Contrastive knowledge transfer from CLIP for open vocabulary object detection

Accurate modeling of disease progression is essential for comprehending the heterogeneous neuropathologies such as Alzheimer's Disease (AD). Traditional neuroimaging analysis often confound disease effects with normal aging, complicating the differential diagnosis. Recent advancements in deep learning have catalyzed the development of disentanglement techniques in Autoencoder networks, aiming to segregate longitudinal changes attributable to aging from those due to disease-specific alterations within the latent space. However, existing longitudinal disentanglement methods usually model disease as a single axis factor which ignores the complexity and heterogeneity of Alzheimer's Disease. In response to this issue, we propose a novel Surface-based Multi-axis Disentanglement framework.This framework posits multiple disease axes within the latent space, enhancing the model's capacity to encapsulate the multifaceted nature of AD, which includes various disease trajectories. To assign axes to data trajectories without explicit ground truth labels, we implement a longitudinal contrastive loss leveraging self-supervision, thereby refining the separation of disease trajectories. Evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset ( ), our model demonstrates superior performance in delineating between cognitively normal (CN), mild cognitive impairment (MCI), and AD subjects,classification of stable MCI vs converting MCI and Amyloid status, compared to the single-axis model. This is further substantiated through an ablation study on the contrastive loss, underscoring the utility of our multi-axis approach in capturing the complex progression patterns of AD. The code is available at: https://github.com/jianweizhang17/MultiAxisDisentanglement.git.

Unsupervised anomaly detection by densely contrastive learning for time series data

Metonymy resolution (MR) is a crucial challenge in natural language understanding and information retrieval. Recent large-scale pre-trained language models have shown promising results in various natural language processing (NLP) tasks, including MR. Despite these achievements, current models still struggle in many real-world scenarios. Since these models rely heavily on contextual information and ignore entity information, they are prone to extract irrelevant features and overfit when fine-tuned with less training data. In this article, we propose a mixed information bottleneck framework to address the above issues, which learns optimal data representations based on the principle of minimal sufficiency. Our model can effectively mitigate irrelevant features in context and entity by using different types of information bottlenecks for entity and context information separately while reducing the dimensionality of latent representations. We show that our approach achieves state-of-the-art performance on three benchmark datasets for location MR, outperforming previous Bert-based methods by a large margin. Ablation studies and qualitative analysis show the effectiveness of our models in reducing dimensionality while extracting more relevant features.

In this investigation, we propose a solution for the author’s gender identification task called AGI-P. This task has several real-world applications across different fields, such as marketing and advertising, forensic linguistics, sociology, recommendation systems, language processing, historical analysis, education, and language learning. We created a new dataset to evaluate our proposed method. The dataset is balanced in terms of gender using a random sampling method and consists of 1944 samples in total. We use accuracy as an evaluation measure and compare the performance of the proposed solution (AGI-P) against state-of-the-art machine learning classifiers and fine-tuned pre-trained multilingual language models such as DistilBERT, mBERT, XLM-RoBERTa, and Multilingual DEBERTa. In this regard, we also propose a customized fine-tuning strategy that improves the accuracy of the pre-trained language models for the author gender identification task. Our extensive experimental studies reveal that our solution (AGI-P) outperforms the well-known machine learning classifiers and fine-tuned pre-trained multilingual language models with an accuracy level of 92.03%. Moreover, the pre-trained multilingual language models, fine-tuned with the proposed customized strategy, outperform the fine-tuned pre-trained language models using an out-of-the-box fine-tuning strategy. The codebase and the corpus will be publicly available for scholars in this area upon publication.

Korean is the native and official language spoken by Chinese-Korean people, and Weibo is a social media software with a huge number of users in China. Currently, there is few studies related to sentiment analysis of Korean-language Weibo texts posted by Chinese-Korean users. In this paper, we propose a sentiment classification method for Chinese-Korean Weibo based on pre-trained language model and transfer learning. Firstly, we crawled the Chinese-Korean Weibo data from Sina Weibo and label them with sentiment to get the Chinese-Korean Weibo sentiment analysis (CKWSA) dataset. Secondly, to solve the problem of few training samples of the Chinese-Korean Weibo sentiment analysis dataset, we fine-tune the classifier based on the pre-trained Korean language model on the Korean Twitter sentiment analysis dataset to obtain the Korean Twitter sentiment classification model; and further fine-tune the model on CKWSA dataset to get Chinese-Korean Weibo sentiment classification model. The experiments show that the proposed classification method based on pre-trained language model and transfer learning has great performance, and there is an improvement compared other baselines on the Chinese-Korean Weibo sentiment analysis dataset.

