Prompt learning has emerged as an effective and data-efficient technique in large Vision-Language Models (VLMs). However, when adapting VLMs to specialized domains such as remote sensing and medical imaging, domain prompt learning remains underexplored. While large-scale domain-specific foundation models can help tackle this challenge, their concentration on a single vision level makes it challenging to prompt both vision and language modalities. To overcome this, we propose to leverage domain-specific knowledge from domain-specific foundation models to transfer the robust recognition ability of VLMs from generalized to specialized domains, using quaternion networks. Specifically, the proposed method involves using domain-specific vision features from domain-specific foundation models to guide the transformation of generalized contextual embeddings from the language branch into a specialized space within the quaternion networks. Moreover, we present a hierarchical approach that generates vision prompt features by analyzing intermodal relationships between hierarchical language prompt features and domain-specific vision features. In this way, quaternion networks can effectively mine the intermodal relationships in the specific domain, facilitating domain-specific vision-language contrastive learning. Extensive experiments on domain-specific datasets show that our proposed method achieves new state-of-the-art results in prompt learning.
Self-supervised Multi-modal Contrastive Learning (SMCL) remarkably advances modern Vision-Language Pre-training (VLP) models by aligning visual and linguistic modalities. Due to noises in web-harvested text-image pairs, however, scaling up training data volume in SMCL presents considerable obstacles in terms of computational cost and data inefficiency. To improve data efficiency in VLP, we propose Text-aware Image Mixing (TiMix), which integrates mix-based data augmentation techniques into SMCL, yielding significant performance improvements without significantly increasing computational overhead. We provide a theoretical analysis of TiMixfrom a mutual information (MI) perspective, showing that mixed data samples for cross-modal contrastive learning implicitly serve as a regularizer for the contrastive loss. The experimental results demonstrate that TiMix exhibits a comparable performance on downstream tasks, even with a reduced amount of training data and shorter training time, when benchmarked against existing methods. This work empirically and theoretically demonstrates the potential of data mixing for data-efficient and computationally viable VLP, benefiting broader VLP model adoption in practical scenarios.
Incomplete multi-view clustering becomes an important research problem, since multi-view data with missing values are ubiquitous in real-world applications. Although great efforts have been made for incomplete multi-view clustering, there are still some challenges: 1) most existing methods didn't make full use of multi-view information to deal with missing values; 2) most methods just employ the consistent information within multi-view data but ignore the complementary information; 3) For the existing incomplete multi-view clustering methods, incomplete multi-view representation learning and clustering are treated as independent processes, which leads to performance gap. In this work, we proposed a novel Incomplete Contrastive Multi-View Clustering method with high-confidence guiding (ICMVC). Firstly, we proposed a multi-view consistency relation transfer plus graph convolutional network to tackle missing values problem. Secondly, instance-level attention fusion and high-confidence guiding are proposed to exploit the complementary information while instance-level contrastive learning for latent representation is designed to employ the consistent information. Thirdly, an end-to-end framework is proposed to integrate multi-view missing values handling, multi-view representation learning and clustering assignment for joint optimization. Experiments compared with state-of-the-art approaches demonstrated the effectiveness and superiority of our method. Our code is publicly available at https://github.com/liunian-Jay/ICMVC.
Federated learning (FL) provides a decentralized machine learning paradigm where a server collaborates with a group of clients to learn a global model without accessing the clients' data. User heterogeneity is a significant challenge for FL, which together with the class-distribution imbalance further enhances the difficulty of FL. Great progress has been made in large vision-language models, such as Contrastive Language-Image Pre-training (CLIP), which paves a new way for image classification and object recognition. Inspired by the success of CLIP on few-shot and zero-shot learning, we use CLIP to optimize the federated learning between server and client models under its vision-language supervision. It is promising to mitigate the user heterogeneity and class-distribution balance due to the powerful cross-modality representation and rich open-vocabulary prior knowledge. In this paper, we propose the CLIP-guided FL (CLIP2FL) method on heterogeneous and long-tailed data. In CLIP2FL, the knowledge of the off-the-shelf CLIP model is transferred to the client-server models, and a bridge is built between the client and server. Specifically, for client-side learning, knowledge distillation is conducted between client models and CLIP to improve the ability of client-side feature representation. For server-side learning, in order to mitigate the heterogeneity and class-distribution imbalance, we generate federated features to retrain the server model. A prototype contrastive learning with the supervision of the text encoder of CLIP is introduced to generate federated features depending on the client-side gradients, and they are used to retrain a balanced server classifier.
