With the proliferation of social media posts in recent years, the need to detect sentiments in multimodal (image-text) content has grown rapidly. Since posts are user-generated, the image and text from the same post can express different or even contradictory sentiments, leading to potential \textbf{sentiment discrepancy}. However, existing works mainly adopt a single-branch fusion structure that primarily captures the consistent sentiment between image and text. The ignorance or implicit modeling of discrepant sentiment results in compromised unimodal encoding and limited performances. In this paper, we propose a semantics Completion and Decomposition (CoDe) network to resolve the above issue. In the semantics completion module, we complement image and text representations with the semantics of the OCR text embedded in the image, helping bridge the sentiment gap. In the semantics decomposition module, we decompose image and text representations with exclusive projection and contrastive learning, thereby explicitly capturing the discrepant sentiment between modalities. Finally, we fuse image and text representations by cross-attention and combine them with the learned discrepant sentiment for final classification. Extensive experiments conducted on four multimodal sentiment datasets demonstrate the superiority of CoDe against SOTA methods.
Hyperspectral target detection (HTD) identifies objects of interest from complex backgrounds at the pixel level, playing a vital role in Earth observation. However, HTD faces challenges due to limited prior knowledge and spectral variation, leading to underfitting models and unreliable performance. To address these challenges, this paper proposes an efficient self-supervised HTD method with a pyramid state space model (SSM), named HTD-Mamba, which employs spectrally contrastive learning to distinguish between target and background based on the similarity measurement of intrinsic features. Specifically, to obtain sufficient training samples and leverage spatial contextual information, we propose a spatial-encoded spectral augmentation technique that encodes all surrounding pixels within a patch into a transformed view of the center pixel. Additionally, to explore global band correlations, we divide pixels into continuous group-wise spectral embeddings and introduce Mamba to HTD for the first time to model long-range dependencies of the spectral sequence with linear complexity. Furthermore, to alleviate spectral variation and enhance robust representation, we propose a pyramid SSM as a backbone to capture and fuse multiresolution spectral-wise intrinsic features. Extensive experiments conducted on four public datasets demonstrate that the proposed method outperforms state-of-the-art methods in both quantitative and qualitative evaluations. Code is available at \url{https://github.com/shendb2022/HTD-Mamba}.
We present CEIA, an effective framework for open-world event-based understanding. Currently training a large event-text model still poses a huge challenge due to the shortage of paired event-text data. In response to this challenge, CEIA learns to align event and image data as an alternative instead of directly aligning event and text data. Specifically, we leverage the rich event-image datasets to learn an event embedding space aligned with the image space of CLIP through contrastive learning. In this way, event and text data are naturally aligned via using image data as a bridge. Particularly, CEIA offers two distinct advantages. First, it allows us to take full advantage of the existing event-image datasets to make up the shortage of large-scale event-text datasets. Second, leveraging more training data, it also exhibits the flexibility to boost performance, ensuring scalable capability. In highlighting the versatility of our framework, we make extensive evaluations through a diverse range of event-based multi-modal applications, such as object recognition, event-image retrieval, event-text retrieval, and domain adaptation. The outcomes demonstrate CEIA's distinct zero-shot superiority over existing methods on these applications.
Multimodal sentiment analysis is an active research area that combines multiple data modalities, e.g., text, image and audio, to analyze human emotions and benefits a variety of applications. Existing multimodal sentiment analysis methods can be classified as modality interaction-based methods, modality transformation-based methods and modality similarity-based methods. However, most of these methods highly rely on the strong correlations between modalities, and cannot fully uncover and utilize the correlations between modalities to enhance sentiment analysis. Therefore, these methods usually achieve bad performance for identifying the sentiment of multimodal data with weak correlations. To address this issue, we proposed a two-stage semi-supervised model termed Correlation-aware Multimodal Transformer (CorMulT) which consists pre-training stage and prediction stage. At the pre-training stage, a modality correlation contrastive learning module is designed to efficiently learn modality correlation coefficients between different modalities. At the prediction stage, the learned correlation coefficients are fused with modality representations to make the sentiment prediction. According to the experiments on the popular multimodal dataset CMU-MOSEI, CorMulT obviously surpasses state-of-the-art multimodal sentiment analysis methods.
