MoCo-Transfer: Investigating out-of-distribution contrastive learning for limited-data domains

Medical imaging data is often siloed within hospitals, limiting the amount of data available for specialized model development. With limited in-domain data, one might hope to leverage larger datasets from related domains. In this paper, we analyze the benefit of transferring self-supervised contrastive representations from moment contrast (MoCo) pretraining on out-of-distribution data to settings with limited data. We consider two X-ray datasets which image different parts of the body, and compare transferring from each other to transferring from ImageNet. We find that depending on quantity of labeled and unlabeled data, contrastive pretraining on larger out-of-distribution datasets can perform nearly as well or better than MoCo pretraining in-domain, and pretraining on related domains leads to higher performance than if one were to use the ImageNet pretrained weights. Finally, we provide a preliminary way of quantifying similarity between datasets.

Reading Between the Mud: A Challenging Motorcycle Racer Number Dataset

This paper introduces the off-road motorcycle Racer number Dataset (RnD), a new challenging dataset for optical character recognition (OCR) research. RnD contains 2,411 images from professional motorsports photographers that depict motorcycle racers in off-road competitions. The images exhibit a wide variety of factors that make OCR difficult, including mud occlusions, motion blur, non-standard fonts, glare, complex backgrounds, etc. The dataset has 5,578 manually annotated bounding boxes around visible motorcycle numbers, along with transcribed digits and letters. Our experiments benchmark leading OCR algorithms and reveal an end-to-end F1 score of only 0.527 on RnD, even after fine-tuning. Analysis of performance on different occlusion types shows mud as the primary challenge, degrading accuracy substantially compared to normal conditions. But the models struggle with other factors including glare, blur, shadows, and dust. Analysis exposes substantial room for improvement and highlights failure cases of existing models. RnD represents a valuable new benchmark to drive innovation in real-world OCR capabilities. The authors hope the community will build upon this dataset and baseline experiments to make progress on the open problem of robustly recognizing text in unconstrained natural environments. The dataset is available at https://github.com/JacobTyo/SwinTextSpotter.

MUDD: A New Re-Identification Dataset with Efficient Annotation for Off-Road Racers in Extreme Conditions

Re-identifying individuals in unconstrained environments remains an open challenge in computer vision. We introduce the Muddy Racer re-IDentification Dataset (MUDD), the first large-scale benchmark for matching identities of motorcycle racers during off-road competitions. MUDD exhibits heavy mud occlusion, motion blurring, complex poses, and extreme lighting conditions previously unseen in existing re-id datasets. We present an annotation methodology incorporating auxiliary information that reduced labeling time by over 65%. We establish benchmark performance using state-of-the-art re-id models including OSNet and ResNet-50. Without fine-tuning, the best models achieve only 33% Rank-1 accuracy. Fine-tuning on MUDD boosts results to 79% Rank-1, but significant room for improvement remains. We analyze the impact of real-world factors including mud, pose, lighting, and more. Our work exposes open problems in re-identifying individuals under extreme conditions. We hope MUDD serves as a diverse and challenging benchmark to spur progress in robust re-id, especially for computer vision applications in emerging sports analytics. All code and data can be found at https://github.com/JacobTyo/MUDD.

Goodhart's Law Applies to NLP's Explanation Benchmarks

Despite the rising popularity of saliency-based explanations, the research community remains at an impasse, facing doubts concerning their purpose, efficacy, and tendency to contradict each other. Seeking to unite the community's efforts around common goals, several recent works have proposed evaluation metrics. In this paper, we critically examine two sets of metrics: the ERASER metrics (comprehensiveness and sufficiency) and the EVAL-X metrics, focusing our inquiry on natural language processing. First, we show that we can inflate a model's comprehensiveness and sufficiency scores dramatically without altering its predictions or explanations on in-distribution test inputs. Our strategy exploits the tendency for extracted explanations and their complements to be "out-of-support" relative to each other and in-distribution inputs. Next, we demonstrate that the EVAL-X metrics can be inflated arbitrarily by a simple method that encodes the label, even though EVAL-X is precisely motivated to address such exploits. Our results raise doubts about the ability of current metrics to guide explainability research, underscoring the need for a broader reassessment of what precisely these metrics are intended to capture.

