Related papers: $f$-MICL: Understanding and Generalizing InfoNCE-b…

This paper targets the problem of multi-task dense prediction which aims to achieve simultaneous learning and inference on a bunch of multiple dense prediction tasks in a single framework. A core objective in design is how to effectively…

Recently, multimodal contrastive learning (MMCL) approaches, such as CLIP, have achieved a remarkable success in learning representations that are robust against distribution shift and generalize to new domains. Despite the empirical…

Human Activity Recognition is a field of research where input data can take many forms. Each of the possible input modalities describes human behaviour in a different way, and each has its own strengths and weaknesses. We explore the…

It is generally believed that robust training of extremely large networks is critical to their success in real-world applications. However, when taken to the extreme, methods that promote robustness can hurt the model's sensitivity to rare…

Meta-learning enables learning systems to adapt quickly to new tasks, similar to humans. Different meta-learning approaches all work under/with the mini-batch episodic training framework. Such framework naturally gives the information about…

Many datasets are biased, namely they contain easy-to-learn features that are highly correlated with the target class only in the dataset but not in the true underlying distribution of the data. For this reason, learning unbiased models…

Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. However, a major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression, a…

In this paper, we propose a simple yet effective contrastive knowledge distillation framework that achieves sample-wise logit alignment while preserving semantic consistency. Conventional knowledge distillation approaches exhibit…

This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias, wherein negative samples may encompass similar semantics (\eg labels). However, existing theories fall short in providing explanations for this…

Contrastive learning (CL) aims to preserve relational structure between samples by learning representations that reflect a similarity graph. Yet, the geometry of the resulting embeddings remains poorly understood. Here we show that weighted…

Most studies focused on information retrieval-based techniques for fault localization, which built representations for bug reports and source code files and matched their semantic vectors through similarity measurement. However, such…

The teacher-free online Knowledge Distillation (KD) aims to train an ensemble of multiple student models collaboratively and distill knowledge from each other. Although existing online KD methods achieve desirable performance, they often…

Large-scale contrastive learning models can learn very informative sentence embeddings, but are hard to serve online due to the huge model size. Therefore, they often play the role of "teacher", transferring abilities to small "student"…

Complex instruction-following with elaborate constraints is imperative for Large Language Models (LLMs). While existing methods have constructed data for complex instruction alignment, they all rely on a more advanced model, especially…

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…

Contrastive learning (CL) has shown great power in self-supervised learning due to its ability to capture insight correlations among large-scale data. Current CL models are biased to learn only the ability to discriminate positive and…

Contrastive learning (CL) has been successful as a powerful representation learning method. In this work we propose CLIM: Contrastive Learning with mutual Information Maximization, to explore the potential of CL on cross-domain sentiment…

Image and Point Clouds provide different information for robots. Finding the correspondences between data from different sensors is crucial for various tasks such as localization, mapping, and navigation. Learning-based descriptors have…

Labeling data is often very time consuming and expensive, leaving us with a majority of unlabeled data. Self-supervised representation learning methods such as SimCLR (Chen et al., 2020) or BYOL (Grill et al., 2020) have been very…

Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong semantic information. However, to optimize CSL with a loss…