PyTorchKR Papers

최신 논문

총 6,233편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2407.08971공식 코드 · Papers with Code

Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization

Weakly-supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos using only video-level supervision. Latest WSTAL methods introduce pseudo label learning framework to bridge the gap between classification-based training and inferencing targets at localization, and achieve cutting-edge results. In these frameworks, a classification-based model is used to generate pseudo labels for a regression-based student model to learn from. However, the quality of pseudo labels in the framework, which is a key factor to the final result, is not carefully studied. In this paper, we propose a set of simple yet efficient pseudo label quality enhancement mechanisms to build our FuSTAL framework. FuSTAL enhances pseudo label quality at three stages: cross-video contrastive learning at proposal Generation-Stage, prior-based filtering at proposal Selection-Stage and EMA-based distillation at Training-Stage. These designs enhance pseudo label quality at different stages in the framework, and help produce more informative, less false and smoother action proposals. With the help of these comprehensive designs at all stages, FuSTAL achieves an average mAP of 50.8% on THUMOS'14, outperforming the previous best method by 1.2%, and becomes the first method to reach the milestone of 50%.

arXiv:2407.08961

Tissue-Contrastive Semi-Masked Autoencoders for Segmentation Pretraining on Chest CT

Existing Masked Image Modeling (MIM) depends on a spatial patch-based masking-reconstruction strategy to perceive objects'features from unlabeled images, which may face two limitations when applied to chest CT: 1) inefficient feature learning due to complex anatomical details presented in CT images, and 2) suboptimal knowledge transfer owing to input disparity between upstream and downstream models. To address these issues, we propose a new MIM method named Tissue-Contrastive Semi-Masked Autoencoder (TCS-MAE) for modeling chest CT images. Our method has two novel designs: 1) a tissue-based masking-reconstruction strategy to capture more fine-grained anatomical features, and 2) a dual-AE architecture with contrastive learning between the masked and original image views to bridge the gap of the upstream and downstream models. To validate our method, we systematically investigate representative contrastive, generative, and hybrid self-supervised learning methods on top of tasks involving segmenting pneumonia, mediastinal tumors, and various organs. The results demonstrate that, compared to existing methods, our TCS-MAE more effectively learns tissue-aware representations, thereby significantly enhancing segmentation performance across all tasks.

arXiv:2403.12986

BaCon: Boosting Imbalanced Semi-supervised Learning via Balanced Feature-Level Contrastive Learning

Semi-supervised Learning (SSL) reduces the need for extensive annotations in deep learning, but the more realistic challenge of imbalanced data distribution in SSL remains largely unexplored. In Class Imbalanced Semi-supervised Learning (CISSL), the bias introduced by unreliable pseudo-labels can be exacerbated by imbalanced data distributions. Most existing methods address this issue at instance-level through reweighting or resampling, but the performance is heavily limited by their reliance on biased backbone representation. Some other methods do perform feature-level adjustments like feature blending but might introduce unfavorable noise. In this paper, we discuss the bonus of a more balanced feature distribution for the CISSL problem, and further propose a Balanced Feature-Level Contrastive Learning method (BaCon). Our method directly regularizes the distribution of instances' representations in a well-designed contrastive manner. Specifically, class-wise feature centers are computed as the positive anchors, while negative anchors are selected by a straightforward yet effective mechanism. A distribution-related temperature adjustment is leveraged to control the class-wise contrastive degrees dynamically. Our method demonstrates its effectiveness through comprehensive experiments on the CIFAR10-LT, CIFAR100-LT, STL10-LT, and SVHN-LT datasets across various settings. For example, BaCon surpasses instance-level method FixMatch-based ABC on CIFAR10-LT with a 1.21% accuracy improvement, and outperforms state-of-the-art feature-level method CoSSL on CIFAR100-LT with a 0.63% accuracy improvement. When encountering more extreme imbalance degree, BaCon also shows better robustness than other methods.

