Weakly supervised semantic segmentation (WSSS) approaches typically rely on class activation maps (CAMs) for initial seed generation, which often fail to capture global context due to limited supervision from image-level labels. To address this issue, we introduce DALNet, Dense Alignment Learning Network that leverages text embeddings to enhance the comprehensive understanding and precise localization of objects across different levels of granularity. Our key insight is to employ a dual-level alignment strategy: (1) Global Implicit Alignment (GIA) to capture global semantics by maximizing the similarity between the class token and the corresponding text embeddings while minimizing the similarity with background embeddings, and (2) Local Explicit Alignment (LEA) to improve object localization by utilizing spatial information from patch tokens. Moreover, we propose a cross-contrastive learning approach that aligns foreground features between image and text modalities while separating them from the background, encouraging activation in missing regions and suppressing distractions. Through extensive experiments on the PASCAL VOC and MS COCO datasets, we demonstrate that DALNet significantly outperforms state-of-the-art WSSS methods. Our approach, in particular, allows for more efficient end-to-end process as a single-stage method.
Breast cancer is a significant threat to human health. Contrastive learning has emerged as an effective method to extract critical lesion features from mammograms, thereby offering a potent tool for breast cancer screening and analysis. A crucial aspect of contrastive learning involves negative sampling, where the selection of appropriate hard negative samples is essential for driving representations to retain detailed information about lesions. In contrastive learning, it is often assumed that features can sufficiently capture semantic content, and that each minibatch inherently includes ideal hard negative samples. However, the characteristics of breast lumps challenge these assumptions. In response, we introduce ManiNeg, a novel approach that leverages manifestations as proxies to mine hard negative samples. Manifestations, which refer to the observable symptoms or signs of a disease, provide a knowledge-driven and robust basis for choosing hard negative samples. This approach benefits from its invariance to model optimization, facilitating efficient sampling. To support ManiNeg and future research endeavors, we developed the MVKL dataset, which includes multi-view mammograms, corresponding reports, meticulously annotated manifestations, and pathologically confirmed benign-malignant outcomes. We evaluate ManiNeg on the benign and malignant classification task. Our results demonstrate that ManiNeg not only improves representation in both unimodal and multimodal contexts but also shows generalization across datasets. The MVKL dataset and our codes are publicly available at https://github.com/wxwxwwxxx/ManiNeg.
Mammography is the primary imaging tool for breast cancer diagnosis. Despite significant strides in applying deep learning to interpret mammography images, efforts that focus predominantly on visual features often struggle with generalization across datasets. We hypothesize that integrating additional modalities in the radiology practice, notably the linguistic features of reports and manifestation features embodying radiological insights, offers a more powerful, interpretable and generalizable representation. In this paper, we announce MVKL, the first multimodal mammography dataset encompassing multi-view images, detailed manifestations and reports. Based on this dataset, we focus on the challanging task of unsupervised pretraining and propose ViKL, a innovative framework that synergizes Visual, Knowledge, and Linguistic features. This framework relies solely on pairing information without the necessity for pathology labels, which are often challanging to acquire. ViKL employs a triple contrastive learning approach to merge linguistic and knowledge-based insights with visual data, enabling both inter-modality and intra-modality feature enhancement. Our research yields significant findings: 1) Integrating reports and manifestations with unsupervised visual pretraining, ViKL substantially enhances the pathological classification and fosters multimodal interactions. 2) Manifestations can introduce a novel hard negative sample selection mechanism. 3) The multimodal features demonstrate transferability across different datasets. 4) The multimodal pretraining approach curbs miscalibrations and crafts a high-quality representation space. The MVKL dataset and ViKL code are publicly available at https://github.com/wxwxwwxxx/ViKL to support a broad spectrum of future research.
We present a simple, self-supervised approach to the Tracking Any Point (TAP) problem. We train a global matching transformer to find cycle consistent tracks through video via contrastive random walks, using the transformer's attention-based global matching to define the transition matrices for a random walk on a space-time graph. The ability to perform "all pairs" comparisons between points allows the model to obtain high spatial precision and to obtain a strong contrastive learning signal, while avoiding many of the complexities of recent approaches (such as coarse-to-fine matching). To do this, we propose a number of design decisions that allow global matching architectures to be trained through self-supervision using cycle consistency. For example, we identify that transformer-based methods are sensitive to shortcut solutions, and propose a data augmentation scheme to address them. Our method achieves strong performance on the TapVid benchmarks, outperforming previous self-supervised tracking methods, such as DIFT, and is competitive with several supervised methods.
