Isaac Robinson

Peter Robicheaux, Matvei Popov, Anish Madan et al.

Vision-language models (VLMs) trained on internet-scale data achieve remarkable zero-shot detection performance on common objects like car, truck, and pedestrian. However, state-of-the-art models still struggle to generalize to out-of-distribution classes, tasks and imaging modalities not typically found in their pre-training. Rather than simply re-training VLMs on more visual data, we argue that one should align VLMs to new concepts with annotation instructions containing a few visual examples and rich textual descriptions. To this end, we introduce Roboflow100-VL, a large-scale collection of 100 multi-modal object detection datasets with diverse concepts not commonly found in VLM pre-training. We evaluate state-of-the-art models on our benchmark in zero-shot, few-shot, semi-supervised, and fully-supervised settings, allowing for comparison across data regimes. Notably, we find that VLMs like GroundingDINO and Qwen2.5-VL achieve less than 2% zero-shot accuracy on challenging medical imaging datasets within Roboflow100-VL, demonstrating the need for few-shot concept alignment. Lastly, we discuss our recent CVPR 2025 Foundational FSOD competition and share insights from the community. Notably, the winning team significantly outperforms our baseline by 17 mAP! Our code and dataset are available at https://github.com/roboflow/rf100-vl and https://universe.roboflow.com/rf100-vl/.

Isaac Robinson

We present a visualization algorithm based on a novel unsupervised Siamese neural network training regime and loss function, called Differentiating Embedding Networks (DEN). The Siamese neural network finds differentiating or similar features between specific pairs of samples in a dataset, and uses these features to embed the dataset in a lower dimensional space where it can be visualized. Unlike existing visualization algorithms such as UMAP or $t$-SNE, DEN is parametric, meaning it can be interpreted by techniques such as SHAP. To interpret DEN, we create an end-to-end parametric clustering algorithm on top of the visualization, and then leverage SHAP scores to determine which features in the sample space are important for understanding the structures shown in the visualization based on the clusters found. We compare DEN visualizations with existing techniques on a variety of datasets, including image and scRNA-seq data. We then show that our clustering algorithm performs similarly to the state of the art despite not having prior knowledge of the number of clusters, and sets a new state of the art on FashionMNIST. Finally, we demonstrate finding differentiating features of a dataset. Code available at https://github.com/isaacrob/DEN

Isaac Robinson, Emma Pierce-Hoffman

t-SNE and hierarchical clustering are popular methods of exploratory data analysis, particularly in biology. Building on recent advances in speeding up t-SNE and obtaining finer-grained structure, we combine the two to create tree-SNE, a hierarchical clustering and visualization algorithm based on stacked one-dimensional t-SNE embeddings. We also introduce alpha-clustering, which recommends the optimal cluster assignment, without foreknowledge of the number of clusters, based off of the cluster stability across multiple scales. We demonstrate the effectiveness of tree-SNE and alpha-clustering on images of handwritten digits, mass cytometry (CyTOF) data from blood cells, and single-cell RNA-sequencing (scRNA-seq) data from retinal cells. Furthermore, to demonstrate the validity of the visualization, we use alpha-clustering to obtain unsupervised clustering results competitive with the state of the art on several image data sets. Software is available at https://github.com/isaacrob/treesne.