논문 ID: document/1048025

CCML: Curriculum and Contrastive Learning Enhanced Meta-Learner for Personalized Spatial Trajectory Prediction

Spatial trajectory prediction is a fundamental problem for diverse location-based applications. However, existing methods fall short in learning and generalization, and cannot sufficiently capture users’ spatiotemporal preferences, especially for cold-start users. Moreover, these methods do not explicitly consider the diversity of moving patterns among users and trajectories, i.e., the learning difficulty of different user and trajectory samples, thus hindering the improvement of prediction accuracy. To solve these problems, we propose a novel Curriculum and Contrastive Learning Enhanced Meta-Learner (CCML) that transfers knowledge from users with rich data to cold-start users. Specifically, a Contrastive-based Trajectory Predictor (CTP) is designed as the base model, which utilizes contrastive learning technique on both user-level and trajectory-level, aiming to facilitate a more profound understanding and differentiation of the varied travel behaviors and preferences exhibited by individuals. Meanwhile, CCML also incorporates the curriculum learning and the hard sample mining strategies. It simultaneously considers the learning difficulty of both user and trajectory samples, and presents the learning tasks by an easy-to-hard curriculum. By learning more challenging combinations of user and trajectory samples in each meta-learning iteration, the meta-learner can converge to a better status. Extensive experiments on two real-world datasets demonstrate the superiority of our models.

arXiv:2407.09364

Is Contrasting All You Need? Contrastive Learning for the Detection and Attribution of AI-generated Text

The significant progress in the development of Large Language Models has contributed to blurring the distinction between human and AI-generated text. The increasing pervasiveness of AI-generated text and the difficulty in detecting it poses new challenges for our society. In this paper, we tackle the problem of detecting and attributing AI-generated text by proposing WhosAI, a triplet-network contrastive learning framework designed to predict whether a given input text has been generated by humans or AI and to unveil the authorship of the text. Unlike most existing approaches, our proposed framework is conceived to learn semantic similarity representations from multiple generators at once, thus equally handling both detection and attribution tasks. Furthermore, WhosAI is model-agnostic and scalable to the release of new AI text-generation models by incorporating their generated instances into the embedding space learned by our framework. Experimental results on the TuringBench benchmark of 200K news articles show that our proposed framework achieves outstanding results in both the Turing Test and Authorship Attribution tasks, outperforming all the methods listed in the TuringBench benchmark leaderboards.

arXiv:2407.09336공식 코드 · Papers with Code

Guidelines for Augmentation Selection in Contrastive Learning for Time Series Classification

Self-supervised contrastive learning has become a key technique in deep learning, particularly in time series analysis, due to its ability to learn meaningful representations without explicit supervision. Augmentation is a critical component in contrastive learning, where different augmentations can dramatically impact performance, sometimes influencing accuracy by over 30%. However, the selection of augmentations is predominantly empirical which can be suboptimal, or grid searching that is time-consuming. In this paper, we establish a principled framework for selecting augmentations based on dataset characteristics such as trend and seasonality. Specifically, we construct 12 synthetic datasets incorporating trend, seasonality, and integration weights. We then evaluate the effectiveness of 8 different augmentations across these synthetic datasets, thereby inducing generalizable associations between time series characteristics and augmentation efficiency. Additionally, we evaluated the induced associations across 6 real-world datasets encompassing domains such as activity recognition, disease diagnosis, traffic monitoring, electricity usage, mechanical fault prognosis, and finance. These real-world datasets are diverse, covering a range from 1 to 12 channels, 2 to 10 classes, sequence lengths of 14 to 1280, and data frequencies from 250 Hz to daily intervals. The experimental results show that our proposed trend-seasonality-based augmentation recommendation algorithm can accurately identify the effective augmentations for a given time series dataset, achieving an average Recall@3 of 0.667, outperforming baselines. Our work provides guidance for studies employing contrastive learning in time series analysis, with wide-ranging applications. All the code, datasets, and analysis results will be released at https://github.com/DL4mHealth/TS-Contrastive-Augmentation-Recommendation.

