相关论文: Contrast Is All You Need

Contrastive learning has shown outstanding performances in both supervised and unsupervised learning, and has recently been introduced to solve weakly supervised learning problems such as semi-supervised learning and noisy label learning.…

Recent advances in vision language models (VLM) have been driven by contrastive models such as CLIP, which learn to associate visual information with their corresponding text descriptions. However, these models have limitations in…

Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack principled guarantees on coverage…

Contrastive learning has proven useful in many applications where access to labelled data is limited. The lack of annotated data is particularly problematic in medical image segmentation as it is difficult to have clinical experts manually…

The scarcity of annotated data has sparked significant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medical visual representation learning. However, existing research overlooks the…

This paper presents miCSE, a mutual information-based contrastive learning framework that significantly advances the state-of-the-art in few-shot sentence embedding. The proposed approach imposes alignment between the attention pattern of…

Multimodal models like CLIP have gained significant attention due to their remarkable zero-shot performance across various tasks. However, studies have revealed that CLIP can inadvertently learn spurious associations between target…

Contrastive Language-Image Pretraining (CLIP) models excel at understanding image-text relationships but struggle with adapting to new data without forgetting prior knowledge. To address this, models are typically fine-tuned using both new…

Contrastive Learning (CL) performances as a rising approach to address the challenge of sparse and noisy recommendation data. Although having achieved promising results, most existing CL methods only perform either hand-crafted data or…

With the fast-growing number of classification models being produced every day, numerous model interpretation and comparison solutions have also been introduced. For example, LIME and SHAP can interpret what input features contribute more…

Text classification is a crucial and fundamental task in web content mining. Compared with the previous learning paradigm of pre-training and fine-tuning by cross entropy loss, the recently proposed supervised contrastive learning approach…

Few-shot learning is an established topic in natural images for years, but few work is attended to histology images, which is of high clinical value since well-labeled datasets and rare abnormal samples are expensive to collect. Here, we…

As the most essential property in a video, motion information is critical to a robust and generalized video representation. To inject motion dynamics, recent works have adopted frame difference as the source of motion information in video…

The impressive performance of GPT-3 using natural language prompts and in-context learning has inspired work on better fine-tuning of moderately-sized models under this paradigm. Following this line of work, we present a contrastive…

Contrastive learning methods enforce label distance relationships in feature space to improve representation capability for regression models. However, these methods highly depend on label information to correctly recover ordinal…

Recently, the advent of Large Visual-Language Models (LVLMs) has received increasing attention across various domains, particularly in the field of visual document understanding (VDU). Different from conventional vision-language tasks, VDU…

Unsupervised contrastive learning has achieved outstanding success, while the mechanism of contrastive loss has been less studied. In this paper, we concentrate on the understanding of the behaviours of unsupervised contrastive loss. We…

Pretext Invariant Representation Learning (PIRL) followed by Supervised Fine-Tuning (SFT) has become a standard paradigm for learning with limited labels. We extend this approach to the Positive Unlabeled (PU) setting, where only a small…

Current debiasing approaches often result a degradation in model capabilities such as factual accuracy and knowledge retention. Through systematic evaluation across multiple benchmarks, we demonstrate that existing debiasing methods face…

Graph Neural Networks (GNNs) are powerful tools for recommendation systems, but they often struggle under data sparsity and noise. To address these issues, we implemented LightGCL, a graph contrastive learning model that uses Singular Value…