Leaderboard Explore Compare Profile Community Blog FAQ Competition 2024 Report Issue

resnet50_eMMCR_Vanilla

Contributed by Martin Schrimpf No reference provided Find on GitHub source Compare this model

CNN

25.6M parameters

Scores on benchmarks

from scoring API

Model rank shown below is with respect to all public models.

.064	average_vision rank 456 138 benchmarks	.064 0 ceiling best median

.006	neural_vision rank 531 77 benchmarks	.006 0 ceiling best median

.022	V1 rank 516 33 benchmarks	.022 0 ceiling best median

.178	Coggan2024_fMRI.V1-rdm v1 rank 49	.178 0 ceiling best median
	24 images Sample stimuli cannot be displayed publicly for this benchmark.

.122	behavior_vision rank 298 61 benchmarks	.122 0 ceiling best median

.098	Geirhos2021-error_consistency [reference] rank 253 17 benchmarks	.098 0 ceiling best median

.179	Geirhos2021colour-error_consistency v1 [reference] rank 225	.179 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.079	Geirhos2021contrast-error_consistency v1 [reference] rank 262	.079 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.160	Geirhos2021cueconflict-error_consistency v1 [reference] rank 194	.160 0 ceiling best median
	1280 images Sample stimuli cannot be displayed publicly for this benchmark.

.084	Geirhos2021edge-error_consistency v1 [reference] rank 162	.084 0 ceiling best median
	160 images Sample stimuli cannot be displayed publicly for this benchmark.

.077	Geirhos2021eidolonI-error_consistency v1 [reference] rank 315	.077 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.173	Geirhos2021eidolonII-error_consistency v1 [reference] rank 254	.173 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.123	Geirhos2021eidolonIII-error_consistency v1 [reference] rank 272	.123 0 ceiling best median
	480 images Sample stimuli cannot be displayed publicly for this benchmark.

.218	Geirhos2021falsecolour-error_consistency v1 [reference] rank 206	.218 0 ceiling best median
	560 images Sample stimuli cannot be displayed publicly for this benchmark.

.048	Geirhos2021highpass-error_consistency v1 [reference] rank 210	.048 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.090	Geirhos2021lowpass-error_consistency v1 [reference] rank 234	.090 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.051	Geirhos2021phasescrambling-error_consistency v1 [reference] rank 261	.051 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.013	Geirhos2021powerequalisation-error_consistency v1 [reference] rank 321	.013 0 ceiling best median
	560 images Sample stimuli cannot be displayed publicly for this benchmark.

.063	Geirhos2021rotation-error_consistency v1 [reference] rank 245	.063 0 ceiling best median
	960 images Sample stimuli cannot be displayed publicly for this benchmark.

.052	Geirhos2021silhouette-error_consistency v1 [reference] rank 327	.052 0 ceiling best median
	160 images Sample stimuli cannot be displayed publicly for this benchmark.

.044	Geirhos2021sketch-error_consistency v1 [reference] rank 259	.044 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.159	Geirhos2021stylized-error_consistency v1 [reference] rank 217	.159 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.061	Geirhos2021uniformnoise-error_consistency v1 [reference] rank 230	.061 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.091	Baker2022 rank 207 3 benchmarks	.091 0 ceiling best median

.274	Baker2022fragmented-accuracy_delta v1 [reference] rank 156	.274 0 ceiling best median
	716 images Sample stimuli cannot be displayed publicly for this benchmark.

.000	Baker2022frankenstein-accuracy_delta v1 [reference] rank 197	.000 0 ceiling best median
	716 images Sample stimuli cannot be displayed publicly for this benchmark.

.000	Baker2022inverted-accuracy_delta v1 [reference] rank 77	.000 0 ceiling best median
	360 images Sample stimuli cannot be displayed publicly for this benchmark.

.146	BMD2024 rank 161 4 benchmarks	.146 0 ceiling best median

.166	BMD2024.dotted_1Behavioral-accuracy_distance v1 rank 104	.166 0 ceiling best median
	100 images Sample stimuli cannot be displayed publicly for this benchmark.

.126	BMD2024.dotted_2Behavioral-accuracy_distance v1 rank 143	.126 0 ceiling best median
	100 images Sample stimuli cannot be displayed publicly for this benchmark.

