstrate the effectiveness of our approach for real-world applications.

arXiv:2302.10601

Few-shot Detection of Anomalies in Industrial Cyber-Physical System via Prototypical Network and Contrastive Learning

The rapid development of Industry 4.0 has amplified the scope and destructiveness of industrial Cyber-Physical System (CPS) by network attacks. Anomaly detection techniques are employed to identify these attacks and guarantee the normal operation of industrial CPS. However, it is still a challenging problem to cope with scenarios with few labeled samples. In this paper, we propose a few-shot anomaly detection model (FSL-PN) based on prototypical network and contrastive learning for identifying anomalies with limited labeled data from industrial CPS. Specifically, we design a contrastive loss to assist the training process of the feature extractor and learn more fine-grained features to improve the discriminative performance. Subsequently, to tackle the overfitting issue during classifying, we construct a robust cost function with a specific regularizer to enhance the generalization capability. Experimental results based on two public imbalanced datasets with few-shot settings show that the FSL-PN model can significantly improve F1 score and reduce false alarm rate (FAR) for identifying anomalous signals to guarantee the security of industrial CPS.

arXiv:2302.10447

Mask-guided BERT for Few Shot Text Classification

Transformer-based language models have achieved significant success in various domains. However, the data-intensive nature of the transformer architecture requires much labeled data, which is challenging in low-resource scenarios (i.e., few-shot learning (FSL)). The main challenge of FSL is the difficulty of training robust models on small amounts of samples, which frequently leads to overfitting. Here we present Mask-BERT, a simple and modular framework to help BERT-based architectures tackle FSL. The proposed approach fundamentally differs from existing FSL strategies such as prompt tuning and meta-learning. The core idea is to selectively apply masks on text inputs and filter out irrelevant information, which guides the model to focus on discriminative tokens that influence prediction results. In addition, to make the text representations from different categories more separable and the text representations from the same category more compact, we introduce a contrastive learning loss function. Experimental results on public-domain benchmark datasets demonstrate the effectiveness of Mask-BERT.