Scores on benchmarks

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

.061	average_vision rank 418 81 benchmarks	.061 0 ceiling best median

.123	behavior_vision rank 217 43 benchmarks	.123 0 ceiling best median

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

Benchmarks bibtex

@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.}
        }
        @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}
}

Layer Commitment

No layer commitments found for this model. Older submissions might not have stored this information but will be updated when evaluated on new benchmarks.

Visual Angle

None degrees

.091	Baker2022 rank 150 3 benchmarks	.091 0 ceiling best median

.274	Baker2022fragmented-accuracy_delta v1 [reference] rank 114	.274 0 ceiling best median

.000	Baker2022frankenstein-accuracy_delta v1 [reference] rank 142	.000 0 ceiling best median

.000	Baker2022inverted-accuracy_delta v1 [reference] rank 54	.000 0 ceiling best median

.417	Maniquet2024 rank 143 2 benchmarks	.417 0 ceiling best median

.164	Maniquet2024-confusion_similarity v1 [reference] rank 171	.164 0 ceiling best median

.671	Maniquet2024-tasks_consistency v1 [reference] rank 59	.671 0 ceiling best median

.166	BMD2024.dotted_1Behavioral-accuracy_distance v1 rank 83	.166 0 ceiling best median

.134	BMD2024.texture_1Behavioral-accuracy_distance v1 rank 127	.134 0 ceiling best median

.157	BMD2024.texture_2Behavioral-accuracy_distance v1 rank 118	.157 0 ceiling best median

.233	Hebart2023-match v1 rank 132	.233 0 ceiling best median

.126	BMD2024.dotted_2Behavioral-accuracy_distance v1 rank 107	.126 0 ceiling best median

.095	Coggan2024_behavior-ConditionWiseAccuracySimilarity v1 rank 160	.095 0 ceiling best median