.134	BMD2024.texture_1Behavioral-accuracy_distance v1 rank 166	.134 0 ceiling best median
	100 images Sample stimuli cannot be displayed publicly for this benchmark.

.157	BMD2024.texture_2Behavioral-accuracy_distance v1 rank 152	.157 0 ceiling best median
	100 images Sample stimuli cannot be displayed publicly for this benchmark.

.019	Ferguson2024 [reference] rank 320 14 benchmarks	.019 0 ceiling best median

.270	Ferguson2024gray_hard-value_delta v1 [reference] rank 230	.270 0 ceiling best median
	2_way_afc task 48 images Sample stimuli cannot be displayed publicly for this benchmark.

.233	Hebart2023-match v1 rank 194	.233 0 ceiling best median
	1854 images Sample stimuli cannot be displayed publicly for this benchmark.

.417	Maniquet2024 rank 254 2 benchmarks	.417 0 ceiling best median

.164	Maniquet2024-confusion_similarity v1 [reference] rank 291	.164 0 ceiling best median
	13600 images Sample stimuli cannot be displayed publicly for this benchmark.

.671	Maniquet2024-tasks_consistency v1 [reference] rank 103	.671 0 ceiling best median
	13600 images Sample stimuli cannot be displayed publicly for this benchmark.

.095	Coggan2024_behavior-ConditionWiseAccuracySimilarity v1 rank 229	.095 0 ceiling best median
	22560 images Sample stimuli cannot be displayed publicly for this benchmark.

.104	engineering_vision rank 323 25 benchmarks	.104 0 ceiling best median

.520	Geirhos2021-top1 [reference] rank 190 17 benchmarks	.520 0 ceiling best median

.948	Geirhos2021colour-top1 v1 [reference] rank 185	.948 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.855	Geirhos2021contrast-top1 v1 [reference] rank 127	.855 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.158	Geirhos2021cueconflict-top1 v1 [reference] rank 280	.158 0 ceiling best median
	1280 images Sample stimuli cannot be displayed publicly for this benchmark.

.194	Geirhos2021edge-top1 v1 [reference] rank 244	.194 0 ceiling best median
	160 images Sample stimuli cannot be displayed publicly for this benchmark.

.498	Geirhos2021eidolonI-top1 v1 [reference] rank 172	.498 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.511	Geirhos2021eidolonII-top1 v1 [reference] rank 177	.511 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.498	Geirhos2021eidolonIII-top1 v1 [reference] rank 197	.498 0 ceiling best median
	480 images Sample stimuli cannot be displayed publicly for this benchmark.

.929	Geirhos2021falsecolour-top1 v1 [reference] rank 167	.929 0 ceiling best median
	560 images Sample stimuli cannot be displayed publicly for this benchmark.

.500	Geirhos2021highpass-top1 v1 [reference] rank 90	.500 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.419	Geirhos2021lowpass-top1 v1 [reference] rank 168	.419 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.539	Geirhos2021phasescrambling-top1 v1 [reference] rank 235	.539 0 ceiling best median
	640 images Sample stimuli cannot be displayed publicly for this benchmark.

.598	Geirhos2021powerequalisation-top1 v1 [reference] rank 219	.598 0 ceiling best median
	560 images Sample stimuli cannot be displayed publicly for this benchmark.

.674	Geirhos2021rotation-top1 v1 [reference] rank 158	.674 0 ceiling best median
	960 images Sample stimuli cannot be displayed publicly for this benchmark.

.319	Geirhos2021silhouette-top1 v1 [reference] rank 278	.319 0 ceiling best median
	160 images Sample stimuli cannot be displayed publicly for this benchmark.

.488	Geirhos2021sketch-top1 v1 [reference] rank 259	.488 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.329	Geirhos2021stylized-top1 v1 [reference] rank 251	.329 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

.381	Geirhos2021uniformnoise-top1 v1 [reference] rank 188	.381 0 ceiling best median
	800 images Sample stimuli cannot be displayed publicly for this benchmark.

How to use

from brainscore_vision import load_model
model = load_model("resnet50_eMMCR_Vanilla")
model.start_task(...)
model.start_recording(...)
model.look_at(...)

