DM-Diaz/SimCLR-ResNet18-ImageNet100

SimCLR ResNet-18 — ImageNet-100

This repository contains the ImageNet-100 SimCLR ResNet-18 checkpoint trained as a non-egocentric reference model for:

Diaz, D. M., & Henderson, M. M. (2026). Eccentricity-Constrained CNN Training Reveals Adaptive Information Coding Around the Visual Field. Proceedings of the 9th Conference on Cognitive Computational Neuroscience.

DOI: 10.32470/0416gfsq
arXiv: 2607.19316
Contributed Talk: CCN 2026 presentation on YouTube

The model was pretrained using SimCLR with a ResNet-18 backbone and served as one of the non-egocentric reference models in the associated study. It was evaluated alongside models pretrained on ImageNet-1K and STL-10 as comparison models for representations learned from naturalistic egocentric visual experience.

Training was implemented using the Lightly self-supervised learning framework. The training images were obtained from the clane9/imagenet-100 dataset on Hugging Face.

Model Architecture

The model uses a standard ResNet-18 encoder with the classification head removed and a SimCLR projection head attached during self-supervised pretraining.

Component	Configuration
Backbone	ResNet-18
Backbone representation	512 dimensions
Projection head	Lightly SimCLRProjectionHead
Projection dimensions	512 → 512 → 128
Projection output	128 dimensions
SSL objective	NT-Xent
Temperature	0.1

The released checkpoint contains both the ResNet-18 backbone and the SimCLR projection head. For downstream applications, the 512-dimensional backbone representation can be extracted independently of the projection head.

Training Configuration

Parameter	Value
Dataset	ImageNet-100
Dataset source	clane9/imagenet-100
Number of classes	100
Epochs	120
Batch size	64
Input resolution	224 × 224
Optimizer	LARS
Initial learning rate	0.075
Momentum	0.9
Weight decay	1e-6
LR schedule	Cosine warmup
Warmup	10 epochs
Precision	16-bit mixed precision
Distributed training	No

The learning rate was linearly scaled from a base learning rate of 0.3 according to batch size:

0.3 × (64 / 256) = 0.075

Training Data

Training data were obtained from the Hugging Face dataset:

clane9/imagenet-100

The dataset was downloaded locally and organized into training and validation directories. The training split was used for self-supervised representation learning.

The dataset itself is not redistributed through this repository and remains subject to its original access conditions and terms.

Checkpoint

File: checkpoint_120-resnet18-simclr-imagenet100.ckpt

The released file is a full PyTorch Lightning checkpoint, rather than a backbone-only state dictionary.

Checkpoint inspection confirmed:

Property	Value
PyTorch Lightning version recorded	2.6.1
Stored epoch	119
Training epochs completed	120
Global step	237,480
State-dict entries	132
Backbone output	512 dimensions
Projection output	128 dimensions
Strict architecture loading	Successful

The stored epoch is zero-indexed, so epoch = 119 corresponds to the completion of epoch 120.

The checkpoint also contains optimizer, learning-rate scheduler, training-loop, callback, and mixed-precision state in addition to the model parameters.

Loading the Checkpoint

The checkpoint can be loaded by reconstructing the ResNet-18 backbone and SimCLR projection head used during training.

import torch
import torch.nn as nn
import torchvision
from lightly.models.modules import heads


class SimCLRResNet18(nn.Module):
    def __init__(self):
        super().__init__()

        resnet = torchvision.models.resnet18(weights=None)
        feature_dim = resnet.fc.in_features  # 512

        # Remove the classification head
        self.backbone = nn.Sequential(
            *list(resnet.children())[:-1]
        )

        # SimCLR projection head: 512 -> 512 -> 128
        self.projection_head = heads.SimCLRProjectionHead(
            feature_dim,
            feature_dim,
            128,
        )

    def forward(self, x):
        features = self.backbone(x).flatten(start_dim=1)
        projections = self.projection_head(features)
        return projections


checkpoint = torch.load(
    "checkpoint_120-resnet18-simclr-imagenet100.ckpt",
    map_location="cpu",
    weights_only=False,
)

model = SimCLRResNet18()
model.load_state_dict(checkpoint["state_dict"], strict=True)
model.eval()

Extracting Backbone Features

For most downstream applications, the 512-dimensional ResNet-18 representation can be extracted without using the SimCLR projection head:

with torch.no_grad():
    features = model.backbone(images).flatten(start_dim=1)

print(features.shape)
# [batch_size, 512]

The 128-dimensional SimCLR projection can instead be obtained with:

with torch.no_grad():
    projections = model(images)

print(projections.shape)
# [batch_size, 128]

Input tensors should have shape [batch_size, 3, 224, 224].

