Beyond Instance Consistency: Investigating View Diversity in Self-supervised Learning
- URL: http://arxiv.org/abs/2509.11344v1
- Date: Sun, 14 Sep 2025 16:41:17 GMT
- Title: Beyond Instance Consistency: Investigating View Diversity in Self-supervised Learning
- Authors: Huaiyuan Qin, Muli Yang, Siyuan Hu, Peng Hu, Yu Zhang, Chen Gong, Hongyuan Zhu,
- Abstract summary: We investigate the effectiveness of self-supervised learning when instance consistency is not guaranteed.<n>We show that SSL can still learn meaningful representations even when positive pairs lack strict instance consistency.<n>Excessive diversity is found to reduce effectiveness, suggesting an optimal range for view diversity.
- Score: 40.22430098149745
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Self-supervised learning (SSL) conventionally relies on the instance consistency paradigm, assuming that different views of the same image can be treated as positive pairs. However, this assumption breaks down for non-iconic data, where different views may contain distinct objects or semantic information. In this paper, we investigate the effectiveness of SSL when instance consistency is not guaranteed. Through extensive ablation studies, we demonstrate that SSL can still learn meaningful representations even when positive pairs lack strict instance consistency. Furthermore, our analysis further reveals that increasing view diversity, by enforcing zero overlapping or using smaller crop scales, can enhance downstream performance on classification and dense prediction tasks. However, excessive diversity is found to reduce effectiveness, suggesting an optimal range for view diversity. To quantify this, we adopt the Earth Mover's Distance (EMD) as an estimator to measure mutual information between views, finding that moderate EMD values correlate with improved SSL learning, providing insights for future SSL framework design. We validate our findings across a range of settings, highlighting their robustness and applicability on diverse data sources.
Related papers
- Adversarial Robustness of Discriminative Self-Supervised Learning in Vision [0.0]
We evaluate the adversarial robustness of seven discriminative self-supervised models and one supervised model across diverse tasks.<n>Our findings suggest that discriminative SSL models generally exhibit better robustness to adversarial attacks compared to their supervised counterpart on ImageNet.
arXiv Detail & Related papers (2025-03-08T23:50:36Z) - On the Discriminability of Self-Supervised Representation Learning [38.598160031349686]
Self-supervised learning (SSL) has recently shown notable success in various visual tasks.<n>However, in terms of discriminability, SSL is still not on par with supervised learning (SL)<n>This paper identifies a key issue, the crowding problem," where features from different classes are not well-separated.
arXiv Detail & Related papers (2024-07-18T14:18:03Z) - The Common Stability Mechanism behind most Self-Supervised Learning
Approaches [64.40701218561921]
We provide a framework to explain the stability mechanism of different self-supervised learning techniques.
We discuss the working mechanism of contrastive techniques like SimCLR, non-contrastive techniques like BYOL, SWAV, SimSiam, Barlow Twins, and DINO.
We formulate different hypotheses and test them using the Imagenet100 dataset.
arXiv Detail & Related papers (2024-02-22T20:36:24Z) - A Probabilistic Model Behind Self-Supervised Learning [53.64989127914936]
In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels.
We present a generative latent variable model for self-supervised learning.
We show that several families of discriminative SSL, including contrastive methods, induce a comparable distribution over representations.
arXiv Detail & Related papers (2024-02-02T13:31:17Z) - Understanding Contrastive Learning Through the Lens of Margins [9.443122526245562]
Self-supervised learning, or SSL, holds the key to expanding the usage of machine learning in real-world tasks.
We use margins as a stepping stone for understanding how contrastive learning works at a deeper level.
arXiv Detail & Related papers (2023-06-20T13:28:27Z) - On Higher Adversarial Susceptibility of Contrastive Self-Supervised
Learning [104.00264962878956]
Contrastive self-supervised learning (CSL) has managed to match or surpass the performance of supervised learning in image and video classification.
It is still largely unknown if the nature of the representation induced by the two learning paradigms is similar.
We identify the uniform distribution of data representation over a unit hypersphere in the CSL representation space as the key contributor to this phenomenon.
We devise strategies that are simple, yet effective in improving model robustness with CSL training.
arXiv Detail & Related papers (2022-07-22T03:49:50Z) - Weak Augmentation Guided Relational Self-Supervised Learning [80.0680103295137]
We introduce a novel relational self-supervised learning (ReSSL) framework that learns representations by modeling the relationship between different instances.
Our proposed method employs sharpened distribution of pairwise similarities among different instances as textitrelation metric.
Experimental results show that our proposed ReSSL substantially outperforms the state-of-the-art methods across different network architectures.
arXiv Detail & Related papers (2022-03-16T16:14:19Z) - ReSSL: Relational Self-Supervised Learning with Weak Augmentation [68.47096022526927]
Self-supervised learning has achieved great success in learning visual representations without data annotations.
We introduce a novel relational SSL paradigm that learns representations by modeling the relationship between different instances.
Our proposed ReSSL significantly outperforms the previous state-of-the-art algorithms in terms of both performance and training efficiency.
arXiv Detail & Related papers (2021-07-20T06:53:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.