Abstract:AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which produce divergent scores for nominally identical evaluations and record metadata inconsistently, hindering comparison, cross-community evaluation science, cost reduction, and reuse. We introduce Every Eval Ever, the first shared schema and community-crowdsourced repository for AI evaluation results. The schema standardizes how evaluations are represented in a unified, single JSON document. It is source-agnostic by design, ingesting results from evaluation harnesses and papers alike, and optionally stores per-instance outputs for fine-grained analysis. We contribute: (i) a community-governed metadata schema with a companion instance-level schema, the first standardization effort of its kind; (ii) automatic converters from popular formats, evaluation harnesses, and leaderboards to the unified schema; and (iii) a crowdsourced community database hosted on Hugging Face, currently spanning to date 22,235 models, 2,273 unique benchmarks, and 31 evaluation formats.
Abstract:We introduce a new -- currently 42 gigabyte -- ``living'' dataset of phone images of dog feces, annotated with manually drawn or AI-assisted polygon labels. There are 6k full resolution images and 4k detailed polygon annotations. The collection and annotation of images started in late 2020 and the dataset grows by roughly 1GB a month. We train VIT and MaskRCNN baseline models to explore the difficulty of the dataset. The best model achieves a pixelwise average precision of 0.858 on a 691-image validation set and 0.847 on a small independently captured 30-image contributor test set. The most recent snapshot of dataset is made publicly available through three different distribution methods: one centralized (Girder) and two decentralized (IPFS and BitTorrent). We study of the trade-offs between distribution methods and discuss the feasibility of each with respect to reliably sharing open scientific data. The code to reproduce the experiments is hosted on GitHub, and the data is published under the Creative Commons Attribution 4.0 International license. Model weights are made publicly available with the dataset. Experimental hardware, time, energy, and emissions are quantified.
Abstract:Learning from multiple sensors is challenging due to spatio-temporal misalignment and differences in resolution and captured spectra. To that end, we introduce GeoWATCH, a flexible framework for training models on long sequences of satellite images sourced from multiple sensor platforms, which is designed to handle image classification, activity recognition, object detection, or object tracking tasks. Our system includes a novel partial weight loading mechanism based on sub-graph isomorphism which allows for continually training and modifying a network over many training cycles. This has allowed us to train a lineage of models over a long period of time, which we have observed has improved performance as we adjust configurations while maintaining a core backbone.
Abstract:The performance of a binary classifier is described by a confusion matrix with four entries: the number of true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN). The Matthew's Correlation Coefficient (MCC), F1, and Fowlkes--Mallows (FM) scores are scalars that summarize a confusion matrix. Both the F1 and FM scores are based on only three of the four entries in the confusion matrix (they ignore TN). In contrast, the MCC takes into account all four entries of the confusion matrix and thus can be seen as providing a more representative picture. However, in object detection problems, measuring the number of true negatives is so large it is often intractable. Thus we ask, what happens to the MCC as the number of true negatives approaches infinity? This paper provides insight into the relationship between the MCC and FM score by proving that the FM-measure is equal to the limit of the MCC as the number of true negatives approaches infinity.