StreetStyle's Two-Part Engine: How One Framework Tracks Known Fashion Trends and Discovers New Ones

The StreetStyle framework employs a two-part engine to analyze fashion trends: supervised learning tracks known attributes, while unsupervised clustering discovers novel styles from millions of social media photos. This computational approach offers a comprehensive view of global and localized fashion movements.

Jasmine Santos

October 31, 2026 · 4 min read

For street style photographers and trend analysts, spotting an emerging trend has traditionally meant standing at the right intersection with the right eye. A 2017 research project from Cornell University—StreetStyle, by Kevin Matzen, Kavita Bala and Noah Snavely—proposed a computational alternative: mine millions of street photos from social media, then let two distinct machine learning processes work in tandem. One tracks fashion attributes you already know to look for; the other surfaces coherent style groupings you never thought to define. Understanding that division of labor is the most useful idea fashion professionals can borrow from the project.

Introduction to the StreetStyle Framework

The project's premise is scale. Each day, the researchers observed, billions of photographs are uploaded to photo-sharing services and social platforms—images packed with information about how people live and dress. Rather than sampling from fashion week coverage, Matzen, Bala and Snavely exploited this trove of social media imagery to understand fashion and style trends worldwide, analyzing millions of photos of people spanning several years and many cities.

Clothing, as they note, is a demanding subject for computer vision: analyzing it requires both detailed attribute-level understanding and social context. The framework's response was a large-scale dataset of photos annotated with clothing attributes—labels such as "wearing glasses" or "short sleeves"—built on earlier vision research that describes people in terms of clothing attributes and recognizes those attributes in new images.

Part 1: Tracking Known Attributes with Supervised Learning

The first half of the engine is supervised learning. Researchers annotate a training dataset of photos with known clothing attributes, then use deep learning to train classifiers that predict those same attributes in new, unlabeled images. The process is "supervised" because a human decision precedes it: someone decides which attributes matter—black clothing, sleeve length, headwear—and the system learns to detect them consistently across millions of photos.

Crucially, this half answers predetermined questions. If you want to know whether short sleeves are rising in Seoul or whether black dominates in Los Angeles, you define the attribute first and let the classifier measure it at scale. The approach inherits the structure of the dataset's annotations: it can only track what it was explicitly trained to recognize.

The Two-Part StreetStyle Analytical Engine

The framework's logic becomes clear when its components are laid side by side. The table below deconstructs StreetStyle into its pipeline, showing how each stage feeds the next and what each process contributes to the final output.

How StreetStyle processes street photos into trend insight
Stage	What happens	What it produces
Input: millions of photos	A large-scale dataset of photos of people from social media, annotated with clothing attributes	Raw material spanning several years and many cities worldwide
Process 1: supervised learning	Deep learning trains attribute classifiers on the annotated dataset to predict pre-defined clothing attributes in new images	Measurable attribute labels—for example, whether a person is wearing black
Process 2: unsupervised clustering	A method automatically detects visually consistent style clusters and correlations within the massive dataset, without prior definitions	Emergent style groupings, including localized patterns like particular types of headwear
Output: spatio-temporal analysis	Attribute proportions and style clusters are analyzed by city and over time	A first-of-its-kind view of global and per-city fashion choices and trends across years

The two processes are complementary rather than redundant. Supervised classifiers yield quantifiable, comparable trend lines; unsupervised clustering yields unexpected groupings that would otherwise go unnamed. Together they produced the project's analysis of global and per-city fashion choices and spatio-temporal trends.