Image-to-Image Translation is a vital area of computer vision that focuses on transforming images from one visual domain to another while preserving their core content and structure. However, this field faces two major challenges: first, the data from the two domains are often unpaired, making it difficult to train generative adversarial networks effectively; second, existing methods tend to produce artifacts or hallucinations during image generation, leading to a decline in image quality. To address these issues, this paper proposes an enhanced unsupervised image-to-image translation method based on the Contrastive Unpaired Translation (CUT) model, incorporating Histogram of Oriented Gradients (HOG) features. This novel approach ensures the preservation of the semantic structure of images, even without semantic labels, by minimizing the loss between the HOG features of input and generated images. The method was tested on translating synthetic game environments from GTA5 dataset to realistic urban scenes in cityscapes dataset, demonstrating significant improvements in reducing hallucinations and enhancing image quality.
With the rapid development of artificial intelligence, multimodal learning has become an important research area. For intelligent agents, the state is a crucial modality to convey precise information alongside common modalities like images, videos, and language. This becomes especially clear with the broad adoption of reinforcement learning and multimodal large language models. Nevertheless, the representation of state modality still lags in development. To this end, we propose a High-Fidelity Contrastive Language-State Pre-training (CLSP) method, which can accurately encode state information into general representations for both reinforcement learning and multimodal large language models. Specifically, we first design a pre-training task based on the classification to train an encoder with coarse-grained information. Next, we construct data pairs of states and language descriptions, utilizing the pre-trained encoder to initialize the CLSP encoder. Then, we deploy contrastive learning to train the CLSP encoder to effectively represent precise state information. Additionally, we enhance the representation of numerical information using the Random Fourier Features (RFF) method for high-fidelity mapping. Extensive experiments demonstrate the superior precision and generalization capabilities of our representation, achieving outstanding results in text-state retrieval, reinforcement learning navigation tasks, and multimodal large language model understanding.
In the context of global energy strategy, accurate natural gas demand forecasting is crucial for ensuring efficient resource allocation and operational planning. Traditional forecasting methods struggle to cope with the growing complexity and variability of gas consumption patterns across diverse industries and commercial sectors. To address these challenges, we propose the first foundation model specifically tailored for natural gas demand forecasting. Foundation models, known for their ability to generalize across tasks and datasets, offer a robust solution to the limitations of traditional methods, such as the need for separate models for different customer segments and their limited generalization capabilities. Our approach leverages contrastive learning to improve prediction accuracy in real-world scenarios, particularly by tackling issues such as noise in historical consumption data and the potential misclassification of similar data samples, which can lead to degradation in the quaility of the representation and thus the accuracy of downstream forecasting tasks. By integrating advanced noise filtering techniques within the contrastive learning framework, our model enhances the quality of learned representations, leading to more accurate predictions. Furthermore, the model undergoes industry-specific fine-tuning during pretraining, enabling it to better capture the unique characteristics of gas consumption across various sectors. We conducted extensive experiments using a large-scale dataset from ENN Group, which includes data from over 10,000 industrial, commercial, and welfare-related customers across multiple regions. Our model outperformed existing state-of-the-art methods, demonstrating a relative improvement in MSE by 3.68\% and in MASE by 6.15\% compared to the best available model.
As various types of crime continue to threaten public safety and economic development, predicting the occurrence of multiple types of crimes becomes increasingly vital for effective prevention measures. Although extensive efforts have been made, most of them overlook the heterogeneity of different crime categories and fail to address the issue of imbalanced spatial distribution. In this work, we propose a Spatial-Temporal Mixture-of-Graph-Experts (ST-MoGE) framework for collective multiple-type crime prediction. To enhance the model's ability to identify diverse spatial-temporal dependencies and mitigate potential conflicts caused by spatial-temporal heterogeneity of different crime categories, we introduce an attentive-gated Mixture-of-Graph-Experts (MGEs) module to capture the distinctive and shared crime patterns of each crime category. Then, we propose Cross-Expert Contrastive Learning(CECL) to update the MGEs and force each expert to focus on specific pattern modeling, thereby reducing blending and redundancy. Furthermore, to address the issue of imbalanced spatial distribution, we propose a Hierarchical Adaptive Loss Re-weighting (HALR) approach to eliminate biases and insufficient learning of data-scarce regions. To evaluate the effectiveness of our methods, we conduct comprehensive experiments on two real-world crime datasets and compare our results with twelve advanced baselines. The experimental results demonstrate the superiority of our methods.