Model API

Code examples

Curated metadata

At-a-glance

Architecture Probable: show confidence source Probable — Existing plugin metadata; primary sources need review.: CNN
Parameters Probable: show confidence source Probable — Existing plugin metadata; primary sources need review.: 25.6M
Input resolution: Not documented
Recurrent: Not documented
Supervision: Not documented
Weights provider: Not documented
Trainable layers Probable: show confidence source Probable — Existing plugin metadata; primary sources need review.: 54 layers
Checkpoint: Not documented

Training and data

Not documented

Objective:: Not documented
Loss:: Not documented
Learning rate:: Not documented
Batch size:: Not documented
Preprocessing:: Not documented

Creators and licensing

Organization:: Not documented
Creators:: Not documented
License:: Not documented

Dashed Not documented fields are awaiting curation.

Brain Encoding Response Generator (BERG)

Through the BERG you can easily generate neural responses to images of your choice using any Brain-Score vision model.

For more information on how to use BERG, see the documentation and tutorial.

Historical trend

Hover the line for a preview; click the chart to pin that month in the sidebar. While pinned, hover does not change it -- use Release or Esc to clear.

Benchmarks BibTeX

@inproceedings{santurkar2019computer,
    title={Computer Vision with a Single (Robust) Classifier},
    author={Shibani Santurkar and Dimitris Tsipras and Brandon Tran and Andrew Ilyas and Logan Engstrom and Aleksander Madry},
    booktitle={ArXiv preprint arXiv:1906.09453},
    year={2019}
}
        @article{geirhos2021partial,
              title={Partial success in closing the gap between human and machine vision},
              author={Geirhos, Robert and Narayanappa, Kantharaju and Mitzkus, Benjamin and Thieringer, Tizian and Bethge, Matthias and Wichmann, Felix A and Brendel, Wieland},
              journal={Advances in Neural Information Processing Systems},
              volume={34},
              year={2021},
              url={https://openreview.net/forum?id=QkljT4mrfs}
        }
        @article{BAKER2022104913,
                title = {Deep learning models fail to capture the configural nature of human shape perception},
                journal = {iScience},
                volume = {25},
                number = {9},
                pages = {104913},
                year = {2022},
                issn = {2589-0042},
                doi = {https://doi.org/10.1016/j.isci.2022.104913},
                url = {https://www.sciencedirect.com/science/article/pii/S2589004222011853},
                author = {Nicholas Baker and James H. Elder},
                keywords = {Biological sciences, Neuroscience, Sensory neuroscience},
                abstract = {Summary
                A hallmark of human object perception is sensitivity to the holistic configuration of the local shape features of an object. Deep convolutional neural networks (DCNNs) are currently the dominant models for object recognition processing in the visual cortex, but do they capture this configural sensitivity? To answer this question, we employed a dataset of animal silhouettes and created a variant of this dataset that disrupts the configuration of each object while preserving local features. While human performance was impacted by this manipulation, DCNN performance was not, indicating insensitivity to object configuration. Modifications to training and architecture to make networks more brain-like did not lead to configural processing, and none of the networks were able to accurately predict trial-by-trial human object judgements. We speculate that to match human configural sensitivity, networks must be trained to solve a broader range of object tasks beyond category recognition.}
        }
        @misc{ferguson_ngo_lee_dicarlo_schrimpf_2024,
         title={How Well is Visual Search Asymmetry predicted by a Binary-Choice, Rapid, Accuracy-based Visual-search, Oddball-detection (BRAVO) task?},
         url={osf.io/5ba3n},
         DOI={10.17605/OSF.IO/5BA3N},
         publisher={OSF},
         author={Ferguson, Michael E, Jr and Ngo, Jerry and Lee, Michael and DiCarlo, James and Schrimpf, Martin},
         year={2024},
         month={Jun}
}
        @article {Maniquet2024.04.02.587669,
	author = {Maniquet, Tim and de Beeck, Hans Op and Costantino, Andrea Ivan},
	title = {Recurrent issues with deep neural network models of visual recognition},
	elocation-id = {2024.04.02.587669},
	year = {2024},
	doi = {10.1101/2024.04.02.587669},
	publisher = {Cold Spring Harbor Laboratory},
	URL = {https://www.biorxiv.org/content/early/2024/04/10/2024.04.02.587669},
	eprint = {https://www.biorxiv.org/content/early/2024/04/10/2024.04.02.587669.full.pdf},
	journal = {bioRxiv}
}

metadata.yaml · Schema v2.0

This annotated template shows the structure of a model’s metadata.yaml. Each section groups related information; comments explain the expected types and allowed values.

