Recent work has identified substantial disparities in generated images of different geographic regions, including stereotypical depictions of everyday objects like houses and cars. However, existing measures for these disparities have been limited to either human evaluations, which are time-consuming and costly, or automatic metrics evaluating full images, which are unable to attribute these disparities to specific parts of the generated images. In this work, we introduce a new set of metrics, Decomposed Indicators of Disparities in Image Generation (Decomposed-DIG), that allows us to separately measure geographic disparities in the depiction of objects and backgrounds in generated images. Using Decomposed-DIG, we audit a widely used latent diffusion model and find that generated images depict objects with better realism than backgrounds and that backgrounds in generated images tend to contain larger regional disparities than objects. We use Decomposed-DIG to pinpoint specific examples of disparities, such as stereotypical background generation in Africa, struggling to generate modern vehicles in Africa, and unrealistically placing some objects in outdoor settings. Informed by our metric, we use a new prompting structure that enables a 52% worst-region improvement and a 20% average improvement in generated background diversity.

There are a thousand ways to caption an image. Contrastive Language Pretraining (CLIP) on the other hand, works by mapping an image and its caption to a single vector -- limiting how well CLIP-like models can represent the diverse ways to describe an image. In this work, we introduce Llip, Latent Language Image Pretraining, which models the diversity of captions that could match an image. Llip's vision encoder outputs a set of visual features that are mixed into a final representation by conditioning on information derived from the text. We show that Llip outperforms non-contextualized baselines like CLIP and SigLIP on a variety of tasks even with large-scale encoders. Llip improves zero-shot classification by an average of 2.9% zero-shot classification benchmarks with a ViT-G/14 encoder. Specifically, Llip attains a zero-shot top-1 accuracy of 83.5% on ImageNet outperforming a similarly sized CLIP by 1.4%. We also demonstrate improvement on zero-shot retrieval on MS-COCO by 6.0%. We provide a comprehensive analysis of the components introduced by the method and demonstrate that Llip leads to richer visual representations.

Data augmentation (DA) encodes invariance and provides implicit regularization critical to a model's performance in image classification tasks. However, while DA improves average accuracy, recent studies have shown that its impact can be highly class dependent: achieving optimal average accuracy comes at the cost of significantly hurting individual class accuracy by as much as 20% on ImageNet. There has been little progress in resolving class-level accuracy drops due to a limited understanding of these effects. In this work, we present a framework for understanding how DA interacts with class-level learning dynamics. Using higher-quality multi-label annotations on ImageNet, we systematically categorize the affected classes and find that the majority are inherently ambiguous, co-occur, or involve fine-grained distinctions, while DA controls the model's bias towards one of the closely related classes. While many of the previously reported performance drops are explained by multi-label annotations, our analysis of class confusions reveals other sources of accuracy degradation. We show that simple class-conditional augmentation strategies informed by our framework improve performance on the negatively affected classes.

For more than a decade, researchers have measured progress in object recognition on ImageNet-based generalization benchmarks such as ImageNet-A, -C, and -R. Recent advances in foundation models, trained on orders of magnitude more data, have begun to saturate these standard benchmarks, but remain brittle in practice. This suggests standard benchmarks, which tend to focus on predefined or synthetic changes, may not be sufficient for measuring real world generalization. Consequently, we propose studying generalization across geography as a more realistic measure of progress using two datasets of objects from households across the globe. We conduct an extensive empirical evaluation of progress across nearly 100 vision models up to most recent foundation models. We first identify a progress gap between standard benchmarks and real-world, geographical shifts: progress on ImageNet results in up to 2.5x more progress on standard generalization benchmarks than real-world distribution shifts. Second, we study model generalization across geographies by measuring the disparities in performance across regions, a more fine-grained measure of real world generalization. We observe all models have large geographic disparities, even foundation CLIP models, with differences of 7-20% in accuracy between regions. Counter to modern intuition, we discover progress on standard benchmarks fails to improve geographic disparities and often exacerbates them: geographic disparities between the least performant models and today's best models have more than tripled. Our results suggest scaling alone is insufficient for consistent robustness to real-world distribution shifts. Finally, we highlight in early experiments how simple last layer retraining on more representative, curated data can complement scaling as a promising direction of future work, reducing geographic disparity on both benchmarks by over two-thirds.