Can Neural Network Memorization Be Localized?

Recent efforts at explaining the interplay of memorization and generalization in deep overparametrized networks have posited that neural networks $\textit{memorize}$ "hard" examples in the final few layers of the model. Memorization refers to the ability to correctly predict on $\textit{atypical}$ examples of the training set. In this work, we show that rather than being confined to individual layers, memorization is a phenomenon confined to a small set of neurons in various layers of the model. First, via three experimental sources of converging evidence, we find that most layers are redundant for the memorization of examples and the layers that contribute to example memorization are, in general, not the final layers. The three sources are $\textit{gradient accounting}$ (measuring the contribution to the gradient norms from memorized and clean examples), $\textit{layer rewinding}$ (replacing specific model weights of a converged model with previous training checkpoints), and $\textit{retraining}$ (training rewound layers only on clean examples). Second, we ask a more generic question: can memorization be localized $\textit{anywhere}$ in a model? We discover that memorization is often confined to a small number of neurons or channels (around 5) of the model. Based on these insights we propose a new form of dropout -- $\textit{example-tied dropout}$ that enables us to direct the memorization of examples to an apriori determined set of neurons. By dropping out these neurons, we are able to reduce the accuracy on memorized examples from $100\%\to3\%$, while also reducing the generalization gap.

T-MARS: Improving Visual Representations by Circumventing Text Feature Learning

Large web-sourced multimodal datasets have powered a slew of new methods for learning general-purpose visual representations, advancing the state of the art in computer vision and revolutionizing zero- and few-shot recognition. One crucial decision facing practitioners is how, if at all, to curate these ever-larger datasets. For example, the creators of the LAION-5B dataset chose to retain only image-caption pairs whose CLIP similarity score exceeded a designated threshold. In this paper, we propose a new state-of-the-art data filtering approach motivated by our observation that nearly 40% of LAION's images contain text that overlaps significantly with the caption. Intuitively, such data could be wasteful as it incentivizes models to perform optical character recognition rather than learning visual features. However, naively removing all such data could also be wasteful, as it throws away images that contain visual features (in addition to overlapping text). Our simple and scalable approach, T-MARS (Text Masking and Re-Scoring), filters out only those pairs where the text dominates the remaining visual features -- by first masking out the text and then filtering out those with a low CLIP similarity score of the masked image. Experimentally, T-MARS outperforms the top-ranked method on the "medium scale" of DataComp (a data filtering benchmark) by a margin of 6.5% on ImageNet and 4.7% on VTAB. Additionally, our systematic evaluation on various data pool sizes from 2M to 64M shows that the accuracy gains enjoyed by T-MARS linearly increase as data and compute are scaled exponentially. Code is available at https://github.com/locuslab/T-MARS.

Moral Machine or Tyranny of the Majority?

With Artificial Intelligence systems increasingly applied in consequential domains, researchers have begun to ask how these systems ought to act in ethically charged situations where even humans lack consensus. In the Moral Machine project, researchers crowdsourced answers to "Trolley Problems" concerning autonomous vehicles. Subsequently, Noothigattu et al. (2018) proposed inferring linear functions that approximate each individual's preferences and aggregating these linear models by averaging parameters across the population. In this paper, we examine this averaging mechanism, focusing on fairness concerns in the presence of strategic effects. We investigate a simple setting where the population consists of two groups, with the minority constituting an {\alpha} < 0.5 share of the population. To simplify the analysis, we consider the extreme case in which within-group preferences are homogeneous. Focusing on the fraction of contested cases where the minority group prevails, we make the following observations: (a) even when all parties report their preferences truthfully, the fraction of disputes where the minority prevails is less than proportionate in {\alpha}; (b) the degree of sub-proportionality grows more severe as the level of disagreement between the groups increases; (c) when parties report preferences strategically, pure strategy equilibria do not always exist; and (d) whenever a pure strategy equilibrium exists, the majority group prevails 100% of the time. These findings raise concerns about stability and fairness of preference vector averaging as a mechanism for aggregating diverging voices. Finally, we discuss alternatives, including randomized dictatorship and median-based mechanisms.