Environment Sound Classification has been a well-studied research problem in the field of signal processing and up till now more focus has been laid on fully supervised approaches. Over the last few years, focus has moved towards semi-supervised methods which concentrate on the utilization of unlabeled data, and self-supervised methods which learn the intermediate representation through pretext task or contrastive learning. However, both approaches require a vast amount of unlabelled data to improve performance. In this work, we propose a novel framework called Environmental Sound Classification with Hierarchical Ontology-guided semi-supervised Learning (ECHO) that utilizes label ontology-based hierarchy to learn semantic representation by defining a novel pretext task. In the pretext task, the model tries to predict coarse labels defined by the Large Language Model (LLM) based on ground truth label ontology. The trained model is further fine-tuned in a supervised way to predict the actual task. Our proposed novel semi-supervised framework achieves an accuracy improvement in the range of 1\% to 8\% over baseline systems across three datasets namely UrbanSound8K, ESC-10, and ESC-50.
Aerial Remote Sensing (ARS) vision tasks pose significant challenges due to the unique characteristics of their viewing angles. Existing research has primarily focused on algorithms for specific tasks, which have limited applicability in a broad range of ARS vision applications. This paper proposes the RingMo-Aerial model, aiming to fill the gap in foundation model research in the field of ARS vision. By introducing the Frequency-Enhanced Multi-Head Self-Attention (FE-MSA) mechanism and an affine transformation-based contrastive learning pre-training method, the model's detection capability for small targets is enhanced and optimized for the tilted viewing angles characteristic of ARS. Furthermore, the ARS-Adapter, an efficient parameter fine-tuning method, is proposed to improve the model's adaptability and effectiveness in various ARS vision tasks. Experimental results demonstrate that RingMo-Aerial achieves SOTA performance on multiple downstream tasks. This indicates the practicality and efficacy of RingMo-Aerial in enhancing the performance of ARS vision tasks.
Existing efforts in text-based video question answering (TextVideoQA) are criticized for their opaque decisionmaking and heavy reliance on scene-text recognition. In this paper, we propose to study Grounded TextVideoQA by forcing models to answer questions and spatio-temporally localize the relevant scene-text regions, thus decoupling QA from scenetext recognition and promoting research towards interpretable QA. The task has three-fold significance. First, it encourages scene-text evidence versus other short-cuts for answer predictions. Second, it directly accepts scene-text regions as visual answers, thus circumventing the problem of ineffective answer evaluation by stringent string matching. Third, it isolates the challenges inherited in VideoQA and scene-text recognition. This enables the diagnosis of the root causes for failure predictions, e.g., wrong QA or wrong scene-text recognition? To achieve Grounded TextVideoQA, we propose the T2S-QA model that highlights a disentangled temporal-to-spatial contrastive learning strategy for weakly-supervised scene-text grounding and grounded TextVideoQA. To facilitate evaluation, we construct a new dataset ViTXT-GQA which features 52K scene-text bounding boxes within 2.2K temporal segments related to 2K questions and 729 videos. With ViTXT-GQA, we perform extensive experiments and demonstrate the severe limitations of existing techniques in Grounded TextVideoQA. While T2S-QA achieves superior results, the large performance gap with human leaves ample space for improvement. Our further analysis of oracle scene-text inputs posits that the major challenge is scene-text recognition. To advance the research of Grounded TextVideoQA, our dataset and code are at https://github.com/zhousheng97/ViTXT-GQA.git
Video anomaly detection is a subject of great interest across industrial and academic domains due to its crucial role in computer vision applications. However, the inherent unpredictability of anomalies and the scarcity of anomaly samples present significant challenges for unsupervised learning methods. To overcome the limitations of unsupervised learning, which stem from a lack of comprehensive prior knowledge about anomalies, we propose VLAVAD (Video-Language Models Assisted Anomaly Detection). Our method employs a cross-modal pre-trained model that leverages the inferential capabilities of large language models (LLMs) in conjunction with a Selective-Prompt Adapter (SPA) for selecting semantic space. Additionally, we introduce a Sequence State Space Module (S3M) that detects temporal inconsistencies in semantic features. By mapping high-dimensional visual features to low-dimensional semantic ones, our method significantly enhance the interpretability of unsupervised anomaly detection. Our proposed approach effectively tackles the challenge of detecting elusive anomalies that are hard to discern over periods, achieving SOTA on the challenging ShanghaiTech dataset.
