Related papers: SupCLAP: Controlling Optimization Trajectory Drift…

Contrastive learning (CL) has become a cornerstone of self-supervised pretraining (SSP) in foundation models, however, extending CL to pixel-wise representation, crucial for medical vision, remains an open problem. Standard CL formulates…

Recently, Supervised Contrastive Learning (SCL) has been shown to achieve excellent performance in most classification tasks. In SCL, a neural network is trained to optimize two objectives: pull an anchor and positive samples together in…

Support vector regression (SVR) is one of the most popular machine learning algorithms aiming to generate the optimal regression curve through maximizing the minimal margin of selected training samples, i.e., support vectors. Recent…

Sound source localization aims to localize objects emitting the sound in visual scenes. Recent works obtaining impressive results typically rely on contrastive learning. However, the common practice of randomly sampling negatives in prior…

Self-supervised pre-training methods based on contrastive learning or regression tasks can utilize more unlabeled data to improve the performance of automatic speech recognition (ASR). However, the robustness impact of combining the two…

Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams by deriving pseudo-rewards from majority voting consensus. However, existing TTRL methods rely…

Speech Emotion Recognition (SER) in real-world scenarios remains challenging due to severe class imbalance and the prevalence of spontaneous, natural speech. While recent approaches leverage self-supervised learning (SSL) representations…

Cross-domain recommendation (CDR) is a task that aims to improve the recommendation performance in a target domain by leveraging the information from source domains. Contrastive learning methods have been widely adopted among intra-domain…

ASR systems based on self-supervised acoustic pretraining and CTC fine-tuning achieve strong performance on native speech but remain sensitive to accent variability. We investigate supervised contrastive learning (SupCon) as a lightweight,…

Self-supervised learning has revolutionized representation learning by eliminating the need for labeled data. Contrastive learning methods, such as SimCLR, maximize the agreement between augmented views of an image but lack explicit…

Anomaly detection plays a critical role in Autonomous Vehicles (AVs) by identifying unusual behaviors through perception systems that could compromise safety and lead to hazardous situations. Current approaches, which often rely on…

Contrastive language-audio pretraining (CLAP) has achieved notable success in learning semantically rich audio representations and is widely adopted for various audio-related tasks. However, current CLAP models face several key limitations.…

Modern visual trackers usually construct online learning models under the assumption that the feature response has a Gaussian distribution with target-centered peak response. Nevertheless, such an assumption is implausible when there is…

Sign language recognition (SLR) is a machine learning task aiming to identify signs in videos. Due to the scarcity of annotated data, unsupervised methods like contrastive learning have become promising in this field. They learn meaningful…

We propose SCVRL, a novel contrastive-based framework for self-supervised learning for videos. Differently from previous contrast learning based methods that mostly focus on learning visual semantics (e.g., CVRL), SCVRL is capable of…

Distracted driving is one of the major reasons for vehicle accidents. Therefore, detecting distracted driving behaviors is of paramount importance to reduce the millions of deaths and injuries occurring worldwide. Distracted or anomalous…

Simultaneously accurate and reliable tracking control for quadrotors in complex dynamic environments is challenging. As aerodynamics derived from drag forces and moment variations are chaotic and difficult to precisely identify, most…

The remarkable success of large-scale contrastive pre-training has been largely driven by by vast yet static datasets. However, as the scaling paradigm evolves, this paradigm encounters a fundamental challenge when applied to dynamic data…

In this study, we proposed a novel semi-supervised training method that uses unlabeled data with a class distribution that is completely different from the target data or data without a target label. To this end, we introduce a contrastive…

Semi-supervised learning acts as an effective way to leverage massive unlabeled data. In this paper, we propose a novel training strategy, termed as Semi-supervised Contrastive Learning (SsCL), which combines the well-known contrastive loss…