PromptNER: Prompting For Named Entity Recognition

In a surprising turn, Large Language Models (LLMs) together with a growing arsenal of prompt-based heuristics now offer powerful off-the-shelf approaches providing few-shot solutions to myriad classic NLP problems. However, despite promising early results, these LLM-based few-shot methods remain far from the state of the art in Named Entity Recognition (NER), where prevailing methods include learning representations via end-to-end structural understanding and fine-tuning on standard labeled corpora. In this paper, we introduce PromptNER, a new state-of-the-art algorithm for few-Shot and cross-domain NER. To adapt to any new NER task PromptNER requires a set of entity definitions in addition to the standard few-shot examples. Given a sentence, PromptNER prompts an LLM to produce a list of potential entities along with corresponding explanations justifying their compatibility with the provided entity type definitions. Remarkably, PromptNER achieves state-of-the-art performance on few-shot NER, achieving an 11% (absolute) improvement in F1 score on the ConLL dataset, and a 10% (absolute) improvement on the FewNERD dataset. PromptNER also moves the state of the art on Cross Domain NER, outperforming all prior methods (including those not limited to the few-shot setting), setting a new mark on all 5 CrossNER target domains, with an average F1 gain of 9%, despite using less than 2% of the available data.

USB: A Unified Summarization Benchmark Across Tasks and Domains

An abundance of datasets exist for training and evaluating models on the task of summary generation.However, these datasets are often derived heuristically, and lack sufficient annotations to support research into all aspects of summarization, such as evidence extraction and controllable summarization. We introduce a benchmark comprising 8 tasks that require multi-dimensional understanding of summarization, e.g., surfacing evidence for a summary, assessing its correctness, and gauging its relevance to different topics. We compare various methods on this benchmark and discover that on multiple tasks, moderately-sized fine-tuned models consistently outperform much larger few-shot prompted language models. For factuality related tasks, we also evaluate existing heuristics to create training data and find that training on them performs worse than training on $20\times$ less human-labeled data. Our benchmark consists of data from 6 different domains, allowing us to study cross-domain performance of trained models. We find that for some tasks, the amount of training data matters more than the domain where it comes from, while for other tasks training specifically on data from the target domain, even if limited, is more beneficial. Our work fulfills the need for a well-annotated summarization benchmark with diverse tasks, and provides useful insights about the impact of the quality, size and domain of training data.

Evaluating Model Performance in Medical Datasets Over Time

Machine learning (ML) models deployed in healthcare systems must face data drawn from continually evolving environments. However, researchers proposing such models typically evaluate them in a time-agnostic manner, splitting datasets according to patients sampled randomly throughout the entire study time period. This work proposes the Evaluation on Medical Datasets Over Time (EMDOT) framework, which evaluates the performance of a model class across time. Inspired by the concept of backtesting, EMDOT simulates possible training procedures that practitioners might have been able to execute at each point in time and evaluates the resulting models on all future time points. Evaluating both linear and more complex models on six distinct medical data sources (tabular and imaging), we show how depending on the dataset, using all historical data may be ideal in many cases, whereas using a window of the most recent data could be advantageous in others. In datasets where models suffer from sudden degradations in performance, we investigate plausible explanations for these shocks. We release the EMDOT package to help facilitate further works in deployment-oriented evaluation over time.