Related papers: Distractors-Immune Representation Learning with Cr…

Speech models may be affected by performance imbalance in different population subgroups, raising concerns about fair treatment across these groups. Prior attempts to mitigate unfairness either focus on user-defined subgroups, potentially…

Current contrastive learning methods use random transformations sampled from a large list of transformations, with fixed hyperparameters, to learn invariance from an unannotated database. Following previous works that introduce a small…

Speech emotion recognition is a challenge and an important step towards more natural human-computer interaction (HCI). The popular approach is multimodal emotion recognition based on model-level fusion, which means that the multimodal…

Contrastive learning between different views of the data achieves outstanding success in the field of self-supervised representation learning and the learned representations are useful in broad downstream tasks. Since all supervision…

Recently, self-supervised learning has attracted attention due to its remarkable ability to acquire meaningful representations for classification tasks without using semantic labels. This paper introduces a self-supervised learning…

What role do augmentations play in contrastive learning? Recent work suggests that good augmentations are label-preserving with respect to a specific downstream task. We complicate this picture by showing that label-destroying augmentations…

One property that remains lacking in image captions generated by contemporary methods is discriminability: being able to tell two images apart given the caption for one of them. We propose a way to improve this aspect of caption generation.…

Detecting Mild Cognitive Impairment from picture descriptions is critical yet challenging, especially in multilingual and multiple picture settings. Prior work has primarily focused on English speakers describing a single picture (e.g., the…

Contrastive learning is a well-established paradigm in representation learning. The standard framework of contrastive learning minimizes the distance between "similar" instances and maximizes the distance between dissimilar ones in the…

Contrastive Learning has shown impressive results on natural and medical images, without requiring annotated data. However, a particularity of medical images is the availability of meta-data (such as age or sex) that can be exploited for…

We propose a visual-linguistic representation learning approach within a self-supervised learning framework by introducing a new operation, loss, and data augmentation strategy. First, we generate diverse features for the image-text…

We propose Domain-Conditioned Meta-Contrastive Learning, a framework for improving the cross-domain generalization of vision-language models. While contrastive models such as CLIP achieve strong performance through large-scale training,…

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 self-supervised learning has become a prominent technique in representation learning. The main step in these methods is to contrast semantically similar and dissimilar pairs of samples. However, in the domain of Natural Language…

Adversarial perturbations are noise-like patterns that can subtly change the data, while failing an otherwise accurate classifier. In this paper, we propose to use such perturbations within a novel contrastive learning setup to build…

Noise robustness in keyword spotting remains a challenge as many models fail to overcome the heavy influence of noises, causing the deterioration of the quality of feature embeddings. We proposed a contrastive regularization method called…

Self-supervised representation learning has made significant leaps fueled by progress in contrastive learning, which seeks to learn transformations that embed positive input pairs nearby, while pushing negative pairs far apart. While…

Semantic search is an important task which objective is to find the relevant index from a database for query. It requires a retrieval model that can properly learn the semantics of sentences. Transformer-based models are widely used as…

Dense retrieval (DR) has shown promising results in information retrieval. In essence, DR requires high-quality text representations to support effective search in the representation space. Recent studies have shown that pre-trained…

In this paper, we focus on the self-supervised learning of visual correspondence using unlabeled videos in the wild. Our method simultaneously considers intra- and inter-video representation associations for reliable correspondence…