arXiv:2407.08647공식 코드 · Papers with Code

From Real to Cloned Singer Identification

Cloned voices of popular singers sound increasingly realistic and have gained popularity over the past few years. They however pose a threat to the industry due to personality rights concerns. As such, methods to identify the original singer in synthetic voices are needed. In this paper, we investigate how singer identification methods could be used for such a task. We present three embedding models that are trained using a singer-level contrastive learning scheme, where positive pairs consist of segments with vocals from the same singers. These segments can be mixtures for the first model, vocals for the second, and both for the third. We demonstrate that all three models are highly capable of identifying real singers. However, their performance deteriorates when classifying cloned versions of singers in our evaluation set. This is especially true for models that use mixtures as an input. These findings highlight the need to understand the biases that exist within singer identification systems, and how they can influence the identification of voice deepfakes in music.

arXiv:2407.08507

Bootstrapping Vision-language Models for Self-supervised Remote Physiological Measurement

Facial video-based remote physiological measurement is a promising research area for detecting human vital signs (e.g., heart rate, respiration frequency) in a non-contact way. Conventional approaches are mostly supervised learning, requiring extensive collections of facial videos and synchronously recorded photoplethysmography (PPG) signals. To tackle it, self-supervised learning has recently gained attentions; due to the lack of ground truth PPG signals, its performance is however limited. In this paper, we propose a novel self-supervised framework that successfully integrates the popular vision-language models (VLMs) into the remote physiological measurement task. Given a facial video, we first augment its positive and negative video samples with varying rPPG signal frequencies. Next, we introduce a frequency-oriented vision-text pair generation method by carefully creating contrastive spatio-temporal maps from positive and negative samples and designing proper text prompts to describe their relative ratios of signal frequencies. A pre-trained VLM is employed to extract features for these formed vision-text pairs and estimate rPPG signals thereafter. We develop a series of generative and contrastive learning mechanisms to optimize the VLM, including the text-guided visual map reconstruction task, the vision-text contrastive learning task, and the frequency contrastive and ranking task. Overall, our method for the first time adapts VLMs to digest and align the frequency-related knowledge in vision and text modalities. Extensive experiments on four benchmark datasets demonstrate that it significantly outperforms state of the art self-supervised methods.

arXiv:2407.08156공식 코드 · Papers with Code

AddressCLIP: Empowering Vision-Language Models for City-wide Image Address Localization

In this study, we introduce a new problem raised by social media and photojournalism, named Image Address Localization (IAL), which aims to predict the readable textual address where an image was taken. Existing two-stage approaches involve predicting geographical coordinates and converting them into human-readable addresses, which can lead to ambiguity and be resource-intensive. In contrast, we propose an end-to-end framework named AddressCLIP to solve the problem with more semantics, consisting of two key ingredients: i) image-text alignment to align images with addresses and scene captions by contrastive learning, and ii) image-geography matching to constrain image features with the spatial distance in terms of manifold learning. Additionally, we have built three datasets from Pittsburgh and San Francisco on different scales specifically for the IAL problem. Experiments demonstrate that our approach achieves compelling performance on the proposed datasets and outperforms representative transfer learning methods for vision-language models. Furthermore, extensive ablations and visualizations exhibit the effectiveness of the proposed method. The datasets and source code are available at https://github.com/xsx1001/AddressCLIP.

arXiv:2407.08739공식 코드 · Papers with Code

MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine

The mathematical capabilities of Multi-modal Large Language Models (MLLMs) remain under-explored with three areas to be improved: visual encoding of math diagrams, diagram-language alignment, and chain-of-thought (CoT) reasoning. This draws forth an urgent demand for an effective training paradigm and a large-scale, comprehensive dataset with detailed CoT rationales, which is challenging to collect and costly to annotate manually. To tackle this issue, we propose MAVIS, a MAthematical VISual instruction tuning pipeline for MLLMs, featuring an automatic data engine to efficiently create mathematical visual datasets. We design the data generation process to be entirely independent of human intervention or GPT API usage, while ensuring the diagram-caption correspondence, question-answer correctness, and CoT reasoning quality. With this approach, we curate two datasets, MAVIS-Caption (558K diagram-caption pairs) and MAVIS-Instruct (834K visual math problems with CoT rationales), and propose four progressive stages for training MLLMs from scratch. First, we utilize MAVIS-Caption to fine-tune a math-specific vision encoder (CLIP-Math) through contrastive learning, tailored for improved diagram visual encoding. Second, we also leverage MAVIS-Caption to align the CLIP-Math with a large language model (LLM) by a projection layer, enhancing vision-language alignment in mathematical domains. Third, we adopt MAVIS-Instruct to perform the instruction tuning for robust problem-solving skills, and term the resulting model as MAVIS-7B. Fourth, we apply Direct Preference Optimization (DPO) to enhance the CoT capabilities of our model, further refining its step-wise reasoning performance. Code and data will be released at https://github.com/ZrrSkywalker/MAVIS