Tripartite graph-based recommender systems markedly diverge from traditional models by recommending unique combinations such as user groups and item bundles. Despite their effectiveness, these systems exacerbate the longstanding cold-start problem in traditional recommender systems, because any number of user groups or item bundles can be formed among users or items. To address this issue, we introduce a Consistency and Discrepancy-based graph contrastive learning method for tripartite graph-based Recommendation. This approach leverages two novel meta-path-based metrics consistency and discrepancy to capture nuanced, implicit associations between the recommended objects and the recommendees. These metrics, indicative of high-order similarities, can be efficiently calculated with infinite graph convolutional networks layers under a multi-objective optimization framework, using the limit theory of GCN.
Cross-lingual word alignment plays a crucial role in various natural language processing tasks, particularly for low-resource languages. Recent study proposes a BiLSTM-based encoder-decoder model that outperforms pre-trained language models in low-resource settings. However, their model only considers the similarity of word embedding spaces and does not explicitly model the differences between word embeddings. To address this limitation, we propose incorporating contrastive learning into the BiLSTM-based encoder-decoder framework. Our approach introduces a multi-view negative sampling strategy to learn the differences between word pairs in the shared cross-lingual embedding space. We evaluate our model on five bilingual aligned datasets spanning four ASEAN languages: Lao, Vietnamese, Thai, and Indonesian. Experimental results demonstrate that integrating contrastive learning consistently improves word alignment accuracy across all datasets, confirming the effectiveness of the proposed method in low-resource scenarios. We will release our data set and code to support future research on ASEAN or more low-resource word alignment.
The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation. However, alongside these advancements come significant challenges related to the accountability and transparency of LLM responses. Reliable source attribution is essential to adhering to stringent legal and regulatory standards, including those set forth by the General Data Protection Regulation. Despite the well-established methods in source attribution within the computer vision domain, the application of robust attribution frameworks to natural language processing remains underexplored. To bridge this gap, we propose a novel and versatile TRansformer-based Attribution framework using Contrastive Embeddings called TRACE that, in particular, exploits contrastive learning for source attribution. We perform an extensive empirical evaluation to demonstrate the performance and efficiency of TRACE in various settings and show that TRACE significantly improves the ability to attribute sources accurately, making it a valuable tool for enhancing the reliability and trustworthiness of LLMs.
The existing barely-supervised medical image segmentation (BSS) methods, adopting a registration-segmentation paradigm, aim to learn from data with very few annotations to mitigate the extreme label scarcity problem. However, this paradigm poses a challenge: pseudo-labels generated by image registration come with significant noise. To address this issue, we propose a self-paced sample selection framework (SPSS) for BSS. Specifically, SPSS comprises two main components: 1) self-paced uncertainty sample selection (SU) for explicitly improving the quality of pseudo labels in the image space, and 2) self-paced bidirectional feature contrastive learning (SC) for implicitly improving the quality of pseudo labels through enhancing the separability between class semantics in the feature space. Both SU and SC are trained collaboratively in a self-paced learning manner, ensuring that SPSS can learn from high-quality pseudo labels for BSS. Extensive experiments on two public medical image segmentation datasets demonstrate the effectiveness and superiority of SPSS over the state-of-the-art. Our code is release at https://github.com/SuuuJM/SPSS.
Treating texts as images, combining prompts with textual labels for prompt tuning, and leveraging the alignment properties of CLIP have been successfully applied in zero-shot multi-label image recognition. Nonetheless, relying solely on textual labels to store visual information is insufficient for representing the diversity of visual objects. In this paper, we propose reversing the training process of CLIP and introducing the concept of Pseudo Visual Prompts. These prompts are initialized for each object category and pre-trained on large-scale, low-cost sentence data generated by large language models. This process mines the aligned visual information in CLIP and stores it in class-specific visual prompts. We then employ contrastive learning to transfer the stored visual information to the textual labels, enhancing their visual representation capacity. Additionally, we introduce a dual-adapter module that simultaneously leverages knowledge from the original CLIP and new learning knowledge derived from downstream datasets. Benefiting from the pseudo visual prompts, our method surpasses the state-of-the-art not only on clean annotated text data but also on pseudo text data generated by large language models.