Recent studies have shown that contrastive learning, like supervised learning, is highly vulnerable to backdoor attacks wherein malicious functions are injected into target models, only to be activated by specific triggers. However, thus far it remains under-explored how contrastive backdoor attacks fundamentally differ from their supervised counterparts, which impedes the development of effective defenses against the emerging threat. This work represents a solid step toward answering this critical question. Specifically, we define TRL, a unified framework that encompasses both supervised and contrastive backdoor attacks. Through the lens of TRL, we uncover that the two types of attacks operate through distinctive mechanisms: in supervised attacks, the learning of benign and backdoor tasks tends to occur independently, while in contrastive attacks, the two tasks are deeply intertwined both in their representations and throughout their learning processes. This distinction leads to the disparate learning dynamics and feature distributions of supervised and contrastive attacks. More importantly, we reveal that the specificities of contrastive backdoor attacks entail important implications from a defense perspective: existing defenses for supervised attacks are often inadequate and not easily retrofitted to contrastive attacks. We also explore several alternative defenses and discuss their potential challenges. Our findings highlight the need for defenses tailored to the specificities of contrastive backdoor attacks, pointing to promising directions for future research.
While recent model-free Reinforcement Learning (RL) methods have demonstrated human-level effectiveness in gaming environments, their success in everyday tasks like visual navigation has been limited, particularly under significant appearance variations. This limitation arises from (i) poor sample efficiency and (ii) over-fitting to training scenarios. To address these challenges, we present a world model that learns invariant features using (i) contrastive unsupervised learning and (ii) an intervention-invariant regularizer. Learning an explicit representation of the world dynamics i.e. a world model, improves sample efficiency while contrastive learning implicitly enforces learning of invariant features, which improves generalization. However, the na\"ive integration of contrastive loss to world models is not good enough, as world-model-based RL methods independently optimize representation learning and agent policy. To overcome this issue, we propose an intervention-invariant regularizer in the form of an auxiliary task such as depth prediction, image denoising, image segmentation, etc., that explicitly enforces invariance to style interventions. Our method outperforms current state-of-the-art model-based and model-free RL methods and significantly improves on out-of-distribution point navigation tasks evaluated on the iGibson benchmark. With only visual observations, we further demonstrate that our approach outperforms recent language-guided foundation models for point navigation, which is essential for deployment on robots with limited computation capabilities. Finally, we demonstrate that our proposed model excels at the sim-to-real transfer of its perception module on the Gibson benchmark.
Inspired by the success of contrastive learning, we systematically examine recommendation losses, including listwise (softmax), pairwise (BPR), and pointwise (MSE and CCL) losses. In this endeavor, we introduce InfoNCE+, an optimized generalization of InfoNCE with balance coefficients, and highlight its performance advantages, particularly when aligned with our new decoupled contrastive loss, MINE+. We also leverage debiased InfoNCE to debias pointwise recommendation loss (CCL) as Debiased CCL. Interestingly, our analysis reveals that linear models like iALS and EASE are inherently debiased. Empirical results demonstrates the effectiveness of MINE+ and Debiased-CCL.
In this paper, we perform a systemic examination of the recommendation losses, including listwise (softmax), pairwise(BPR), and pointwise (mean-squared error, MSE, and Cosine Contrastive Loss, CCL) losses through the lens of contrastive learning. We introduce and study both debiased InfoNCE and mutual information neural estimator (MINE), for the first time, under the recommendation setting. We also relate and differentiate these two losses with the BPR loss through the lower bound analysis. Furthermore, we present the debiased pointwise loss (for both MSE and CCL) and theoretically certify both iALS and EASE, two of the most popular linear models, are inherently debiased. The empirical experimental results demonstrate the effectiveness of the debiased losses and newly introduced mutual-information losses outperform the existing (biased) ones.