Passage re-ranking is to obtain a permutation over the candidate passage set from retrieval stage. Re-rankers have been boomed by Pre-trained Language Models (PLMs) due to their overwhelming advantages in natural language understanding. However, existing PLM based re-rankers may easily suffer from vocabulary mismatch and lack of domain specific knowledge. To alleviate these problems, explicit knowledge contained in knowledge graph is carefully introduced in our work. Specifically, we employ the existing knowledge graph which is incomplete and noisy, and first apply it in passage re-ranking task. To leverage a reliable knowledge, we propose a novel knowledge graph distillation method and obtain a knowledge meta graph as the bridge between query and passage. To align both kinds of embedding in the latent space, we employ PLM as text encoder and graph neural network over knowledge meta graph as knowledge encoder. Besides, a novel knowledge injector is designed for the dynamic interaction between text and knowledge encoder. Experimental results demonstrate the effectiveness of our method especially in queries requiring in-depth domain knowledge.

Segmenting or detecting objects in sparse Lidar point clouds are two important tasks in autonomous driving to allow a vehicle to act safely in its 3D environment. The best performing methods in 3D semantic segmentation or object detection rely on a large amount of annotated data. Yet annotating 3D Lidar data for these tasks is tedious and costly. In this context, we propose a self-supervised pretraining method for 3D perception models that is tailored to autonomous driving data. Specifically, we leverage the availability of synchronized and calibrated image and Lidar sensors in autonomous driving setups for distilling self-supervised pre-trained image representations into 3D models. Hence, our method does not require any point cloud nor image annotations. The keyingredient of our method is the use of superpixels which are used to pool 3D point features and 2D pixel features in visually similar regions. We then train a 3D network on the self-supervised task of matching these pooled point features with the corresponding pooled image pixel features. The advantages of contrasting regions obtained by superpixels are that: (1) grouping together pixels and points of visually coherent regions leads to a more meaningful contrastive task that produces features well adapted to 3D semantic segmentation and 3D object detection; (2) all the different regions have the same weight in the contrastive loss regardless of the number of 3D points sampled in these regions; (3) it mitigates the noise produced by incorrect matching of points and pixels due to occlusions between the different sensors. Extensive experiments on autonomous driving datasets demonstrate the ability of our image-to-Lidar distillation strategy to produce 3D representations that transfer well on semantic segmentation and object detection tasks.

Knowledge Graph Embeddings (KGE) aim to map entities and relations to low dimensional spaces and have become the de-facto standard for knowledge graph completion. Most existing KGE methods suffer from the sparsity challenge, where it is harder to predict entities that appear less frequently in knowledge graphs. In this work, we propose a novel framework KRACL1 to alleviate the widespread sparsity in KGs with graph context and contrastive learning. Firstly, we propose the Knowledge Relational Attention Network (KRAT) to leverage the graph context by simultaneously projecting neighboring triples to different latent spaces and jointly aggregating messages with the attention mechanism. KRAT is capable of capturing the subtle semantic information and importance of different context triples as well as leveraging multi-hop information in knowledge graphs. Secondly, we propose the knowledge contrastive loss by combining the contrastive loss with cross entropy loss, which introduces more negative samples and thus enriches the feedback to sparse entities. Our experiments demonstrate that KRACL achieves superior results across various standard knowledge graph benchmarks, especially on WN18RR and NELL-995 which have large numbers of low in-degree entities. Extensive experiments also bear out KRACL’s effectiveness in handling sparse knowledge graphs and robustness against noisy triples.

Radiotherapy has become a common treatment option for head and neck (H&N) cancer, and organs at risk (OARs) need to be delineated to implement a high conformal dose distribution. Manual drawing of OARs is time consuming and inaccurate, so automatic drawing based on deep learning models has been proposed to accurately delineate the OARs. However, state-of-the-art performance usually requires a decent amount of delineation, but collecting pixel-level manual delineations is labor intensive and may not be necessary for representation learning. Encouraged by the recent progress in self-supervised learning, this study proposes and evaluates a novel multiview contrastive representation learning to boost the models from unlabelled data. The proposed learning architecture leverages three views of CTs (coronal, sagittal, and transverse plane) to collect positive and negative training samples. Specifically, a CT in 3D is first projected into three 2D views (coronal, sagittal, and transverse planes), then a convolutional neural network takes 3 views as inputs and outputs three individual representations in latent space, and finally, a contrastive loss is used to pull representation of different views of the same image closer (“positive pairs”) and push representations of views from different images (“negative pairs”) apart. To evaluate performance, we collected 220 CT images in H&N cancer patients. The experiment demonstrates that our method significantly improves quantitative performance over the state-of-the-art (from 83% to 86% in absolute Dice scores). Thus, our method provides a powerful and principled means to deal with the label-scarce problem.