arXiv:2407.08216공식 코드 · Papers with Code

Multimodal contrastive learning for spatial gene expression prediction using histology images

In recent years, the advent of spatial transcriptomics (ST) technology has unlocked unprecedented opportunities for delving into the complexities of gene expression patterns within intricate biological systems. Despite its transformative potential, the prohibitive cost of ST technology remains a significant barrier to its widespread adoption in large-scale studies. An alternative, more cost-effective strategy involves employing artificial intelligence to predict gene expression levels using readily accessible whole-slide images (WSIs) stained with Hematoxylin and Eosin (H\&E). However, existing methods have yet to fully capitalize on multimodal information provided by H&E images and ST data with spatial location. In this paper, we propose \textbf{mclSTExp}, a multimodal contrastive learning with Transformer and Densenet-121 encoder for Spatial Transcriptomics Expression prediction. We conceptualize each spot as a "word", integrating its intrinsic features with spatial context through the self-attention mechanism of a Transformer encoder. This integration is further enriched by incorporating image features via contrastive learning, thereby enhancing the predictive capability of our model. Our extensive evaluation of \textbf{mclSTExp} on two breast cancer datasets and a skin squamous cell carcinoma dataset demonstrates its superior performance in predicting spatial gene expression. Moreover, mclSTExp has shown promise in interpreting cancer-specific overexpressed genes, elucidating immune-related genes, and identifying specialized spatial domains annotated by pathologists. Our source code is available at https://github.com/shizhiceng/mclSTExp.

arXiv:2407.08164

Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks

In multi-agent reinforcement learning (MARL), the Centralized Training with Decentralized Execution (CTDE) framework is pivotal but struggles due to a gap: global state guidance in training versus reliance on local observations in execution, lacking global signals. Inspired by human societal consensus mechanisms, we introduce the Hierarchical Consensus-based Multi-Agent Reinforcement Learning (HC-MARL) framework to address this limitation. HC-MARL employs contrastive learning to foster a global consensus among agents, enabling cooperative behavior without direct communication. This approach enables agents to form a global consensus from local observations, using it as an additional piece of information to guide collaborative actions during execution. To cater to the dynamic requirements of various tasks, consensus is divided into multiple layers, encompassing both short-term and long-term considerations. Short-term observations prompt the creation of an immediate, low-layer consensus, while long-term observations contribute to the formation of a strategic, high-layer consensus. This process is further refined through an adaptive attention mechanism that dynamically adjusts the influence of each consensus layer. This mechanism optimizes the balance between immediate reactions and strategic planning, tailoring it to the specific demands of the task at hand. Extensive experiments and real-world applications in multi-robot systems showcase our framework's superior performance, marking significant advancements over baselines.

arXiv:2407.07582공식 코드 · Papers with Code

TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Data

Images and structured tables are essential parts of real-world databases. Though tabular-image representation learning is promising to create new insights, it remains a challenging task, as tabular data is typically heterogeneous and incomplete, presenting significant modality disparities with images. Earlier works have mainly focused on simple modality fusion strategies in complete data scenarios, without considering the missing data issue, and thus are limited in practice. In this paper, we propose TIP, a novel tabular-image pre-training framework for learning multimodal representations robust to incomplete tabular data. Specifically, TIP investigates a novel self-supervised learning (SSL) strategy, including a masked tabular reconstruction task for tackling data missingness, and image-tabular matching and contrastive learning objectives to capture multimodal information. Moreover, TIP proposes a versatile tabular encoder tailored for incomplete, heterogeneous tabular data and a multimodal interaction module for inter-modality representation learning. Experiments are performed on downstream multimodal classification tasks using both natural and medical image datasets. The results show that TIP outperforms state-of-the-art supervised/SSL image/multimodal algorithms in both complete and incomplete data scenarios. Our code is available at https://github.com/siyi-wind/TIP.

arXiv:2407.07479

How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?