Zero-shot object counting (ZOC) aims to enumerate objects in images using only the names of object classes during testing, without the need for manual annotations. However, a critical challenge in current ZOC methods lies in their inability to identify high-quality exemplars effectively. This deficiency hampers scalability across diverse classes and undermines the development of strong visual associations between the identified classes and image content. To this end, we propose the Visual Association-based Zero-shot Object Counting (VA-Count) framework. VA-Count consists of an Exemplar Enhancement Module (EEM) and a Noise Suppression Module (NSM) that synergistically refine the process of class exemplar identification while minimizing the consequences of incorrect object identification. The EEM utilizes advanced vision-language pretaining models to discover potential exemplars, ensuring the framework's adaptability to various classes. Meanwhile, the NSM employs contrastive learning to differentiate between optimal and suboptimal exemplar pairs, reducing the negative effects of erroneous exemplars. VA-Count demonstrates its effectiveness and scalability in zero-shot contexts with superior performance on two object counting datasets.
Real-world data often follows a long-tailed distribution, where a few head classes occupy most of the data and a large number of tail classes only contain very limited samples. In practice, deep models often show poor generalization performance on tail classes due to the imbalanced distribution. To tackle this, data augmentation has become an effective way by synthesizing new samples for tail classes. Among them, one popular way is to use CutMix that explicitly mixups the images of tail classes and the others, while constructing the labels according to the ratio of areas cropped from two images. However, the area-based labels entirely ignore the inherent semantic information of the augmented samples, often leading to misleading training signals. To address this issue, we propose a Contrastive CutMix (ConCutMix) that constructs augmented samples with semantically consistent labels to boost the performance of long-tailed recognition. Specifically, we compute the similarities between samples in the semantic space learned by contrastive learning, and use them to rectify the area-based labels. Experiments show that our ConCutMix significantly improves the accuracy on tail classes as well as the overall performance. For example, based on ResNeXt-50, we improve the overall accuracy on ImageNet-LT by 3.0% thanks to the significant improvement of 3.3% on tail classes. We highlight that the improvement also generalizes well to other benchmarks and models. Our code and pretrained models are available at https://github.com/PanHaulin/ConCutMix.
Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones. However, in 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling remains dominant. This raises the question: Can we take the best of both worlds? To answer this question, we first empirically validate that integrating MAE-based point cloud pre-training with the standard contrastive learning paradigm, even with meticulous design, can lead to a decrease in performance. To address this limitation, we reintroduce CL into the MAE-based point cloud pre-training paradigm by leveraging the inherent contrastive properties of MAE. Specifically, rather than relying on extensive data augmentation as commonly used in the image domain, we randomly mask the input tokens twice to generate contrastive input pairs. Subsequently, a weight-sharing encoder and two identically structured decoders are utilized to perform masked token reconstruction. Additionally, we propose that for an input token masked by both masks simultaneously, the reconstructed features should be as similar as possible. This naturally establishes an explicit contrastive constraint within the generative MAE-based pre-training paradigm, resulting in our proposed method, Point-CMAE. Consequently, Point-CMAE effectively enhances the representation quality and transfer performance compared to its MAE counterpart. Experimental evaluations across various downstream applications, including classification, part segmentation, and few-shot learning, demonstrate the efficacy of our framework in surpassing state-of-the-art techniques under standard ViTs and single-modal settings. The source code and trained models are available at: https://github.com/Amazingren/Point-CMAE.