Many longitudinal neuroimaging studies aim to improve the understanding of brain aging and diseases by studying the dynamic interactions between brain function and cognition. Doing so requires accurate encoding of their multidimensional relationship while accounting for individual variability over time. For this purpose, we propose an unsupervised learning model (called \underline{\textbf{Co}}ntrastive Learning-based \underline{\textbf{Gra}}ph Generalized \underline{\textbf{Ca}}nonical Correlation Analysis (CoGraCa)) that encodes their relationship via Graph Attention Networks and generalized Canonical Correlational Analysis. To create brain-cognition fingerprints reflecting unique neural and cognitive phenotype of each person, the model also relies on individualized and multimodal contrastive learning. We apply CoGraCa to longitudinal dataset of healthy individuals consisting of resting-state functional MRI and cognitive measures acquired at multiple visits for each participant. The generated fingerprints effectively capture significant individual differences and outperform current single-modal and CCA-based multimodal models in identifying sex and age. More importantly, our encoding provides interpretable interactions between those two modalities.
Recent years have been marked with the fast-pace diversification and increasing ubiquity of machine learning applications. Yet, a firm theoretical understanding of the surprising efficiency of neural networks to learn from high-dimensional data still proves largely elusive. In this endeavour, analyses inspired by statistical physics have proven instrumental, enabling the tight asymptotic characterization of the learning of neural networks in high dimensions, for a broad class of solvable models. This manuscript reviews the tools and ideas underlying recent progress in this line of work. We introduce a generic model -- the sequence multi-index model -- which encompasses numerous previously studied models as special instances. This unified framework covers a broad class of machine learning architectures with a finite number of hidden units, including multi-layer perceptrons, autoencoders, attention mechanisms; and tasks, including (un)supervised learning, denoising, contrastive learning, in the limit of large data dimension, and comparably large number of samples. We explicate in full detail the analysis of the learning of sequence multi-index models, using statistical physics techniques such as the replica method and approximate message-passing algorithms. This manuscript thus provides a unified presentation of analyses reported in several previous works, and a detailed overview of central techniques in the field of statistical physics of machine learning. This review should be a useful primer for machine learning theoreticians curious of statistical physics approaches; it should also be of value to statistical physicists interested in the transfer of such ideas to the study of neural networks.
Given the significant potential of large language models (LLMs) in sequence modeling, emerging studies have begun applying them to time-series forecasting. Despite notable progress, existing methods still face two critical challenges: 1) their reliance on large amounts of paired text data, limiting the model applicability, and 2) a substantial modality gap between text and time series, leading to insufficient alignment and suboptimal performance. In this paper, we introduce \textbf{H}ierarchical \textbf{T}ext-\textbf{F}ree \textbf{A}lignment (\textbf{TS-HTFA}), a novel method that leverages hierarchical alignment to fully exploit the representation capacity of LLMs while eliminating the dependence on text data. Specifically, we replace paired text data with adaptive virtual text based on QR decomposition word embeddings and learnable prompt. Furthermore, we establish comprehensive cross-modal alignment at three levels: input, feature, and output. Extensive experiments on multiple time-series benchmarks demonstrate that HTFA achieves state-of-the-art performance, significantly improving prediction accuracy and generalization.
Can we directly visualize what we imagine in our brain together with what we describe? The inherent nature of human perception reveals that, when we think, our body can combine language description and build a vivid picture in our brain. Intuitively, generative models should also hold such versatility. In this paper, we introduce BrainDreamer, a novel end-to-end language-guided generative framework that can mimic human reasoning and generate high-quality images from electroencephalogram (EEG) brain signals. Our method is superior in its capacity to eliminate the noise introduced by non-invasive EEG data acquisition and meanwhile achieve a more precise mapping between the EEG and image modality, thus leading to significantly better-generated images. Specifically, BrainDreamer consists of two key learning stages: 1) modality alignment and 2) image generation. In the alignment stage, we propose a novel mask-based triple contrastive learning strategy to effectively align EEG, text, and image embeddings to learn a unified representation. In the generation stage, we inject the EEG embeddings into the pre-trained Stable Diffusion model by designing a learnable EEG adapter to generate high-quality reasoning-coherent images. Moreover, BrainDreamer can accept textual descriptions (e.g., color, position, etc.) to achieve controllable image generation. Extensive experiments show that our method significantly outperforms prior arts in terms of generating quality and quantitative performance.
