Related papers: Variance Covariance Regularization Enforces Pairwi…
Recent self-supervised methods for image representation learning are based on maximizing the agreement between embedding vectors from different views of the same image. A trivial solution is obtained when the encoder outputs constant…
Variance-Invariance-Covariance Regularization (VICReg) is a self-supervised learning (SSL) method that has shown promising results on a variety of tasks. However, the fundamental mechanisms underlying VICReg remain unexplored. In this…
Self-Supervised Learning (SSL) surmises that inputs and pairwise positive relationships are enough to learn meaningful representations. Although SSL has recently reached a milestone: outperforming supervised methods in many modalities\dots…
Self-supervised learning (SSL) has emerged as a powerful paradigm for representation learning by optimizing geometric objectives, such as invariance to augmentations, variance preservation, and feature decorrelation, without requiring…
Self-supervised learning (SSL) has recently advanced through non-contrastive methods that couple an invariance term with variance, covariance, or redundancy-reduction penalties. While such objectives shape first- and second-order statistics…
Self-supervised learning (SSL) has had great success in both computer vision. Most of the current mainstream computer vision SSL frameworks are based on Siamese network architecture. These approaches often rely on cleverly crafted loss…
In this paper, we argue that viewing VICReg-a popular self-supervised learning (SSL) method--through the lens of spectral embedding reveals a potential source of sub-optimality: it may struggle to generalize robustly to unseen data due to…
Multiview recognition has been well studied in the literature and achieves decent performance in object recognition and retrieval task. However, most previous works rely on supervised learning and some impractical underlying assumptions,…
Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deformations of the same input. Essentially, the model captures the…
Self-supervised learning (SSL) has emerged as a powerful paradigm for learning representations without labeled data, often by enforcing invariance to input transformations such as rotations or blurring. Recent studies have highlighted two…
Video representation learning is an increasingly important topic in machine learning research. We present Video JEPA with Variance-Covariance Regularization (VJ-VCR): a joint-embedding predictive architecture for self-supervised video…
Self-supervised learning (SSL) is a powerful technique for learning from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo can reach quality on par with supervised approaches.…
Joint-embedding self-supervised learning (SSL), the key paradigm for unsupervised representation learning from visual data, learns from invariances between semantically-related data pairs. We study the one-to-many mapping problem in SSL,…
Self-supervised learning (SSL) typically learns representations invariant to semantic-preserving augmentations. While effective for recognition, enforcing strong invariance can suppress transformation-dependent structure that is useful for…
One of the latest self-supervised learning (SSL) methods, VICReg, showed a great performance both in the linear evaluation and the fine-tuning evaluation. However, VICReg is proposed in computer vision and it learns by pulling…
Current multimodal models often suffer from shallow reasoning, leading to errors caused by incomplete or inconsistent thought processes. To address this limitation, we propose Self-Verification and Self-Rectification (SVSR), a unified…
Modern neural network optimization relies heavily on architectural priorssuch as Batch Normalization and Residual connectionsto stabilize training dynamics. Without these, or in low-data regimes with aggressive augmentation, low-bias…
Visual Geo-localization (VG) is a critical research area for identifying geo-locations from visual inputs, particularly in autonomous navigation for robotics and vehicles. Current VG methods often learn feature extractors from geo-labeled…
A desirable objective in self-supervised learning (SSL) is to avoid feature collapse. Whitening loss guarantees collapse avoidance by minimizing the distance between embeddings of positive pairs under the conditioning that the embeddings…
Training speaker-discriminative and robust speaker verification systems without speaker labels is still challenging and worthwhile to explore. In this study, we propose an effective self-supervised learning framework and a novel…