Related papers: DUET: 2D Structured and Approximately Equivariant …

Self-supervised learning (SSL) has emerged as a powerful technique for learning visual representations. While recent SSL approaches achieve strong results in global image understanding, they are limited in capturing the structured…

3D deep learning is a growing field of interest due to the vast amount of information stored in 3D formats. Triangular meshes are an efficient representation for irregular, non-uniform 3D objects. However, meshes are often challenging to…

Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious,…

We study the problem of learning permutation invariant representations that can capture "flexible" notions of containment. We formalize this problem via a measure theoretic definition of multisets, and obtain a theoretically-motivated…

Learning discrete representations of data is a central machine learning task because of the compactness of the representations and ease of interpretation. The task includes clustering and hash learning as special cases. Deep neural networks…

Self-supervised learning (SSL) aims to eliminate one of the major bottlenecks in representation learning - the need for human annotations. As a result, SSL holds the promise to learn representations from data in-the-wild, i.e., without the…

Machine learning systems may encounter unexpected problems when the data distribution changes in the deployment environment. A major reason is that certain combinations of domains and labels are not observed during training but appear in…

Self-Supervised Learning (SSL) for Vision Transformers (ViTs) has recently demonstrated considerable potential as a pre-training strategy for a variety of computer vision tasks, including image classification and segmentation, both in…

In the image domain, excellent representations can be learned by inducing invariance to content-preserving transformations via noise contrastive learning. In this paper, we generalize contrastive learning to a wider set of transformations,…

Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, facing two critical challenges:cross-modal misalignment bias…

Partially Supervised Multi-Task Learning (PS-MTL) aims to leverage knowledge across tasks when annotations are incomplete. Existing approaches, however, have largely focused on the simpler setting of homogeneous, dense prediction tasks,…

Continual learning aims to provide intelligent agents that are capable of learning continually a sequence of tasks, building on previously learned knowledge. A key challenge in this learning paradigm is catastrophically forgetting…

Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequential decision-making problems. Given the difficulty of designing such controllers manually,…

Pre-trained deep image representations are useful for post-training tasks such as classification through transfer learning, image retrieval, and object detection. Data augmentations are a crucial aspect of pre-training robust…

We propose a novel method of introducing structure into existing machine learning techniques by developing structure-based similarity and distance measures. To learn structural information, low-dimensional structure of the data is captured…

Self-supervision has shown outstanding results for natural language processing, and more recently, for image recognition. Simultaneously, vision transformers and its variants have emerged as a promising and scalable alternative to…

Self-supervised learning (SSL) has gained remarkable success, for which contrastive learning (CL) plays a key role. However, the recent development of new non-CL frameworks has achieved comparable or better performance with high improvement…

In-context learning (ICL) is a valuable capability exhibited by Transformers pretrained on diverse sequence tasks. However, previous studies have observed that ICL often conflicts with the model's inherent in-weight learning (IWL) ability.…

This paper investigates two techniques for developing efficient self-supervised vision transformers (EsViT) for visual representation learning. First, we show through a comprehensive empirical study that multi-stage architectures with…

In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels. A common task is to classify augmentations or different modalities of the data, which share semantic content (e.g. an object in…