Comparative Evaluation Results

The table below reproduces the summary metrics reported in the associated paper across all VEDB-trained conditions and reference models. Rows corresponding to this repository's ImageNet-100 checkpoint are bolded.

Task	Condition	Val Loss	Top-1 (%)	Top-5 (%)	Best Macro-F1 (%)
SimCLR	Baseline	0.4331	87.60	—	—
SimCLR	Fovea-Gaze	0.3749	90.43	—	—
SimCLR	Periph-NF	0.4548	90.04	—	—
SimCLR	Periph	0.4545	89.26	—	—
In-Domain	Baseline	0.9811	—	—	42.17
In-Domain	Fovea-Gaze	1.2031	—	—	43.64
In-Domain	Periph-NF	1.3090	—	—	30.93
In-Domain	Periph	1.0623	—	—	36.56
In-Domain	STL-10	1.6666	—	—	25.41
In-Domain	ImageNet-100	1.2342	—	—	41.23
In-Domain	ImageNet-1K	0.9713	—	—	43.33
VGGFace2	Baseline	7.8101	5.21	11.73	3.26
VGGFace2	Fovea-Gaze	7.9104	4.58	10.76	2.70
VGGFace2	Periph-NF	8.0232	3.39	8.17	1.90
VGGFace2	Periph	8.1681	2.54	6.39	1.35
VGGFace2	STL-10	6.9973	9.55	18.96	7.43
VGGFace2	ImageNet-100	6.7985	10.77	21.07	8.71
VGGFace2	ImageNet-1K	6.7964	10.74	21.08	8.77
Places365	Baseline	3.9690	25.63	51.90	23.16
Places365	Fovea-Gaze	4.2347	21.86	46.21	19.14
Places365	Periph-NF	4.2621	20.51	44.58	17.86
Places365	Periph	4.2671	20.26	44.10	17.65
Places365	STL-10	3.8281	26.57	53.47	24.82
Places365	ImageNet-100	3.9207	24.99	51.21	23.32
Places365	ImageNet-1K	3.6264	30.17	58.46	28.36

Note: SimCLR Top-1 is computed from the self-supervised pretraining evaluation and is not directly comparable to downstream supervised classification accuracy. For downstream tasks, the pretrained ResNet-18 backbone was frozen and only a linear classifier was trained; the backbone weights were not fine-tuned. Classifier checkpoints were selected by best validation Macro-F1. In-domain Top-1 accuracy is omitted because label imbalance across VEDB frame categories can make accuracy misleading; Macro-F1 is reported as the primary class-balanced metric. STL-10, ImageNet-100, and ImageNet-1K are treated as out-of-domain reference models because they were not pretrained on VEDB.

Intended Use

This checkpoint is provided for research and downstream applications involving self-supervised visual representations, including:

• reproducing the reference-model analyses reported in Diaz and Henderson (2026),
• extracting ResNet-18 representations for comparison with the VEDB-pretrained models,
• reproducing the associated NSD voxelwise encoding analyses,
• linear-probe or fine-tuned image classification,
• transfer learning to other visual recognition tasks, and
• representation-learning and visual-neuroscience research.

The released checkpoint contains a self-supervised ResNet-18 encoder and SimCLR projection head rather than a trained classification head. For image classification, users can attach and train an appropriate classifier on the learned backbone representations or fine-tune the encoder for the target task.

Related Models

This model was used as a non-egocentric reference model in the study associated with the Eccentricity-Constrained SimCLR Models (VEDB) collection.

• VEDB SimCLR ResNet-18 — Baseline
• VEDB SimCLR ResNet-18 — Fovea-Gaze
• VEDB SimCLR ResNet-18 — Periph
• VEDB SimCLR ResNet-18 — Periph-NF
• VEDB NSD ResNet-18 — Encoding Models
• SimCLR ResNet-18 — ImageNet-1K
• SimCLR ResNet-18 — ImageNet-100
• SimCLR ResNet-18 — STL-10 (external pretrained reference model; checkpoint provided by Spijkervet/SimCLR and not redistributed by this project)

Citation

If you use this checkpoint or representations derived from it in academic work, please cite the associated study:

@inproceedings{diaz2026eccentricity,
  author    = {Diaz, Dylan M. and Henderson, Margaret M.},
  title     = {Eccentricity-Constrained CNN Training Reveals Adaptive Information Coding Around the Visual Field},
  booktitle = {Proceedings of the 9th Conference on Cognitive Computational Neuroscience},
  address   = {New York, NY, USA},
  year      = {2026},
  doi       = {10.32470/0416gfsq}
}

Proceedings: Diaz & Henderson (2026)
Preprint: arXiv:2607.19316

License

The released checkpoint and repository materials are provided under the Apache License 2.0.

The ImageNet-100 training dataset and third-party software used to produce the model remain subject to their respective licenses, access requirements, and terms of use.