The Gleason groups serve as the primary histological grading system for prostate cancer, providing crucial insights into the cancer's potential for growth and metastasis. In clinical practice, pathologists determine the Gleason groups based on specimens obtained from ultrasound-guided biopsies. In this study, we investigate the feasibility of directly estimating the Gleason groups from MRI scans to reduce otherwise required biopsies. We identify two characteristics of this task, ordinality and the resulting dependent yet unknown variances between Gleason groups. In addition to the inter- / intra- observer variability in a multi-step Gleason scoring process based on the interpretation of Gleason patterns, our MR-based prediction is also subject to specimen sampling variance and, to a lesser degree, varying MR imaging protocols. To address this challenge, we propose a novel Poisson ordinal network (PON). PONs model the prediction using a Poisson distribution and leverages Poisson encoding and Poisson focal loss to capture a learnable dependency between ordinal classes (here, Gleason groups), rather than relying solely on the numerical ground-truth (e.g. Gleason Groups 1-5 or Gleason Scores 6-10). To improve this modelling efficacy, PONs also employ contrastive learning with a memory bank to regularise intra-class variance, decoupling the memory requirement of contrast learning from the batch size. Experimental results based on the images labelled by saturation biopsies from 265 prior-biopsy-blind patients, across two tasks demonstrate the superiority and effectiveness of our proposed method.
Composed Image Retrieval (CIR) aims to retrieve images based on a query image with text. Current Zero-Shot CIR (ZS-CIR) methods try to solve CIR tasks without using expensive triplet-labeled training datasets. However, the gap between ZS-CIR and triplet-supervised CIR is still large. In this work, we propose Hybrid CIR (HyCIR), which uses synthetic labels to boost the performance of ZS-CIR. A new label Synthesis pipeline for CIR (SynCir) is proposed, in which only unlabeled images are required. First, image pairs are extracted based on visual similarity. Second, query text is generated for each image pair based on vision-language model and LLM. Third, the data is further filtered in language space based on semantic similarity. To improve ZS-CIR performance, we propose a hybrid training strategy to work with both ZS-CIR supervision and synthetic CIR triplets. Two kinds of contrastive learning are adopted. One is to use large-scale unlabeled image dataset to learn an image-to-text mapping with good generalization. The other is to use synthetic CIR triplets to learn a better mapping for CIR tasks. Our approach achieves SOTA zero-shot performance on the common CIR benchmarks: CIRR and CIRCO.
Contrastive learning has emerged as a powerful technique in audio-visual representation learning, leveraging the natural co-occurrence of audio and visual modalities in webscale video datasets. However, conventional contrastive audio-visual learning (CAV) methodologies often rely on aggregated representations derived through temporal aggregation, neglecting the intrinsic sequential nature of the data. This oversight raises concerns regarding the ability of standard approaches to capture and utilize fine-grained information within sequences. In response to this limitation, we propose sequential contrastive audiovisual learning (SCAV), which contrasts examples based on their non-aggregated representation space using multidimensional sequential distances. Audio-visual retrieval experiments with the VGGSound and Music datasets demonstrate the effectiveness of SCAV, with up to 3.5x relative improvements in recall against traditional aggregation-based contrastive learning and other previously proposed methods, which utilize more parameters and data. We also show that models trained with SCAV exhibit a significant degree of flexibility regarding the metric employed for retrieval, allowing us to use a hybrid retrieval approach that is both effective and efficient.
Training a classifier on web-crawled data demands learning algorithms that are robust to annotation errors and irrelevant examples. This paper builds upon the recent empirical observation that applying unsupervised contrastive learning to noisy, web-crawled datasets yields a feature representation under which the in-distribution (ID) and out-of-distribution (OOD) samples are linearly separable. We show that direct estimation of the separating hyperplane can indeed offer an accurate detection of OOD samples, and yet, surprisingly, this detection does not translate into gains in classification accuracy. Digging deeper into this phenomenon, we discover that the near-perfect detection misses a type of clean examples that are valuable for supervised learning. These examples often represent visually simple images, which are relatively easy to identify as clean examples using standard loss- or distance-based methods despite being poorly separated from the OOD distribution using unsupervised learning. Because we further observe a low correlation with SOTA metrics, this urges us to propose a hybrid solution that alternates between noise detection using linear separation and a state-of-the-art (SOTA) small-loss approach. When combined with the SOTA algorithm PLS, we substantially improve SOTA results for real-world image classification in the presence of web noise github.com/PaulAlbert31/LSA
In the realm of autonomous driving, accurate 3D perception is the foundation. However, developing such models relies on extensive human annotations -- a process that is both costly and labor-intensive. To address this challenge from a data representation learning perspective, we introduce SuperFlow, a novel framework designed to harness consecutive LiDAR-camera pairs for establishing spatiotemporal pretraining objectives. SuperFlow stands out by integrating two key designs: 1) a dense-to-sparse consistency regularization, which promotes insensitivity to point cloud density variations during feature learning, and 2) a flow-based contrastive learning module, carefully crafted to extract meaningful temporal cues from readily available sensor calibrations. To further boost learning efficiency, we incorporate a plug-and-play view consistency module that enhances the alignment of the knowledge distilled from camera views. Extensive comparative and ablation studies across 11 heterogeneous LiDAR datasets validate our effectiveness and superiority. Additionally, we observe several interesting emerging properties by scaling up the 2D and 3D backbones during pretraining, shedding light on the future research of 3D foundation models for LiDAR-based perception.
