Related papers: Object-aware Contrastive Learning for Debiased Sce…

Contrastive learning has recently demonstrated great potential for unsupervised pre-training in 3D scene understanding tasks. However, most existing work randomly selects point features as anchors while building contrast, leading to a clear…

Recent advancements in self-supervised learning have demonstrated that effective visual representations can be learned from unlabeled images. This has led to increased interest in applying self-supervised learning to the medical domain,…

We propose a supervised contrastive learning framework for video representation learning that leverages temporally global context. We introduce a video to image aggregation strategy that spatially arranges multiple frames from each video…

Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes sub-optimal for…

After a model is deployed on edge devices, it is desirable for these devices to learn from unlabeled data to continuously improve accuracy. Contrastive learning has demonstrated its great potential in learning from unlabeled data. However,…

Recent advances in self-supervised visual representation learning have paved the way for unsupervised methods tackling tasks such as object discovery and instance segmentation. However, discovering objects in an image with no supervision is…

Sound localization aims to find the source of the audio signal in the visual scene. However, it is labor-intensive to annotate the correlations between the signals sampled from the audio and visual modalities, thus making it difficult to…

Improving generalization is a major challenge in audio classification due to labeled data scarcity. Self-supervised learning (SSL) methods tackle this by leveraging unlabeled data to learn useful features for downstream classification…

Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to disentangle and…

Recently, vehicle re-identification methods based on deep learning constitute remarkable achievement. However, this achievement requires large-scale and well-annotated datasets. In constructing the dataset, assigning globally available…

Self-supervised representation learning for visual pre-training has achieved remarkable success with sample (instance or pixel) discrimination and semantics discovery of instance, whereas there still exists a non-negligible gap between…

Accurate and robust image-based geo-localization at a global scale is challenging due to diverse environments, visually ambiguous scenes, and the lack of distinctive landmarks in many regions. While contrastive learning methods show…

The recent success in human action recognition with deep learning methods mostly adopt the supervised learning paradigm, which requires significant amount of manually labeled data to achieve good performance. However, label collection is an…

In this paper, we introduce a novel approach to novel object captioning which employs relative contrastive learning to learn visual and semantic alignment. Our approach maximizes compatibility between regions and object tags in a…

Contrastive learning has shown promising potential in self-supervised spatio-temporal representation learning. Most works naively sample different clips to construct positive and negative pairs. However, we observe that this formulation…

Contrastive learning has recently shown immense potential in unsupervised visual representation learning. Existing studies in this track mainly focus on intra-image invariance learning. The learning typically uses rich intra-image…

In this paper, we tackle the problem of learning visual representations from unlabeled scene-centric data. Existing works have demonstrated the potential of utilizing the underlying complex structure within scene-centric data; still, they…

We propose a self-supervised method to learn feature representations from videos. A standard approach in traditional self-supervised methods uses positive-negative data pairs to train with contrastive learning strategy. In such a case,…

We present a new self-supervised pre-training of Vision Transformers for dense prediction tasks. It is based on a contrastive loss across views that compares pixel-level representations to global image representations. This strategy…

Labeling videos at scale is impractical. Consequently, self-supervised visual representation learning is key for efficient video analysis. Recent success in learning image representations suggests contrastive learning is a promising…