Objective: Biomedical Knowledge Graphs play a pivotal role in various biomedical research domains. Concurrently, term clustering emerges as a crucial step in constructing these knowledge graphs, aiming to identify synonymous terms. Due to a lack of knowledge, previous contrastive learning models trained with Unified Medical Language System (UMLS) synonyms struggle at clustering difficult terms and do not generalize well beyond UMLS terms. In this work, we leverage the world knowledge from Large Language Models (LLMs) and propose Contrastive Learning for Representing Terms via Explanations (CoRTEx) to enhance term representation and significantly improves term clustering. Materials and Methods: The model training involves generating explanations for a cleaned subset of UMLS terms using ChatGPT. We employ contrastive learning, considering term and explanation embeddings simultaneously, and progressively introduce hard negative samples. Additionally, a ChatGPT-assisted BIRCH algorithm is designed for efficient clustering of a new ontology. Results: We established a clustering test set and a hard negative test set, where our model consistently achieves the highest F1 score. With CoRTEx embeddings and the modified BIRCH algorithm, we grouped 35,580,932 terms from the Biomedical Informatics Ontology System (BIOS) into 22,104,559 clusters with O(N) queries to ChatGPT. Case studies highlight the model's efficacy in handling challenging samples, aided by information from explanations. Conclusion: By aligning terms to their explanations, CoRTEx demonstrates superior accuracy over benchmark models and robustness beyond its training set, and it is suitable for clustering terms for large-scale biomedical ontologies.
X (formerly Twitter) has evolved into a contemporary agora, offering a platform for individuals to express opinions and viewpoints on current events. The majority of the topics discussed on Twitter are directly related to ongoing events, making it an important source for monitoring public discourse. However, linking tweets to specific news presents a significant challenge due to their concise and informal nature. Previous approaches, including topic models, graph-based models, and supervised classifiers, have fallen short in effectively capturing the unique characteristics of tweets and articles. Inspired by the success of the CLIP model in computer vision, which employs contrastive learning to model similarities between images and captions, this paper introduces a contrastive learning approach for training a representation space where linked articles and tweets exhibit proximity. We present our contrastive learning approach, CATBERT (Contrastive Articles Tweets BERT), leveraging pre-trained BERT models. The model is trained and tested on a dataset containing manually labeled English and Polish tweets and articles related to the Russian-Ukrainian war. We evaluate CATBERT's performance against traditional approaches like LDA, and the novel method based on OpenAI embeddings, which has not been previously applied to this task. Our findings indicate that CATBERT demonstrates superior performance in associating tweets with relevant news articles. Furthermore, we demonstrate the performance of the models when applied to finding the main topic -- represented by an article -- of the whole cascade of tweets. In this new task, we report the performance of the different models in dependence on the cascade size.
Chromosome recognition is an essential task in karyotyping, which plays a vital role in birth defect diagnosis and biomedical research. However, existing classification methods face significant challenges due to the inter-class similarity and intra-class variation of chromosomes. To address this issue, we propose a supervised contrastive learning strategy that is tailored to train model-agnostic deep networks for reliable chromosome classification. This method enables extracting fine-grained chromosomal embeddings in latent space. These embeddings effectively expand inter-class boundaries and reduce intra-class variations, enhancing their distinctiveness in predicting chromosome types. On top of two large-scale chromosome datasets, we comprehensively validate the power of our contrastive learning strategy in boosting cutting-edge deep networks such as Transformers and ResNets. Extensive results demonstrate that it can significantly improve models' generalization performance, with an accuracy improvement up to +4.5%. Codes and pretrained models will be released upon acceptance of this work.
Recently, patch-wise contrastive learning is drawing attention for the image translation by exploring the semantic correspondence between the input and output images. To further explore the patch-wise topology for high-level semantic understanding, here we exploit the graph neural network to capture the topology-aware features. Specifically, we construct the graph based on the patch-wise similarity from a pretrained encoder, whose adjacency matrix is shared to enhance the consistency of patch-wise relation between the input and the output. Then, we obtain the node feature from the graph neural network, and enhance the correspondence between the nodes by increasing mutual information using the contrastive loss. In order to capture the hierarchical semantic structure, we further propose the graph pooling. Experimental results demonstrate the state-of-art results for the image translation thanks to the semantic encoding by the constructed graphs.
