mlsanityData to 7 Oct 2026

Capturing the objects of vision with neural networks

arXiv 2109.03351 ↗First posted 7 Sep 2021q-bio.NC cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Human visual perception carves a scene at its physical joints, decomposing the world into objects, which are selectively attended, tracked, and predicted as we engage our surroundings. Object representations emancipate perception from the sensory input, enabling us to keep in mind that which is out of sight and to use perceptual content as a basis for action and symbolic cognition. Human behavioral studies have documented how object representations emerge through grouping, amodal completion, proto-objects, and object files. Deep neural network (DNN) models of visual object recognition, by contrast, remain largely tethered to the sensory input, despite achieving human-level performance at labeling objects. Here, we review related work in both fields and examine how these fields can help each other. The cognitive literature provides a starting point for the development of new experimental tasks that reveal mechanisms of human object perception and serve as benchmarks driving development of deep neural network models that will put the object into object recognition.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 52 of its 329 references that are in the map. First posted on arXiv 7 Sep 2021.

Builds on

52 of 329 references.

References · 52

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2017Mask R-CNNcited by 7,259
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  5. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  6. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  7. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  8. 2020Object-Centric Learning with Slot Attentioncited by 865
  9. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 850
  10. 2014Deep Learning in Neural Networks: An Overviewcited by 765
  11. 2017Dynamic Routing Between Capsulescited by 689
  12. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
38 more
  1. 2019CLEVRER: CoLlision Events for Video REpresentation and Reasoningcited by 475
  2. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  3. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
  4. 2018Towards a Definition of Disentangled Representationscited by 294
  5. 2019Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetcited by 260
  6. 2016Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagationcited by 251
  7. 2018Generalisation in humans and deep neural networkscited by 237
  8. 2019Human uncertainty makes classification more robustcited by 231
  9. 2020On the Binding Problem in Artificial Neural Networkscited by 230
  10. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  11. 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
  12. 2014Multiple Object Tracking: A Literature Reviewcited by 165
  13. 2019PHYRE: A New Benchmark for Physical Reasoningcited by 137
  14. 2019CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoningcited by 137
  15. 2018Learning to Decompose and Disentangle Representations for Video Predictioncited by 120
  16. 2019Entity Abstraction in Visual Model-Based Reinforcement Learningcited by 110
  17. 2017Interpreting Deep Visual Representations via Network Dissectioncited by 103
  18. 2018Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactionscited by 100
  19. 2017Building machines that adapt and compute like brainscited by 99
  20. 2014Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathwaycited by 93
  21. 2019Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNscited by 90
  22. 2019Stacked Capsule Autoencoderscited by 82
  23. 2019CoPhy: Counterfactual Learning of Physical Dynamicscited by 80
  24. 2015Learning to Segment Object Candidatescited by 79
  25. 2016DeepMind Labcited by 74
  26. 2018IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoningcited by 72
  27. 2016Towards deep learning with segregated dendritescited by 71
  28. 2019Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoningcited by 60
  29. 2019Recurrence is required to capture the representational dynamics of the human visual systemcited by 58
  30. 2017Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physicscited by 57
  31. 2013Neuronal Synchrony in Complex-Valued Deep Networkscited by 28
  32. 2019Unsupervised Discovery of Parts, Structure, and Dynamicscited by 20
  33. 2020Going in circles is the way forward: the role of recurrence in visual inferencecited by 19
  34. 2019The Animal-AI Environment: Training and Testing Animal-Like Artificial Cognitioncited by 16
  35. 2018Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agentscited by 14
  36. 2019A Perspective on Objects and Systematic Generalization in Model-Based RLcited by 14
  37. 2020A neural network walks into a lab: towards using deep nets as models for human behaviorcited by 10
  38. 2019Controversial stimuli: pitting neural networks against each other as models of human recognitioncited by 7

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 11; 2024: 3; 2025: 3; 2026: 1.

21 papers.

Sort:

By area:

  1. 2022Breaking the "Object" in Video Object Segmentationcited by 48
  2. 2023Provably Learning Object-Centric Representationscited by 45
  3. 2023Neither hype nor gloom do DNNs justicecited by 40
  4. 2023CLIP in Medical Imaging: A Surveycited by 40
  5. 2023Learning to reason over visual objectscited by 19
  6. 2025Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?cited by 19
  7. 2022Self-supervised Amodal Video Object Segmentationcited by 14
  8. 2023Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?cited by 10
  9. 2022Object-based active inferencecited by 7
  10. 2025Object-Centric Pretraining via Target Encoder Bootstrappingcited by 6
  11. 2023Affinity-based Attention in Self-supervised Transformers Predicts Dynamics of Object Grouping in Humanscited by 5
  12. 2023Regularity as Intrinsic Reward for Free Playcited by 5
9 more
  1. 2024Object-centric proto-symbolic behavioural reasoning from pixelscited by 2
  2. 2023Beyond the limitations of any imaginable mechanism: large language models and psycholinguisticscited by 1
  3. 2023BIFRNet: A Brain-Inspired Feature Restoration DNN for Partially Occluded Image Recognitioncited by 1
  4. 2023Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Networkscited by 1
  5. 2024A Robotics-Inspired Scanpath Model Reveals the Importance of Uncertainty and Semantic Object Cues for Gaze Guidance in Dynamic Scenescited by 1
  6. 2026Human-like Object Grouping in Self-supervised Vision Transformerscited by 1
  7. 2023Fixing the problems of deep neural networks will require better training data and learning algorithmscited by 0
  8. 2024Lightweight, error-tolerant edge detection using memristor-enabled stochastic logicscited by 0
  9. 2025Ideal Observer for Segmentation of Dead Leaves Imagescited by 0