Update README.md

README.md

@@ -17,10 +17,10 @@ Current metrics for perceptual image similarity operate at the level of pixels a
 DreamSim is a new metric for perceptual image similarity that bridges the gap between "low-level" metrics (e.g. LPIPS, PSNR, SSIM) and "high-level" measures (e.g. CLIP). Our model was trained by concatenating CLIP, OpenCLIP, and DINO embeddings, and then finetuning on human perceptual judgements. We gathered these judgements on a dataset of ~20k image triplets, generated by diffusion models. Our model achieves better alignment with human similarity judgements than existing metrics, and can be used for downstream applications such as image retrieval.
 
 ## 🕰️ Coming soon
-* JND Dataset release
+* ✅ JND Dataset release
+* ✅ Compatibility with the most recent version of PEFT
 * Distilled DreamSim models (i.e. smaller models distilled from the main ensemble)
 * DreamSim variants trained for higher resolutions
-* Compatibility with the most recent version of PEFT
 
 ## 🚀 Newest Updates
 **X/XX/24:** Released new versions of the ensemble and single-branch DreamSim models compatible with `peft>=0.2.0`. 
@@ -36,7 +36,7 @@ Here's how they perform on the NIGHTS validation set:
 * [Setup](#setup)
 * [Usage](#usage)
   * [Quickstart](#quickstart-perceptual-similarity-metric)
-  * [Single-branch models](#new-single-branch-models)
+  * [Single-branch models](#single-branch-models)
   * [Feature extraction](#feature-extraction)
   * [Image retrieval](#image-retrieval)
   * [Perceptual loss function](#perceptual-loss-function)
@@ -95,9 +95,9 @@ distance = model(img1, img2) # The model takes an RGB image from [0, 1], size ba
 To run on example images, run `demo.py`. The script should produce distances (0.424, 0.34). 
 
 ### Single-branch models
-By default, DreamSim uses an ensemble of CLIP, DINO, and OpenCLIP (all ViT-B/16). If you need a lighter-weight model you can use *single-branch* versions of DreamSim where only a single backbone is finetuned. The available options are OpenCLIP-ViTB/32, DINO-ViTB/16, CLIP-ViTB/32, in order of performance.  
+By default, DreamSim uses an ensemble of CLIP, DINO, and OpenCLIP (all ViT-B/16). If you need a lighter-weight model you can use *single-branch* versions of DreamSim where only a single backbone is finetuned. **The single-branch models provide a ~3x speedup over the ensemble.**
 
-To load a single-branch model, use the `dreamsim_type` argument. For example:
+The available options are OpenCLIP-ViTB/32, DINO-ViTB/16, CLIP-ViTB/32, in order of performance. To load a single-branch model, use the `dreamsim_type` argument. For example:
 ```
 dreamsim_dino_model, preprocess = dreamsim(pretrained=True, dreamsim_type="dino_vitb16")
 ```