Related papers: Detecting Spurious Correlations via Robust Visual …

Shortcut mitigation strategies commonly rely on training data annotations, group-balanced held-out data or the presence of all groups, i.e., all combinations of (spurious) attributes and classes, in the training data. However, these…

Recent works find that AI algorithms learn biases from data. Therefore, it is urgent and vital to identify biases in AI algorithms. However, the previous bias identification pipeline overly relies on human experts to conjecture potential…

The recent development of generative models unleashes the potential of generating hyper-realistic fake images. To prevent the malicious usage of fake images, AI-generated image detection aims to distinguish fake images from real images.…

State-of-the-art AI models largely lack an understanding of the cause-effect relationship that governs human understanding of the real world. Consequently, these models do not generalize to unseen data, often produce unfair results, and are…

This paper proposes an explicit way to optimize the super-resolution network for generating visually pleasing images. The previous approaches use several loss functions which is hard to interpret and has the implicit relationships to…

We consider the problem of visually explaining similarity models, i.e., explaining why a model predicts two images to be similar in addition to producing a scalar score. While much recent work in visual model interpretability has focused on…

Sub-visible particle analysis using flow imaging microscopy combined with deep learning has proven effective in identifying particle types, enabling the distinction of harmless components such as silicone oil from protein particles.…

Recent advances in AI-powered image editing tools have significantly lowered the barrier to image modification, raising pressing security concerns those related to spreading misinformation and disinformation on social platforms. Image…

As synthetic content increasingly infiltrates the web, generative AI models may be retrained on their own outputs: a process termed "autophagy". This leads to model collapse: a progressive loss of performance and diversity across…

Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for…

In prediction tasks, there exist features that are related to the label in the same way across different settings for that task; these are semantic features or semantics. Features with varying relationships to the label are nuisances. For…

As AI-generated images become increasingly photorealistic, distinguishing them from natural images poses a growing challenge. This paper presents a robust detection framework that leverages multiple uncertainty measures to decide whether to…

As applications of generative AI become mainstream, it is important to understand what generative models are capable of producing, and the extent to which one can predictably control their outputs. In this paper, we propose a visualization…

Patch-wise multi-label classification provides an efficient alternative to full pixel-wise segmentation on high-resolution images, particularly when the objective is to determine the presence or absence of target objects within a patch…

AI-generated imagery has reached near-photorealistic fidelity, yet this technology poses significant threats to information security and societal trust. Existing deepfake detection methods often exhibit limited robustness in open-world…

Trained on massive amounts of human-generated content, AI-generated image synthesis is capable of reproducing semantically coherent images that match the visual appearance of its training data. We show that when retrained on even small…

Humans can systematically generalize to novel compositions of existing concepts. Recent studies argue that neural networks appear inherently ineffective in such cognitive capacity, leading to a pessimistic view and a lack of attention to…

As generative models continue to evolve, detecting AI-generated images remains a critical challenge. While effective detection methods exist, they often lack formal interpretability and may rely on implicit assumptions about fake content,…

In machine learning, incorporating more data is often seen as a reliable strategy for improving model performance; this work challenges that notion by demonstrating that the addition of external datasets in many cases can hurt the resulting…

By inferring latent groups in the training data, recent works introduce invariant learning to the case where environment annotations are unavailable. Typically, learning group invariance under a majority/minority split is empirically shown…