Dominant dual-encoder models enable efficient image-text retrieval but suffer from limited accuracy while the cross-encoder models offer higher accuracy at the expense of efficiency. Distilling cross-modality matching knowledge from cross-encoder to dual-encoder provides a natural approach to harness their strengths. Thus we investigate the following valuable question: how to make cross-encoder a good teacher for dual-encoder? Our findings are threefold:(1) Cross-modal similarity score distribution of cross-encoder is more concentrated while the result of dual-encoder is nearly normal making vanilla logit distillation less effective. However ranking distillation remains practical as it is not affected by the score distribution.(2) Only the relative order between hard negatives conveys valid knowledge while the order information between easy negatives has little significance.(3) Maintaining the coordination between distillation loss and dual-encoder training loss is beneficial for knowledge transfer. Based on these findings we propose a novel Contrastive Partial Ranking Distillation (CPRD) method which implements the objective of mimicking relative order between hard negative samples with contrastive learning. This approach coordinates with the training of the dual-encoder effectively transferring valid knowledge from the cross-encoder to the dual-encoder. Extensive experiments on image-text retrieval and ranking tasks show that our method surpasses other distillation methods and significantly improves the accuracy of dual-encoder.

arXiv:2407.07478

EA-VTR: Event-Aware Video-Text Retrieval

Understanding the content of events occurring in the video and their inherent temporal logic is crucial for video-text retrieval. However, web-crawled pre-training datasets often lack sufficient event information, and the widely adopted video-level cross-modal contrastive learning also struggles to capture detailed and complex video-text event alignment. To address these challenges, we make improvements from both data and model perspectives. In terms of pre-training data, we focus on supplementing the missing specific event content and event temporal transitions with the proposed event augmentation strategies. Based on the event-augmented data, we construct a novel Event-Aware Video-Text Retrieval model, ie, EA-VTR, which achieves powerful video-text retrieval ability through superior video event awareness. EA-VTR can efficiently encode frame-level and video-level visual representations simultaneously, enabling detailed event content and complex event temporal cross-modal alignment, ultimately enhancing the comprehensive understanding of video events. Our method not only significantly outperforms existing approaches on multiple datasets for Text-to-Video Retrieval and Video Action Recognition tasks, but also demonstrates superior event content perceive ability on Multi-event Video-Text Retrieval and Video Moment Retrieval tasks, as well as outstanding event temporal logic understanding ability on Test of Time task.

arXiv:2407.07315

CosmoCLIP: Generalizing Large Vision-Language Models for Astronomical Imaging

Existing vision-text contrastive learning models enhance representation transferability and support zero-shot prediction by matching paired image and caption embeddings while pushing unrelated pairs apart. However, astronomical image-label datasets are significantly smaller compared to general image and label datasets available from the internet. We introduce CosmoCLIP, an astronomical image-text contrastive learning framework precisely fine-tuned on the pre-trained CLIP model using SpaceNet and BLIP-based captions. SpaceNet, attained via FLARE, constitutes ~13k optimally distributed images, while BLIP acts as a rich knowledge extractor. The rich semantics derived from this SpaceNet and BLIP descriptions, when learned contrastively, enable CosmoCLIP to achieve superior generalization across various in-domain and out-of-domain tasks. Our results demonstrate that CosmoCLIP is a straightforward yet powerful framework, significantly outperforming CLIP in zero-shot classification and image-text retrieval tasks.