Multi-task contrastive learning for automatic CT and X-ray diagnosis of COVID-19

This paper describes the models designated for the MEDIQA 2019 shared tasks by the team PANLP. We take advantages of the recent advances in pre-trained bidirectional transformer language models such as BERT (Devlin et al., 2018) and MT-DNN (Liu et al., 2019b). We find that pre-trained language models can significantly outperform traditional deep learning models. Transfer learning from the NLI task to the RQE task is also experimented, which proves to be useful in improving the results of fine-tuning MT-DNN large. A knowledge distillation process is implemented, to distill the knowledge contained in a set of models and transfer it into an single model, whose performance turns out to be comparable with that obtained by the ensemble of that set of models. Finally, for test submissions, model ensemble and a re-ranking process are implemented to boost the performances. Our models participated in all three tasks and ranked the 1st place for the RQE task, and the 2nd place for the NLI task, and also the 2nd place for the QA task.

Pre-trained Language Models (PLMs) have achieved remarkable performance for various language understanding tasks in IR systems, which require the fine-tuning process based on labeled training data. For low-resource scenarios, prompt-based learning for PLMs exploits prompts as task guidance and turns downstream tasks into masked language problems for effective few-shot fine-tuning. In most existing approaches, the high performance of prompt-based learning heavily relies on handcrafted prompts and verbalizers, which may limit the application of such approaches in real-world scenarios. To solve this issue, we present CP-Tuning, an end-to-end Contrastive Prompt Tuning framework for fine-tuning PLMs without any manual engineering of task-specific prompts and verbalizers. It is integrated with the task-invariant continuous prompt encoding technique with fully trainable prompt parameters. We further propose the pair-wise cost-sensitive contrastive learning procedure to optimize the model in order to achieve verbalizer-free class mapping and enhance the task-invariance of prompts. It explicitly learns to distinguish different classes and makes the decision boundary smoother by assigning different costs to easy and hard cases. Experiments over a variety of language understanding tasks and different PLMs show that CP-Tuning outperforms state-of-the-art methods.

Siamese networks usually consist of two parallel networks and each network is made of a backbone and some fully connected layers. The entire Siamese structure is trained by a loss function, while the similarity of the latent spaces of the two networks is decisive at the inference time. The weights of the network can be shared in Siamese networks. Therefore, in this paper, four weight-sharing mechanisms are proposed, and their effects on the performance of Siamese networks are investigated. These methods are named "full weight sharing," "partial weight sharing in FC," "partial weight sharing in CNN," and "without weight sharing." In this paper, four network backbones are examined and trained by employing the four aforementioned weight-sharing methods; two losses (proxy anchor loss and contrastive loss) are utilized for training. According to the obtained results, "partial weight sharing in FC" combined with contrastive loss has the best result on all backbones.

This study addresses the challenges of data noise and model interpretability in depression diagnosis by proposing an intelligent diagnostic framework based on real-world medical scenarios. Utilizing a labeled dataset of 11,188 Chinese online consultation records, we developed a dual-channel architecture integrating BERT/RoBERTa pre-trained models with the SHAP interpretability framework for depression severity classification. Experimental results demonstrated that the BERT model achieved 92% overall accuracy, with 93% accuracy specifically for severe depression detection. SHAP analysis revealed the model’s focus on clinically relevant features like suicidal tendencies and low mood, showing significant alignment with DSM-5 diagnostic criteria. The study confirms pre-trained models’ capability in extracting pathological semantics from medical texts, while the “prediction-interpretation” framework provides a technical prototype for overcoming clinical application barriers of black-box models.

Script event prediction aims to predict the subsequent event given the context. This requires the capability to infer the correlations between events. Recent works have attempted to improve event correlation reasoning by using pretrained language models and incorporating external knowledge (e.g., discourse relations). Though promising results have been achieved, some challenges still remain. First, the pretrained language models adopted by current works ignore event-level knowledge, resulting in an inability to capture the correlations between events well. Second, modeling correlations between events with discourse relations is limited because it can only capture explicit correlations between events with discourse markers, and cannot capture many implicit correlations. To this end, we propose a novel generative approach for this task, in which a pretrained language model is fine-tuned with an event-centric pretraining objective and predicts the next event within a generative paradigm. Specifically, we first introduce a novel event-level blank infilling strategy as the learning objective to inject event-level knowledge into the pretrained language model, and then design a likelihood-based contrastive loss for fine-tuning the generative model. Instead of using an additional prediction layer, we perform prediction by using sequence likelihoods generated by the generative model. Our approach models correlations between events in a soft way without any external knowledge. The likelihood-based prediction eliminates the need to use additional networks to make predictions and is somewhat interpretable since it scores each word in the event. Experimental results on the multi-choice narrative cloze (MCNC) task demonstrate that our approach achieves better results than other state-of-the-art baselines. Our code will be available at https://github.com/zhufq00/mcnc.