Update README.md

README.md

@@ -21,14 +21,86 @@ This repository contains the **ImageNet-100 SimCLR ResNet-18 checkpoint** traine
 
 **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`<br>
-**arXiv:** `2607.19316`<br>
+**DOI:** [10.32470/0416gfsq](https://doi.org/10.32470/0416gfsq)<br>
+**arXiv:** [2607.19316](https://arxiv.org/abs/2607.19316)<br>
 **Contributed Talk:** [CCN 2026 presentation on YouTube](https://www.youtube.com/watch?v=Lb4S3FWqd2M&t=2545s)
 
-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 used alongside models pretrained on ImageNet-1K and STL-10 to provide comparison points for evaluating representations learned from naturalistic egocentric visual experience.
+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](https://docs.lightly.ai/self-supervised-learning/index.html). The training images were obtained from the [`clane9/imagenet-100`](https://huggingface.co/datasets/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`](https://huggingface.co/datasets/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.
+
 ### 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.**
@@ -61,13 +133,32 @@ The table below reproduces the summary metrics reported in the associated paper
 | **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 contrastive objective 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 frames 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 baselines because they were not pretrained on VEDB.
+**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.
 
-For in-domain classification, Macro-F1 was used as the primary class-balanced metric because of label imbalance across VEDB frame categories.
+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.
+
+## Limitations
+
+The checkpoint does not contain a trained ImageNet-100 classification head. Classification or other supervised applications therefore require an additional prediction head, linear probe, or model fine-tuning.
+
+The exact installed version of Lightly used during training was not stored in the checkpoint. The PyTorch Lightning checkpoint metadata records version `2.6.1`.
+
+Exact reproduction of the analyses reported in the associated study also requires the corresponding preprocessing, feature-extraction, linear-probe, and NSD encoding-model procedures.
 
 ## Related Models
 
-This repository is associated with the **[Eccentricity-Constrained SimCLR Models (VEDB)](https://hf.co/collections/DM-Diaz/eccentricity-constrained-simclr-models-vedb)** collection.
+This model was used as a non-egocentric reference model in the study associated with the **[Eccentricity-Constrained SimCLR Models (VEDB)](https://hf.co/collections/DM-Diaz/eccentricity-constrained-simclr-models-vedb)** collection.
 
 - [VEDB SimCLR ResNet-18 — Baseline](https://huggingface.co/DM-Diaz/VEDB-SimCLR-ResNet18-Baseline)
 - [VEDB SimCLR ResNet-18 — Fovea-Gaze](https://huggingface.co/DM-Diaz/VEDB-SimCLR-ResNet18-Fovea-Gaze)
@@ -76,4 +167,18 @@ This repository is associated with the **[Eccentricity-Constrained SimCLR Models
 - [VEDB NSD ResNet-18 — Encoding Models](https://huggingface.co/DM-Diaz/VEDB-NSD-ResNet18-Encoding-Models)
 - [SimCLR ResNet-18 — ImageNet-1K](https://huggingface.co/DM-Diaz/SimCLR-ResNet18-ImageNet1K)
 - [SimCLR ResNet-18 — ImageNet-100](https://huggingface.co/DM-Diaz/SimCLR-ResNet18-ImageNet100)
-- [SimCLR ResNet-18 — STL-10](https://github.com/Spijkervet/SimCLR) *(external pretrained reference model; checkpoint provided by Spijkervet/SimCLR and not redistributed by this project)*
+- [SimCLR ResNet-18 — STL-10](https://github.com/Spijkervet/SimCLR) *(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:
+
+```bibtex
+@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}
+}