Neural network classifiers can largely rely on simple spurious features, such as backgrounds, to make predictions. However, even in these cases, we show that they still often learn core features associated with the desired attributes of the data, contrary to recent findings. Inspired by this insight, we demonstrate that simple last layer retraining can match or outperform state-of-the-art approaches on spurious correlation benchmarks, but with profoundly lower complexity and computational expenses. Moreover, we show that last layer retraining on large ImageNet-trained models can also significantly reduce reliance on background and texture information, improving robustness to covariate shift, after only minutes of training on a single GPU.

Deep neural networks are susceptible to shortcut learning, using simple features to achieve low training loss without discovering essential semantic structure. Contrary to prior belief, we show that generative models alone are not sufficient to prevent shortcut learning, despite an incentive to recover a more comprehensive representation of the data than discriminative approaches. However, we observe that shortcuts are preferentially encoded with minimal information, a fact that generative models can exploit to mitigate shortcut learning. In particular, we propose Chroma-VAE, a two-pronged approach where a VAE classifier is initially trained to isolate the shortcut in a small latent subspace, allowing a secondary classifier to be trained on the complementary, shortcut-free latent subspace. In addition to demonstrating the efficacy of Chroma-VAE on benchmark and real-world shortcut learning tasks, our work highlights the potential for manipulating the latent space of generative classifiers to isolate or interpret specific correlations.

Learning new tasks continuously without forgetting on a constantly changing data distribution is essential for real-world problems but extremely challenging for modern deep learning. In this work we propose HCL, a Hybrid generative-discriminative approach to Continual Learning for classification. We model the distribution of each task and each class with a normalizing flow. The flow is used to learn the data distribution, perform classification, identify task changes, and avoid forgetting, all leveraging the invertibility and exact likelihood which are uniquely enabled by the normalizing flow model. We use the generative capabilities of the flow to avoid catastrophic forgetting through generative replay and a novel functional regularization technique. For task identification, we use state-of-the-art anomaly detection techniques based on measuring the typicality of the model's statistics. We demonstrate the strong performance of HCL on a range of continual learning benchmarks such as split-MNIST, split-CIFAR, and SVHN-MNIST.

Large, deep networks can learn representations that generalize well. While smaller, more efficient networks lack the inductive biases to find these representations from training data alone, they may have the capacity to represent these solutions [e.g., 1, 16, 27, 39]. Influential work on knowledge distillation [19] argues that Bucilă et al. [4] "demonstrate convincingly that the knowledge acquired by a large ensemble of models [the teacher] can be transferred to a single small model [the student]". Indeed this quote encapsulates the conventional narrative of knowledge distillation: a student model learns a high-fidelity representation of a larger teacher, enabled by the teacher's soft labels. Conversely, in Figure 1 we show that with modern architectures knowledge distillation can lead to students with very different predictions from their teachers, even when the student has the capacity to perfectly match the teacher.

Detecting out-of-distribution (OOD) data is crucial for robust machine learning systems. Normalizing flows are flexible deep generative models that often surprisingly fail to distinguish between in- and out-of-distribution data: a flow trained on pictures of clothing assigns higher likelihood to handwritten digits. We investigate why normalizing flows perform poorly for OOD detection. We demonstrate that flows learn local pixel correlations and generic image-to-latent-space transformations which are not specific to the target image dataset. We show that by modifying the architecture of flow coupling layers we can bias the flow towards learning the semantic structure of the target data, improving OOD detection. Our investigation reveals that properties that enable flows to generate high-fidelity images can have a detrimental effect on OOD detection.

Bayesian inference was once a gold standard for learning with neural networks, providing accurate full predictive distributions and well calibrated uncertainty. However, scaling Bayesian inference techniques to deep neural networks is challenging due to the high dimensionality of the parameter space. In this paper, we construct low-dimensional subspaces of parameter space, such as the first principal components of the stochastic gradient descent (SGD) trajectory, which contain diverse sets of high performing models. In these subspaces, we are able to apply elliptical slice sampling and variational inference, which struggle in the full parameter space. We show that Bayesian model averaging over the induced posterior in these subspaces produces accurate predictions and well calibrated predictive uncertainty for both regression and image classification.