arXiv:2407.07171공식 코드 · Papers with Code

ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation

The costly and time-consuming annotation process to produce large training sets for modelling semantic LiDAR segmentation methods has motivated the development of semi-supervised learning (SSL) methods. However, such SSL approaches often concentrate on employing consistency learning only for individual LiDAR representations. This narrow focus results in limited perturbations that generally fail to enable effective consistency learning. Additionally, these SSL approaches employ contrastive learning based on the sampling from a limited set of positive and negative embedding samples. This paper introduces a novel semi-supervised LiDAR semantic segmentation framework called ItTakesTwo (IT2). IT2 is designed to ensure consistent predictions from peer LiDAR representations, thereby improving the perturbation effectiveness in consistency learning. Furthermore, our contrastive learning employs informative samples drawn from a distribution of positive and negative embeddings learned from the entire training set. Results on public benchmarks show that our approach achieves remarkable improvements over the previous state-of-the-art (SOTA) methods in the field. The code is available at: https://github.com/yyliu01/IT2.

arXiv:2407.06326공식 코드 · Papers with Code

Tile Compression and Embeddings for Multi-Label Classification in GeoLifeCLEF 2024

We explore methods to solve the multi-label classification task posed by the GeoLifeCLEF 2024 competition with the DS@GT team, which aims to predict the presence and absence of plant species at specific locations using spatial and temporal remote sensing data. Our approach uses frequency-domain coefficients via the Discrete Cosine Transform (DCT) to compress and pre-compute the raw input data for convolutional neural networks. We also investigate nearest neighborhood models via locality-sensitive hashing (LSH) for prediction and to aid in the self-supervised contrastive learning of embeddings through tile2vec. Our best competition model utilized geolocation features with a leaderboard score of 0.152 and a best post-competition score of 0.161. Source code and models are available at https://github.com/dsgt-kaggle-clef/geolifeclef-2024.

arXiv:2407.04738

A Contrastive Learning Based Convolutional Neural Network for ERP Brain-Computer Interfaces

ERP-based EEG detection is gaining increasing attention in the field of brain-computer interfaces. However, due to the complexity of ERP signal components, their low signal-to-noise ratio, and significant inter-subject variability, cross-subject ERP signal detection has been challenging. The continuous advancement in deep learning has greatly contributed to addressing this issue. This brief proposes a contrastive learning training framework and an Inception module to extract multi-scale temporal and spatial features, representing the subject-invariant components of ERP signals. Specifically, a base encoder integrated with a linear Inception module and a nonlinear projector is used to project the raw data into latent space. By maximizing signal similarity under different targets, the inter-subject EEG signal differences in latent space are minimized. The extracted spatiotemporal features are then used for ERP target detection. The proposed algorithm achieved the best AUC performance in single-trial binary classification tasks on the P300 dataset and showed significant optimization in speller decoding tasks compared to existing algorithms.

arXiv:2407.06833공식 코드 · Papers with Code

Training-free CryoET Tomogram Segmentation

Cryogenic Electron Tomography (CryoET) is a useful imaging technology in structural biology that is hindered by its need for manual annotations, especially in particle picking. Recent works have endeavored to remedy this issue with few-shot learning or contrastive learning techniques. However, supervised training is still inevitable for them. We instead choose to leverage the power of existing 2D foundation models and present a novel, training-free framework, CryoSAM. In addition to prompt-based single-particle instance segmentation, our approach can automatically search for similar features, facilitating full tomogram semantic segmentation with only one prompt. CryoSAM is composed of two major parts: 1) a prompt-based 3D segmentation system that uses prompts to complete single-particle instance segmentation recursively with Cross-Plane Self-Prompting, and 2) a Hierarchical Feature Matching mechanism that efficiently matches relevant features with extracted tomogram features. They collaborate to enable the segmentation of all particles of one category with just one particle-specific prompt. Our experiments show that CryoSAM outperforms existing works by a significant margin and requires even fewer annotations in particle picking. Further visualizations demonstrate its ability when dealing with full tomogram segmentation for various subcellular structures. Our code is available at: https://github.com/xulabs/aitom