SPARC: SuperPixel-Aware Region Contrastive Learning for Self-Supervised Dense Prediction

David Szczecina; Yuanpei Xiang; Jitao Hu; David Clausi; Yuhao Chen; Jason Deglint; Paul Fieguth

cs.CVSep 16, 2026

SPARC: SuperPixel-Aware Region Contrastive Learning for Self-Supervised Dense Prediction

Authors: David Szczecina, Yuanpei Xiang, Jitao Hu, David Clausi, Yuhao Chen, Jason Deglint, Paul Fieguth

Organizations: Systems Design Engineering University of Waterloo Waterloo, Ontario, Canada

Abstract

Self-supervised learning (SSL) has become an effective approach for learning visual representations without manual annotations. Among SSL approaches, contrastive learning has been widely used for visual representation learning. However, existing contrastive SSL methods have focused primarily on image-level or pixel-level representation learning, while region-level representation learning remains less explored. We propose SPARC, a region-level contrastive learning framework that leverages superpixels to establish explicit correspondence between augmented image views. SPARC introduces a region contrastive branch that performs superpixel-based feature pooling and optimizes a region-level contrastive objective jointly with a global image-level objective. Under identical settings, SPARC consistently outperforms previous methods such as MoCo-v2 and DenseCL, achieving improvements of up to +9.79 mIoU for semantic segmentation and +4.88 AP for object detection. Ablation studies further demonstrate that region-level objectives produce the strongest performance. Thus, region-level contrastive learning is an effective approach for improving self-supervised visual pretraining for dense prediction tasks. Code repository can be accessed at https://github.com/xRIPEIx/SPARC.

Figures & tables

Figure 1: SPARC Framework Overview. SPARC’s framework is inspired by DenseCL’s double-branch design [ 19 ] . We reframe it to adapt the region-level contrastive learning objective by introducing SLIC pre-segmentation, superpixel mask alignment, and superpixel pooling. Overall, SPARC performs feature and mask preparation through data preprocessing, dense feature encoding, and superpixel mask alignment, followed by contrastive learning branches. The global branch learns image-level representations, while the region branch uses superpixels to guide feature extraction and learn region-level representations.

Training Epochs	Method	Segmentation		Detection
Training Epochs	Method	mIoU	Acc	AP	AP 50
Pre-train: 50 Finetune: 10	MoCo-v2	15.74 $\pm$ 0.09	78.12 $\pm$ 0.18	20.04 $\pm$ 0.34	41.97 $\pm$ 0.55
	DenseCL	20.21 $\pm$ 0.41	79.63 $\pm$ 0.25	20.97 $\pm$ 0.06	42.83 $\pm$ 0.23
	SPARC	24.13 $\pm$ 0.56	80.78 $\pm$ 0.28	24.00 $\pm$ 0.17	47.18 $\pm$ 0.29
Pre-train: 100 Finetune: 10	MoCo-v2	18.01 $\pm$ 0.19	79.08 $\pm$ 0.26	20.63 $\pm$ 0.26	43.09 $\pm$ 0.43
	DenseCL	21.92 $\pm$ 0.75	80.42 $\pm$ 0.28	21.59 $\pm$ 0.16	43.59 $\pm$ 0.18

Table 1: Transfer performance on PASCAL VOC (in %). Pre-trained on COCO with ResNet-18. SPARC consistently outperforms MoCo-v2 and DenseCL across all configurations.

Training Epochs	Method	Segmentation		Detection
Training Epochs	Method	mIoU	Acc	AP	AP 50
Pre-train: 50 Finetune: 10	MoCo-v2	13.68 $\pm$ 0.47	76.74 $\pm$ 0.22	18.73 $\pm$ 0.37	39.97 $\pm$ 0.54
	DenseCL	17.70 $\pm$ 0.63	78.24 $\pm$ 0.35	20.20 $\pm$ 0.20	41.53 $\pm$ 0.23
	SPARC	21.48 $\pm$ 0.35	79.86 $\pm$ 0.31	23.38 $\pm$ 0.38	46.06 $\pm$ 0.64
Pre-train: 100 Finetune: 10	MoCo-v2	15.00 $\pm$ 0.61	77.56 $\pm$ 0.14	19.15 $\pm$ 0.25	40.66 $\pm$ 0.29
	DenseCL	18.61 $\pm$ 0.53	78.80 $\pm$ 0.18	20.41 $\pm$ 0.19	41.80 $\pm$ 0.35

Table 2: Same as Table 1 , but pretrained on ImageNet100.

Panel of Figure 2 — Figure 2: Semantic Segmentation and Object Detection Performance between SPARC and DenseCL across different $\lambda$ values. At $\lambda=0$ , both methods use only the image-level contrastive objective, corresponding to the MoCo-v2 baseline. At $\lambda=1$ , only the region-level or pixel-level contrastive objective is used for the proposed SPARC and DenseCL, respectively. The proposed SPARC’s pure region-level contrastive learning significantly outperforms pure pixel-level and image-level contrastive learning frameworks.

Explore similar work

Learning to Perceive "Where": Spatial Pretext Tasks for Robust Self-Supervised Learning
May 11, 2026Yang Shen, Yusen Cai, Weronika Hryniewska-Guzik +2Visual Spatial Reasoning Self-Supervised Visual Representation Learning
Nanyang Technological University, Singapore · Warsaw University of Technology, Poland
Scalable Patch-Level Self-Supervised Learning
Oct 7, 2026Maximilian Seitzer, Gabriele Trivigno, Antonín Vobecký +5Self-Supervised Learning Self-Supervised Visual Representation Learning
Meta FAIR
Learning Accurate Segmentation Purely from Self-Supervision
Feb 27, 2026Zuyao You, Zuxuan Wu, Yu-Gang JiangUnsupervised Image Segmentation Salient Object Detection
Fudan University

May 11, 2026J/K move · Enter open · S save

Learning to Perceive "Where": Spatial Pretext Tasks for Robust Self-Supervised Learning

Yang Shen, Yusen Cai, Weronika Hryniewska-Guzik, Qing Lin+1

Nanyang Technological University, Singapore · Warsaw University of Technology, Poland

Visual Spatial Reasoning Self-Supervised Visual Representation Learning

Open paper AskPDF arXiv

Existing self-supervised learning (SSL) methods primarily learn object-invariant representations but often neglect the spatial structure and relationships among object parts. To address this limitation, we introduce Spatial Prediction (SP), a spatially aware pretext regression task that predicts the relative position and scale between a pair of disentangled local views from the same image. By modeling part-to-part relationships in a continuous geometric space, SP encourages representations to capture fine-grained spatial dependencies beyond invariant categorical semantics, thereby learning the compositional structure of visual scenes. SP is implemented as a decoupled plug-in and can be seamlessly integrated into diverse SSL frameworks. Extensive experiments show consistent improvements across image recognition, fine-grained classification, semantic segmentation, and depth estimation, as well as substantial gains in out-of-distribution robustness for object recognition. To evaluate spatial reasoning, we introduce (1) a position and scale prediction task on image patch pairs and (2) a jigsaw understanding task requiring patch reordering and recognition after reconstruction. Strong performance on these tasks indicates improved spatial structure and geometric awareness. Overall, explicitly modeling spatial information provides an effective inductive bias for SSL, leading to more structured representations and better generalization. Code and models will be released.

Abstract

Explore similar work

Learning to Perceive "Where": Spatial Pretext Tasks for Robust Self-Supervised Learning

Scalable Patch-Level Self-Supervised Learning

Learning Accurate Segmentation Purely from Self-Supervision