We present FoundationPose, a unified foundation model for 6D object pose estimation and tracking, supporting both model-based and model-free setups. Our approach can be instantly applied at test-time to a novel object without fine-tuning, as long as its CAD model is given, or a small number of reference images are captured. We bridge the gap between these two setups with a neural implicit representation that allows for effective novel view synthesis, keeping the downstream pose estimation modules invariant under the same unified framework. Strong generalizability is achieved via large-scale synthetic training, aided by a large language model (LLM), a novel transformer-based architecture, and contrastive learning formulation. Extensive evaluation on multiple public datasets involving challenging scenarios and objects indicate our unified approach outperforms existing methods specialized for each task by a large margin. In addition, it even achieves comparable results to instance-level methods despite the reduced assumptions. Project page: https://nvlabs.github.io/FoundationPose/
Click-through rate (CTR) prediction is a vital task in industrial recommendation systems. Most existing methods focus on the network architecture design of the CTR model for better accuracy and suffer from the data sparsity problem. Especially in industrial recommendation systems, the widely applied negative sample down-sampling technique due to resource limitation worsens the problem, resulting in a decline in performance. In this paper, we propose \textbf{A}uxiliary Match \textbf{T}asks for enhancing \textbf{C}lick-\textbf{T}hrough \textbf{R}ate prediction accuracy (AT4CTR) by alleviating the data sparsity problem. Specifically, we design two match tasks inspired by collaborative filtering to enhance the relevance modeling between user and item. As the "click" action is a strong signal which indicates the user's preference towards the item directly, we make the first match task aim at pulling closer the representation between the user and the item regarding the positive samples. Since the user's past click behaviors can also be treated as the user him/herself, we apply the next item prediction as the second match task. For both the match tasks, we choose the InfoNCE as their loss function. The two match tasks can provide meaningful training signals to speed up the model's convergence and alleviate the data sparsity. We conduct extensive experiments on one public dataset and one large-scale industrial recommendation dataset. The result demonstrates the effectiveness of the proposed auxiliary match tasks. AT4CTR has been deployed in the real industrial advertising system and has gained remarkable revenue.
Graph Contrastive Learning (GCL) is unsupervised graph representation learning that can obtain useful representation of unknown nodes. The node representation can be utilized as features of downstream tasks. However, GCL is vulnerable to poisoning attacks as with existing learning models. A state-of-the-art defense cannot sufficiently negate adverse effects by poisoned graphs although such a defense introduces adversarial training in the GCL. To achieve further improvement, pruning adversarial edges is important. To the best of our knowledge, the feasibility remains unexplored in the GCL domain. In this paper, we propose a simple defense for GCL, EdgePruner. We focus on the fact that the state-of-the-art poisoning attack on GCL tends to mainly add adversarial edges to create poisoned graphs, which means that pruning edges is important to sanitize the graphs. Thus, EdgePruner prunes edges that contribute to minimizing the contrastive loss based on the node representation obtained after training on poisoned graphs by GCL. Furthermore, we focus on the fact that nodes with distinct features are connected by adversarial edges in poisoned graphs. Thus, we introduce feature similarity between neighboring nodes to help more appropriately determine adversarial edges. This similarity is helpful in further eliminating adverse effects from poisoned graphs on various datasets. Finally, EdgePruner outputs a graph that yields the minimum contrastive loss as the sanitized graph. Our results demonstrate that pruning adversarial edges is feasible on six datasets. EdgePruner can improve the accuracy of node classification under the attack by up to 5.55% compared with that of the state-of-the-art defense. Moreover, we show that EdgePruner is immune to an adaptive attack.
