Improving Unsupervised Task-driven Models of Ventral Visual Stream via Relative Position Predictivity
Not on the map. Why?
Abstract (arXiv)
Based on the concept that ventral visual stream (VVS) mainly functions for object recognition, current unsupervised task-driven methods model VVS by contrastive learning, and have achieved good brain similarity. However, we believe functions of VVS extend beyond just object recognition. In this paper, we introduce an additional function involving VVS, named relative position (RP) prediction. We first theoretically explain contrastive learning may be unable to yield the model capability of RP prediction. Motivated by this, we subsequently integrate RP learning with contrastive learning, and propose a new unsupervised task-driven method to model VVS, which is more inline with biological reality. We conduct extensive experiments, demonstrating that: (i) our method significantly improves downstream performance of object recognition while enhancing RP predictivity; (ii) RP predictivity generally improves the model brain similarity. Our results provide strong evidence for the involvement of VVS in location perception (especially RP prediction) from a computational perspective.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 11 of its 44 references that are in the map. First posted on arXiv 13 May 2025.
Builds on
11 of 44 references.
References · 11
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2020How Well Do Self-Supervised Models Transfer?cited by 213
- 2017Multi-task Self-Supervised Visual Learningcited by 200
- 2014Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathwaycited by 94
- 2019Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNscited by 90
- 2016Learning to Push by Grasping: Using multiple tasks for effective learningcited by 37
- 2020Unsupervised deep learning identifies semantic disentanglement in single inferotemporal neuronscited by 33
- 2018Task-Driven Convolutional Recurrent Models of the Visual Systemcited by 27
- 2023Deep Spiking Neural Networks with High Representation Similarity Model Visual Pathways of Macaque and Mousecited by 6
- 2024Clean-image Backdoor Attackscited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.