Recent studies empirically indicate that language models (LMs) encode rich world knowledge beyond mere semantics, attracting significant attention across various fields. However, in the recommendation domain, it remains uncertain whether LMs implicitly encode user preference information. Contrary to prevailing understanding that LMs and traditional recommenders learn two distinct representation spaces due to the huge gap in language and behavior modeling objectives, this work re-examines such understanding and explores extracting a recommendation space directly from the language representation space. Surprisingly, our findings demonstrate that item representations, when linearly mapped from advanced LM representations, yield superior recommendation performance. This outcome suggests the possible homomorphism between the advanced language representation space and an effective item representation space for recommendation, implying that collaborative signals may be implicitly encoded within LMs. Motivated by these findings, we explore the possibility of designing advanced collaborative filtering (CF) models purely based on language representations without ID-based embeddings. To be specific, we incorporate several crucial components to build a simple yet effective model, with item titles as the input. Empirical results show that such a simple model can outperform leading ID-based CF models, which sheds light on using language representations for better recommendation. Moreover, we systematically analyze this simple model and find several key features for using advanced language representations: a good initialization for item representations, zero-shot recommendation abilities, and being aware of user intention. Our findings highlight the connection between language modeling and behavior modeling, which can inspire both natural language processing and recommender system communities.
Continuous learning from an immense volume of data streams becomes exceptionally critical in the internet era. However, data streams often do not conform to the same distribution over time, leading to a phenomenon called concept drift. Since a fixed static model is unreliable for inferring concept-drifted data streams, establishing an adaptive mechanism for detecting concept drift is crucial. Current methods for concept drift detection primarily assume that the labels or error rates of downstream models are given and/or underlying statistical properties exist in data streams. These approaches, however, struggle to address high-dimensional data streams with intricate irregular distribution shifts, which are more prevalent in real-world scenarios. In this paper, we propose MCD-DD, a novel concept drift detection method based on maximum concept discrepancy, inspired by the maximum mean discrepancy. Our method can adaptively identify varying forms of concept drift by contrastive learning of concept embeddings without relying on labels or statistical properties. With thorough experiments under synthetic and real-world scenarios, we demonstrate that the proposed method outperforms existing baselines in identifying concept drifts and enables qualitative analysis with high explainability.
Does popular music from the 60s sound different than that of the 90s? Prior study has shown that there would exist some variations of patterns and regularities related to instrumentation changes and growing loudness across multi-decadal trends. This indicates that perceiving the era of a song from musical features such as audio and artist information is possible. Music era information can be an important feature for playlist generation and recommendation. However, the release year of a song can be inaccessible in many circumstances. This paper addresses a novel task of music era recognition. We formulate the task as a music classification problem and propose solutions based on supervised contrastive learning. An audio-based model is developed to predict the era from audio. For the case where the artist information is available, we extend the audio-based model to take multimodal inputs and develop a framework, called MultiModal Contrastive (MMC) learning, to enhance the training. Experimental result on Million Song Dataset demonstrates that the audio-based model achieves 54% in accuracy with a tolerance of 3-years range; incorporating the artist information with the MMC framework for training leads to 9% improvement further.