Lune

NeurIPS2021Top-tier venue

Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases

Shashi Kant Gupta, Mengmi Zhang, Chia-Chien Wu, Jeremy M. Wolfe, Gabriel Kreiman

Abstract

Visual search is a ubiquitous and often challenging daily task, exemplified by looking for the car keys at home or a friend in a crowd. An intriguing property of some classical search tasks is an asymmetry such that finding a target A among distractors B can be easier than finding B among A. To elucidate the mechanisms responsible for asymmetry in visual search, we propose a computational model that takes a target and a search image as inputs and produces a sequence of eye movements until the target is found. The model integrates eccentricity-dependent visual recognition with target-dependent top-down cues. We compared the model against human behavior in six paradigmatic search tasks that show asymmetry in humans. Without prior exposure to the stimuli or task-specific training, the model provides a plausible mechanism for search asymmetry. We hypothesized that the polarity of search asymmetry arises from experience with the natural environment. We tested this hypothesis by training the model on augmented versions of ImageNet where the biases of natural images were either removed or reversed. The polarity of search asymmetry disappeared or was altered depending on the training protocol. This study highlights how classical perceptual properties can emerge in neural network models, without the need for task-specific training, but rather as a consequence of the statistical properties of the developmental diet fed to the model. All source code and data are publicly available at https: //github.com/kreimanlab/VisualSearchAsymmetry .

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.

5 top-tier papers have 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

  • Peering into the Unknown: Active View Selection with Neural Uncertainty Maps for 3D Reconstruction cites Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers5

  1. LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image RecognitionYoubing Hu, Yun Cheng, Anqi Lu, Zhiqiang Cao et al.AAAI 2024 · 25 citations
  2. Peering into the Unknown: Active View Selection with Neural Uncertainty Maps for 3D ReconstructionZhengquan Zhang, Feng Xu, Mengmi ZhangICLR 2026 · 4 citations
  3. Flexible Context-Driven Sensory Processing in Dynamical Vision ModelsLakshmi Narasimhan Govindarajan, Abhiram Iyer, Valmiki Kothare, Ila FieteNeurIPS 2024 · 1 citation
  4. Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual ForagingBo Wang, Dingwei Tan, Yen-Ling Kuo, Zhaowei Sun et al.CVPR 2025
  5. L-WISE: Boosting Human Visual Category Learning Through Model-Based Image Selection and EnhancementMorgan Bruce Talbot, Gabriel Kreiman, James J. DiCarlo, Guy GazivICLR 2025

Related papers

  1. Towards Robust Image Classification Using Sequential Attention ModelsDaniel Zoran, Mike Chrzanowski, Po-Sen Huang, Sven Gowal et al.CVPR 2020
  2. SeekUI: Predicting Visual Search Behavior on Graphical User Interfaces with a Reward-Augmented Vision Language ModelZixin Guo, Yue Jiang, Luis A. Leiva, Antti OulasvirtaCHI 2026 · 1 citation
  3. Modeling Human Visual Search Performance on Realistic Webpages Using Analytical and Deep Learning MethodsArianna Yuan, Yang LiCHI 2020 · 20 citations
  4. Simulating Human Audiovisual Search BehaviorHyunsung Cho, Xuejing Luo, Byungjoo Lee, David Lindlbauer et al.CHI 2026 · 1 citation
  5. RA-Det: Towards Universal Detection of AI-Generated Images via Robustness AsymmetryXinchang Wang, Yunhao Chen, Yuechen Zhang, Congcong Bian et al.ICML 2026 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines