Lune

CVPR2025Top-tier venue

Perceptual Inductive Bias Is What You Need Before Contrastive Learning

Junru Zhao, Tianqin Li, Dunhan Jiang, Shenghao Wu, Alan Ramirez, Tai Sing Lee

Abstract

David Marr's seminal theory of human perception stipulates that visual processing is a multi-stage process, prioritizing the derivation of boundary and surface properties before forming semantic object representations. In contrast, contrastive representation learning frameworks typically bypass this explicit multi-stage approach, defining their objective as the direct learning of a semantic representation space for objects. While effective in general contexts, this approach sacrifices the inductive biases of vision, leading to slower convergence speed and learning shortcut resulting in texture bias. In this work, we demonstrate that leveraging Marr's multi-stage theory-by first constructing boundary and surface-level representations using perceptual constructs from early visual processing stages and subsequently training for object semantics-leads to 2x faster convergence on ResNet18, improved final representations on semantic segmentation, depth estimation, and object recognition, and enhanced robustness and out-ofdistribution capability. Together, we propose a pretraining stage before the general contrastive representation pretraining to further enhance the final representation quality and reduce the overall convergence time via inductive bias from human vision systems.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Unsupervised Learning of Dense Visual Representations cites A Simple Framework for Contrastive Learning of Visual Representations
  • Partial success in closing the gap between human and machine vision cites A Simple Framework for Contrastive Learning of Visual Representations
  • Unsupervised Learning of Visual Features by Contrasting Cluster Assignments cites A Simple Framework for Contrastive Learning of Visual Representations
  • Unsupervised Learning of Visual Features by Contrasting Cluster Assignments cites Prototypical Contrastive Learning of Unsupervised Representations
  • Prototypical Contrastive Learning of Unsupervised Representations cites Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
  • Prototypical Contrastive Learning of Unsupervised Representations cites A Simple Framework for Contrastive Learning of Visual Representations
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Reallocating Attention Across Layers to Reduce Multimodal HallucinationHaolang Lu, Bolun Chu, WeiYe Fu, Guoshun Nan et al.CVPR 2026 · 3 citations

Builds on9

  1. A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. HintonICML 2020 · 24,064 citations
  2. Unsupervised Learning of Visual Features by Contrasting Cluster AssignmentsMathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal et al.NeurIPS 2020 · 5,249 citations
  3. Prototypical Contrastive Learning of Unsupervised RepresentationsJunnan Li, Pan Zhou, Caiming Xiong, Steven C. H. HoiICLR 2021 · 484 citations
  4. Partial success in closing the gap between human and machine visionRobert Geirhos, Kantharaju Narayanappa, Benjamin Mitzkus, Tizian Thieringer et al.NeurIPS 2021 · 304 citations
  5. Unsupervised Learning of Dense Visual RepresentationsPedro O. Pinheiro, Amjad Almahairi, Ryan Y. Benmalek, Florian Golemo et al.NeurIPS 2020 · 227 citations

Related papers

  1. Dense Semantic Contrast for Self-Supervised Visual Representation LearningXiaoni Li, Yu Zhou, Yifei Zhang, Aoting Zhang et al.ACM MM 2021 · 35 citations
  2. Semantic Information in Contrastive LearningShengjiang Quan, Masahiro Hirano, Yuji YamakawaICCV 2023 · 4 citations
  3. Pri3D: Can 3D Priors Help 2D Representation Learning?Ji Hou, Saining Xie, Benjamin Graham, Angela Dai et al.ICCV 2021 · 94 citations
  4. Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal EmbeddingDa Li, Yuxiao Luo, Keping Bi, Jiafeng Guo et al.ACL 2026 · 3 citations
  5. CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV PerceptionJiachen Sun, Haizhong Zheng, Qingzhao Zhang, Atul Prakash et al.ICLR 2024 · 15 citations
Dusk over the sea between two cliffs drawn in fine vertical lines