Required: schema_version, domain, and models keyed by model identifier. Other fields may be omitted or set to null when undocumented. Use [] for empty lists.

The values below are illustrative, not this model’s metadata. Metadata changes are proposed in repository pull requests and published after merge.

# metadata.yaml — proposed schema v2.0
# Example values below are illustrative, not metadata for a real model.
# Required: schema_version, domain, and models keyed by exact model identifier.
# Other fields may be omitted or set to null when undocumented.
# Use [] for an empty list. Do not use "unknown" as a numeric/boolean value.
# Keep identifiers exact, including checkpoint suffixes.

schema_version: "2.0"  # String; quote the version.

domain: vision  # Must match the repository's registered domain.
models:
  example-model:
    sources:
      example-source:
        kind: other  # paper | huggingface | other | unreviewed
        url: https://example.org/model-card
        citation: Illustrative source, not evidence for a real model.
    model:
      display_name: Example model
      version: null  # String, e.g. "1.0".
      architecture:
        family: convolutional_neural_network  # String describing the architecture family.
        description: A convolutional model trained for image classification.
      parameter_count: 25000000  # Nonnegative integer; count, not "25M".
      parameter_count_exact: false  # Boolean; false means the count is approximate.
      trainable_layers: "All layers"  # Text; can describe partial fine-tuning.
      recurrent: false  # Boolean.
      input_resolution:
        channels: 3  # Nonnegative integer.
        height: 224  # Nonnegative integer, pixels.
        width: 224  # Nonnegative integer, pixels.
      visual_degrees: null  # Nonnegative number; vision models only.
      visual_degrees_description: null  # Text explaining the field of view.
      supervision:
        type: supervised  # String, e.g. supervised, self_supervised, weakly_supervised.
        description: Trained using class labels.

    training:
      process: null  # Text describing the training procedure.
      objective: null  # Text describing what the model learns.
      loss: null  # Text, e.g. "Cross-entropy".
      learning_rate: null  # Text; supports schedules, e.g. "0.1 with cosine decay".
      batch_size: null  # Text; supports different values across training stages.
      preprocessing: null  # Text describing normalization and augmentation.

    data:
      summary: null  # Text summarizing the data used.
      training_datasets:
        - identifier: example-training-set  # Optional dataset identifier.
          name: Example training set  # Required for each dataset entry.
          role: training  # training | pretraining | fine_tuning
          description: null  # Text describing this dataset's use.

    eval:
      test_datasets: []  # Entries: {identifier: optional, name: required, description: optional}.
      validation_datasets: []  # Same entry structure; role is implied by the list.

    io:
      modality: image  # String, e.g. image or text.
      interface: null  # Text describing the model's interface.
      input_format: null  # Text describing accepted inputs and their shape.
      output_format: null  # Text describing returned values and their shape.
      tokenizer: null  # Text; language models, where applicable.

    provenance:
      weights_provider: null  # Organization or repository providing the weights.
      checkpoint: null  # Exact checkpoint identifier.
      source_url: null  # Link to the original code or model card.
      curation_confidence: null  # Text summarizing confidence in the curated record.

    legal:
      license: null  # License identifier or full terms; distinguish code and weights.

    people:
      creators: []  # List of names, e.g. ["Example Researcher"].
      organizations: []  # List of organization names.

    use:
      applications: []  # List of intended applications (strings).
      users: []  # List of intended user groups (strings).
      limitations: []  # List of known limitations (strings).
      biases: []  # List of known biases (strings).

    lineage:
      base_models:
        - identifier: example-base  # Optional; exact identifier in the same domain.
          name: Example base model  # Required for each base-model entry.
          relationship: fine_tuned_from  # variant_of | fine_tuned_from | derived_from

    # Optional verification records. Omit this section if no verification is recorded.
    # Paths refer to fields in this YAML document, not database columns.
    assertions:
      - path: /model/architecture
        status: probable  # verified | probable | uncertain | undocumented
        sources: [example-source]  # References the structured sources above.

Region	Layer
V1	`layer3.1`