SCS-SupCon: 基于Sigmoid的共同与风格监督对比学习与自适应决策边界
SCS-SupCon: Sigmoid-based Common and Style Supervised Contrastive Learning with Adaptive Decision Boundaries
AI总结：
SCS-SupCon通过引入基于Sigmoid的对比损失和风格距离约束，提升细粒度图像分类性能。
摘要：
图像分类受到细微类间差异和显著类内变化的限制，这限制了现有对比学习方法的有效性。基于InfoNCE损失的监督对比方法面临负样本稀释和缺乏自适应决策边界的问题，从而在细粒度识别任务中降低判别能力。为了解决这些限制，我们提出了基于Sigmoid的共同与风格监督对比学习（SCS-SupCon）。我们的框架引入了一种基于Sigmoid的成对对比损失，具有可学习的温度和偏置参数，以实现自适应决策边界。这种形式强调了困难的负样本，缓解了负样本稀释，并更有效地利用监督。此外，显式风格距离约束进一步解耦了风格和内容表示，导致更稳健的特征学习。在六个基准数据集上进行了全面实验，包括CUB200-2011和斯坦福狗，证明SCS-SupCon在CNN和Transformer后端上均实现了最先进的性能。在CIFAR-100使用ResNet-50时，SCS-SupCon在五折交叉验证下比SupCon提高了约3.9个百分点，比CS-SupCon提高了约1.7个百分点。在细粒度数据集上，它比CS-SupCon高出0.4-3.0个百分点。广泛的消融研究和统计分析进一步确认了所提出框架的鲁棒性和泛化能力，Friedman检验和Nemenyi事后检验验证了观察到的改进的稳定性。
英文摘要：
Image classification is hindered by subtle inter-class differences and substantial intra-class variations, which limit the effectiveness of existing contrastive learning methods. Supervised contrastive approaches based on the InfoNCE loss suffer from negative-sample dilution and lack adaptive decision boundaries, thereby reducing discriminative power in fine-grained recognition tasks. To address these limitations, we propose Sigmoid-based Common and Style Supervised Contrastive Learning (SCS-SupCon). Our framework introduces a sigmoid-based pairwise contrastive loss with learnable temperature and bias parameters to enable adaptive decision boundaries. This formulation emphasizes hard negatives, mitigates negative-sample dilution, and more effectively exploits supervision. In addition, an explicit style-distance constraint further disentangles style and content representations, leading to more robust feature learning. Comprehensive experiments on six benchmark datasets, including CUB200-2011 and Stanford Dogs, demonstrate that SCS-SupCon achieves state-of-the-art performance across both CNN and Transformer backbones. On CIFAR-100 with ResNet-50, SCS-SupCon improves top-1 accuracy over SupCon by approximately 3.9 percentage points and over CS-SupCon by approximately 1.7 points under five-fold cross-validation. On fine-grained datasets, it outperforms CS-SupCon by 0.4--3.0 points. Extensive ablation studies and statistical analyses further confirm the robustness and generalization of the proposed framework, with Friedman tests and Nemenyi post-hoc evaluations validating the stability of the observed improvements.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