Accurate solar flare prediction is crucial due to the significant risks that intense solar flares pose to astronauts, space equipment, and satellite communication systems. Our research enhances solar flare prediction by utilizing advanced data preprocessing and classification methods on a multivariate time series-based dataset of photospheric magnetic field parameters. First, our study employs a novel preprocessing pipeline that includes missing value imputation, normalization, balanced sampling, near decision boundary sample removal, and feature selection to significantly boost prediction accuracy. Second, we integrate contrastive learning with a GRU regression model to develop a novel classifier, termed ContReg, which employs dual learning methodologies, thereby further enhancing prediction performance. To validate the effectiveness of our preprocessing pipeline, we compare and demonstrate the performance gain of each step, and to demonstrate the efficacy of the ContReg classifier, we compare its performance to that of sequence-based deep learning architectures, machine learning models, and findings from previous studies. Our results illustrate exceptional True Skill Statistic (TSS) scores, surpassing previous methods and highlighting the critical role of precise data preprocessing and classifier development in time series-based solar flare prediction.
As LLMs evolve, significant effort is spent on manually crafting prompts. While existing prompt optimization methods automate this process, they rely solely on learning from incorrect samples, leading to a sub-optimal performance. Additionally, an unexplored challenge in the literature is prompts effective for prior models may not perform well on newer versions or different languages. We propose the Learning from Contrastive Prompts (LCP) framework to address these gaps, enhancing both prompt optimization and adaptation. LCP employs contrastive learning to generate effective prompts by analyzing patterns in good and bad prompt examples. Our evaluation on the Big-Bench Hard dataset shows that LCP has a win rate of over 76% over existing methods in prompt optimization and demonstrates strong adaptability across different model versions, families, and languages. LCP offers a systematic approach to prompt engineering, reducing manual effort in deploying LLMs across varied contexts.
Emojis have gained immense popularity on social platforms, serving as a common means to supplement or replace text. However, existing data mining approaches generally either completely ignore or simply treat emojis as ordinary Unicode characters, which may limit the model's ability to grasp the rich semantic information in emojis and the interaction between emojis and texts. Thus, it is necessary to release the emoji's power in social media data mining. To this end, we first construct a heterogeneous graph consisting of three types of nodes, i.e. post, word and emoji nodes to improve the representation of different elements in posts. The edges are also well-defined to model how these three elements interact with each other. To facilitate the sharing of information among post, word and emoji nodes, we propose a graph pre-train framework for text and emoji co-modeling, which contains two graph pre-training tasks: node-level graph contrastive learning and edge-level link reconstruction learning. Extensive experiments on the Xiaohongshu and Twitter datasets with two types of downstream tasks demonstrate that our approach proves significant improvement over previous strong baseline methods.
Logical reading comprehension is a challenging task that entails grasping the underlying semantics of text and applying reasoning to deduce the correct answer. Prior researches have primarily focused on enhancing logical reasoning capabilities through Chain-of-Thought (CoT) or data augmentation. However, previous work constructing chain-of-thought rationales concentrates solely on analyzing correct options, neglecting the incorrect alternatives. Addtionally, earlier efforts on data augmentation by altering contexts rely on rule-based methods, which result in generated contexts that lack diversity and coherence. To address these issues, we propose a Premise-Oriented Data Augmentation (PODA) framework. This framework can generate CoT rationales including analyses for both correct and incorrect options, while constructing diverse and high-quality counterfactual contexts from incorrect candidate options. We integrate summarizing premises and identifying premises for each option into rationales. Subsequently, we employ multi-step prompts with identified premises to construct counterfactual context. To facilitate the model's capabilities to better differentiate the reasoning process associated with each option, we introduce a novel thought-path contrastive learning method that compares reasoning paths between the original and counterfactual samples. Experimental results on three representative LLMs demonstrate that our method can improve the baselines substantially across two challenging logical reasoning benchmarks (ReClor and LogiQA 2.0). The data and code are released at https://github.com/lalalamdbf/TPReasoner.