With the surge in realistic text tampering, detecting fraudulent text in images has gained prominence for maintaining information security. However, the high costs associated with professional text manipulation and annotation limit the availability of real-world datasets, with most relying on synthetic tampering, which inadequately replicates real-world tampering attributes. To address this issue, we present the Real Text Manipulation (RTM) dataset, encompassing 14,250 text images, which include 5,986 manually and 5,258 automatically tampered images, created using a variety of techniques, alongside 3,006 unaltered text images for evaluating solution stability. Our evaluations indicate that existing methods falter in text forgery detection on the RTM dataset. We propose a robust baseline solution featuring a Consistency-aware Aggregation Hub and a Gated Cross Neighborhood-attention Fusion module for efficient multi-modal information fusion, supplemented by a Tampered-Authentic Contrastive Learning module during training, enriching feature representation distinction. This framework, extendable to other dual-stream architectures, demonstrated notable localization performance improvements of 7.33% and 6.38% on manual and overall manipulations, respectively. Our contributions aim to propel advancements in real-world text tampering detection. Code and dataset will be made available at https://github.com/DrLuo/RTM
Whole-slide image (WSI) analysis plays a crucial role in cancer diagnosis and treatment. In addressing the demands of this critical task, self-supervised learning (SSL) methods have emerged as a valuable resource, leveraging their efficiency in circumventing the need for a large number of annotations, which can be both costly and time-consuming to deploy supervised methods. Nevertheless, patch-wise representation may exhibit instability in performance, primarily due to class imbalances stemming from patch selection within WSIs. In this paper, we introduce Nearby Patch Contrastive Learning (NearbyPatchCL), a novel self-supervised learning method that leverages nearby patches as positive samples and a decoupled contrastive loss for robust representation learning. Our method demonstrates a tangible enhancement in performance for downstream tasks involving patch-level multi-class classification. Additionally, we curate a new dataset derived from WSIs sourced from the Canine Cutaneous Cancer Histology, thus establishing a benchmark for the rigorous evaluation of patch-level multi-class classification methodologies. Intensive experiments show that our method significantly outperforms the supervised baseline and state-of-the-art SSL methods with top-1 classification accuracy of 87.56%. Our method also achieves comparable results while utilizing a mere 1% of labeled data, a stark contrast to the 100% labeled data requirement of other approaches. Source code: https://github.com/nvtien457/NearbyPatchCL
Image Quality Assessment (IQA) has long been a research hotspot in the field of image processing, especially No-Reference Image Quality Assessment (NR-IQA). Due to the powerful feature extraction ability, existing Convolution Neural Network (CNN) and Transformers based NR-IQA methods have achieved considerable progress. However, they still exhibit limited capability when facing unknown authentic distortion datasets. To further improve NR-IQA performance, in this paper, a novel supervised contrastive learning (SCL) and Transformer-based NR-IQA model SaTQA is proposed. We first train a model on a large-scale synthetic dataset by SCL (no image subjective score is required) to extract degradation features of images with various distortion types and levels. To further extract distortion information from images, we propose a backbone network incorporating the Multi-Stream Block (MSB) by combining the CNN inductive bias and Transformer long-term dependence modeling capability. Finally, we propose the Patch Attention Block (PAB) to obtain the final distorted image quality score by fusing the degradation features learned from contrastive learning with the perceptual distortion information extracted by the backbone network. Experimental results on seven standard IQA datasets show that SaTQA outperforms the state-of-the-art methods for both synthetic and authentic datasets. Code is available at https://github.com/I2-Multimedia-Lab/SaTQA
Histopathological image classification is an important task in medical image analysis. Recent approaches generally rely on weakly supervised learning due to the ease of acquiring case-level labels from pathology reports. However, patch-level classification is preferable in applications where only a limited number of cases are available or when local prediction accuracy is critical. On the other hand, acquiring extensive datasets with localized labels for training is not feasible. In this paper, we propose a semi-supervised patch-level histopathological image classification model, named CLASS-M, that does not require extensively labeled datasets. CLASS-M is formed by two main parts: a contrastive learning module that uses separated Hematoxylin and Eosin images generated through an adaptive stain separation process, and a module with pseudo-labels using MixUp. We compare our model with other state-of-the-art models on two clear cell renal cell carcinoma datasets. We demonstrate that our CLASS-M model has the best performance on both datasets. Our code is available at github.com/BzhangURU/Paper_CLASS-M/tree/main
Multi-modal large language models (MLLMs) have been shown to efficiently integrate natural language with visual information to handle multi-modal tasks. However, MLLMs still face a fundamental limitation of hallucinations, where they tend to generate erroneous or fabricated information. In this paper, we address hallucinations in MLLMs from a novel perspective of representation learning. We first analyzed the representation distribution of textual and visual tokens in MLLM, revealing two important findings: 1) there is a significant gap between textual and visual representations, indicating unsatisfactory cross-modal representation alignment; 2) representations of texts that contain and do not contain hallucinations are entangled, making it challenging to distinguish them. These two observations inspire us with a simple yet effective method to mitigate hallucinations. Specifically, we introduce contrastive learning into MLLMs and use text with hallucination as hard negative examples, naturally bringing representations of non-hallucinative text and visual samples closer while pushing way representations of non-hallucinating and hallucinative text. We evaluate our method quantitatively and qualitatively, showing its effectiveness in reducing hallucination occurrences and improving performance across multiple benchmarks. On the MMhal-Bench benchmark, our method obtains a 34.66% /29.5% improvement over the baseline MiniGPT-4/LLaVA. Our code is available on https://github.com/X-PLUG/mPLUG-HalOwl/tree/main/hacl.