Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training?

• URL: http://arxiv.org/abs/2607.13192v1
• Date: Tue, 14 Jul 2026 18:45:04 GMT
• Title: Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training?
• Abstract summary: Self-supervision is a powerful technique for learning visual representations from unlabeled data.<n>Existing techniques adopt a two-stage approach for self-supervised learning (SSL): a pretraining stage on unlabeled data followed by a finetuning stage on labeled data.<n>We investigate whether jointly optimizing the self-supervised and supervised objectives during training provides a better alternative.
• Score: 0.07340017786387766
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervision is a powerful technique for learning visual representations from unlabeled data. Existing techniques primarily adopt a two-stage approach for self-supervised learning (SSL): a pretraining stage on unlabeled data followed by a finetuning stage on labeled data. While this pipeline has demonstrated extreme effectiveness, the interaction between self-supervised and supervised learning objectives remains insufficiently understood. In this work, we systematically investigate whether jointly optimizing the self-supervised and supervised objectives during training provides a better alternative. We compare two training paradigms: (1) the aforementioned pretraining followed by finetuning (PFT) and (2) joint training (JT), where self-supervised and supervised losses are optimized simultaneously in the same network. Across eight representative SSL methods and diverse computer vision tasks on natural, medical, crisis response, and remote sensing data, we evaluate performance under varying percentages of labeled data. Our results reveal that the relative effectiveness of PFT and JT depends strongly on the task at hand, the availability of labeled data, and the complexity of the domain. We find that JT consistently improves data and training efficiency while being robust in low-label settings, while PFT is more reliable in more specialized domains. We further analyze representation quality, robustness, and cross-domain generalization, providing new insights into how self-supervised and supervised objectives interact during optimization. We establish a comprehensive empirical benchmark for hybrid SSL-based semi-supervised learning and offer practical guidance for selecting appropriate training strategies across diverse vision applications.

Related papers

• Underlying Semantic Diffusion for Effective and Efficient In-Context Learning [113.4003355229632]
  Underlying Semantic Diffusion (US-Diffusion) is an enhanced diffusion model that boosts underlying semantics learning, computational efficiency, and in-context learning capabilities.<n>We present a Feedback-Aided Learning (FAL) framework, which leverages feedback signals to guide the model in capturing semantic details.<n>We also propose a plug-and-play Efficient Sampling Strategy (ESS) for dense sampling at time steps with high-noise levels.
  arXiv  Detail & Related papers  (2025-03-06T03:06:22Z)
• Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate [118.37653302885607]
  We present the Modality Integration Rate (MIR), an effective, robust, and generalized metric to indicate the multi-modal pre-training quality of Large Vision Language Models (LVLMs) MIR is indicative about training data selection, training strategy schedule, and model architecture design to get better pre-training results.
  arXiv  Detail & Related papers  (2024-10-09T17:59:04Z)
• In-Domain Self-Supervised Learning Improves Remote Sensing Image Scene Classification [5.323049242720532]
  Self-supervised learning has emerged as a promising approach for remote sensing image classification. We present a study of different self-supervised pre-training strategies and evaluate their effect across 14 downstream datasets.
  arXiv  Detail & Related papers  (2023-07-04T10:57:52Z)
• ALP: Action-Aware Embodied Learning for Perception [60.64801970249279]
  We introduce Action-Aware Embodied Learning for Perception (ALP) ALP incorporates action information into representation learning through a combination of optimizing a reinforcement learning policy and an inverse dynamics prediction objective. We show that ALP outperforms existing baselines in several downstream perception tasks.
  arXiv  Detail & Related papers  (2023-06-16T21:51:04Z)
• Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics [9.741019160068388]
  We introduce the Cost-Sensitive Self-Training (CSST) framework which generalizes the self-training-based methods for optimizing non-decomposable metrics. Our results demonstrate that CSST achieves an improvement over the state-of-the-art in majority of the cases across datasets and objectives.
  arXiv  Detail & Related papers  (2023-04-28T10:31:12Z)
• Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methods [29.141145775835106]
  Given a fixed FLOP budget, what are the best datasets, models, and (self-supervised) training methods for obtaining high accuracy on representative visual tasks? We examine five large-scale datasets (JFT-300M, ALIGN, ImageNet-1K, ImageNet-21K, and COCO) and six pre-training methods (CLIP, DINO, SimCLR, BYOL, Masked Autoencoding, and supervised) Our results call into question the commonly-held assumption that self-supervised methods inherently scale to large, uncurated data.
  arXiv  Detail & Related papers  (2022-09-30T17:04:55Z)
• Towards Sequence-Level Training for Visual Tracking [60.95799261482857]
  This work introduces a sequence-level training strategy for visual tracking based on reinforcement learning. Four representative tracking models, SiamRPN++, SiamAttn, TransT, and TrDiMP, consistently improve by incorporating the proposed methods in training.
  arXiv  Detail & Related papers  (2022-08-11T13:15:36Z)
• Self-Supervision Can Be a Good Few-Shot Learner [42.06243069679068]
  We propose an effective unsupervised few-shot learning method, learning representations with self-supervision. Specifically, we maximize the mutual information (MI) of instances and their representations with a low-bias MI estimator. We show that self-supervised pre-training can outperform supervised pre-training under the appropriate conditions.
  arXiv  Detail & Related papers  (2022-07-19T10:23:40Z)
• UniVIP: A Unified Framework for Self-Supervised Visual Pre-training [50.87603616476038]
  We propose a novel self-supervised framework to learn versatile visual representations on either single-centric-object or non-iconic dataset. Massive experiments show that UniVIP pre-trained on non-iconic COCO achieves state-of-the-art transfer performance. Our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2.5% with the same pre-training epochs in linear probing.
  arXiv  Detail & Related papers  (2022-03-14T10:04:04Z)
• SLIP: Self-supervision meets Language-Image Pre-training [79.53764315471543]
  We study whether self-supervised learning can aid in the use of language supervision for visual representation learning. We introduce SLIP, a multi-task learning framework for combining self-supervised learning and CLIP pre-training. We find that SLIP enjoys the best of both worlds: better performance than self-supervision and language supervision.
  arXiv  Detail & Related papers  (2021-12-23T18:07:13Z)

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.