Visual grounding seeks to localize the image region corresponding to a free-form text description. Recently, the strong multimodal capabilities of Large Vision-Language Models (LVLMs) have driven substantial improvements in visual grounding, though they inevitably require fine-tuning and additional model components to explicitly generate bounding boxes or segmentation masks. However, we discover that a few attention heads in frozen LVLMs demonstrate strong visual grounding capabilities. We refer to these heads, which consistently capture object locations related to text semantics, as localization heads. Using localization heads, we introduce a straightforward and effective training-free visual grounding framework that utilizes text-to-image attention maps from localization heads to identify the target objects. Surprisingly, only three out of thousands of attention heads are sufficient to achieve competitive localization performance compared to existing LVLM-based visual grounding methods that require fine-tuning. Our findings suggest that LVLMs can innately ground objects based on a deep comprehension of the text-image relationship, as they implicitly focus on relevant image regions to generate informative text outputs. All the source codes will be made available to the public.

Large multimodal models (LMMs) "see" images by leveraging the attention mechanism between text and visual tokens in the transformer decoder. Ideally, these models should focus on key visual information relevant to the text token. However, recent findings indicate that LMMs have an extraordinary tendency to consistently allocate high attention weights to specific visual tokens, even when these tokens are irrelevant to the corresponding text. In this study, we investigate the property behind the appearance of these irrelevant visual tokens and examine their characteristics. Our findings show that this behavior arises due to the massive activation of certain hidden state dimensions, which resembles the attention sink found in language models. Hence, we refer to this phenomenon as the visual attention sink. In particular, our analysis reveals that removing the irrelevant visual sink tokens does not impact model performance, despite receiving high attention weights. Consequently, we recycle the attention to these tokens as surplus resources, redistributing the attention budget to enhance focus on the image. To achieve this, we introduce Visual Attention Redistribution (VAR), a method that redistributes attention in image-centric heads, which we identify as innately focusing on visual information. VAR can be seamlessly applied across different LMMs to improve performance on a wide range of tasks, including general vision-language tasks, visual hallucination tasks, and vision-centric tasks, all without the need for additional training, models, or inference steps. Experimental results demonstrate that VAR enables LMMs to process visual information more effectively by adjusting their internal attention mechanisms, offering a new direction to enhancing the multimodal capabilities of LMMs.

Disentangled representation learning (DRL) aims to break down observed data into core intrinsic factors for a profound understanding of the data. In real-world scenarios, manually defining and labeling these factors are non-trivial, making unsupervised methods attractive. Recently, there have been limited explorations of utilizing diffusion models (DMs), which are already mainstream in generative modeling, for unsupervised DRL. They implement their own inductive bias to ensure that each latent unit input to the DM expresses only one distinct factor. In this context, we design Dynamic Gaussian Anchoring to enforce attribute-separated latent units for more interpretable DRL. This unconventional inductive bias explicitly delineates the decision boundaries between attributes while also promoting the independence among latent units. Additionally, we also propose Skip Dropout technique, which easily modifies the denoising U-Net to be more DRL-friendly, addressing its uncooperative nature with the disentangling feature extractor. Our methods, which carefully consider the latent unit semantics and the distinct DM structure, enhance the practicality of DM-based disentangled representations, demonstrating state-of-the-art disentanglement performance on both synthetic and real data, as well as advantages in downstream tasks.

Tremendous recent literature show that associations between different brain regions, i.e., brain connectivity, provide early symptoms of neurological disorders. Despite significant efforts made for graph neural network (GNN) techniques, their focus on graph nodes makes the state-of-the-art GNN methods not suitable for classifying brain connectivity as graphs where the objective is to characterize disease-relevant network dysfunction patterns on graph links. To address this issue, we propose Multi-resolution Edge Network (MENET) to detect disease-specific connectomic benchmarks with high discrimination power across diagnostic categories. The core of MENET is a novel graph edge-wise transform that we propose, which allows us to capture multi-resolution ``connectomic'' features. Using a rich set of the connectomic features, we devise a graph learning framework to jointly select discriminative edges and assign diagnostic labels for graphs. Experiments on two real datasets show that MENET accurately predicts diagnostic labels and identify brain connectivities highly associated with neurological disorders such as Alzheimer's Disease and Attention-Deficit/Hyperactivity Disorder.

Significant methodological strides have been made toward Chest X-ray (CXR) understanding via modern vision-language models (VLMs), demonstrating impressive Visual Question Answering (VQA) and CXR report generation abilities. However, existing CXR understanding frameworks still possess several procedural caveats. (1) Previous methods solely use CXR reports, which are insufficient for comprehensive Visual Question Answering (VQA), especially when additional health-related data like medication history and prior diagnoses are needed. (2) Previous methods use raw CXR reports, which are often arbitrarily structured. While modern language models can understand various text formats, restructuring reports for clearer, organized anatomy-based information could enhance their usefulness. (3) Current evaluation methods for CXR-VQA primarily emphasize linguistic correctness, lacking the capability to offer nuanced assessments of the generated answers. In this work, to address the aforementioned caveats, we introduce WoLF, a Wide-scope Large Language Model Framework for CXR understanding. To resolve (1), we capture multi-faceted records of patients, which are utilized for accurate diagnoses in real-world clinical scenarios. Specifically, we adopt the Electronic Health Records (EHR) to generate instruction-following data suited for CXR understanding. Regarding (2), we enhance report generation performance by decoupling knowledge in CXR reports based on anatomical structure even within the attention step via masked attention. To address (3), we introduce an AI-evaluation protocol optimized for assessing the capabilities of LLM. Through extensive experimental validations, WoLF demonstrates superior performance over other models on MIMIC-CXR in the AI-evaluation arena about VQA (up to +9.47%p mean score) and by metrics about report generation (+7.3%p BLEU-1).

Transfer learning has been widely utilized to mitigate the data scarcity problem in the field of Alzheimer's disease (AD). Conventional transfer learning relies on re-using models trained on AD-irrelevant tasks such as natural image classification. However, it often leads to negative transfer due to the discrepancy between the non-medical source and target medical domains. To address this, we present evidence-empowered transfer learning for AD diagnosis. Unlike conventional approaches, we leverage an AD-relevant auxiliary task, namely morphological change prediction, without requiring additional MRI data. In this auxiliary task, the diagnosis model learns the evidential and transferable knowledge from morphological features in MRI scans. Experimental results demonstrate that our framework is not only effective in improving detection performance regardless of model capacity, but also more data-efficient and faithful.

Application of deep neural networks to medical imaging tasks has in some sense become commonplace. Still, a "thorn in the side" of the deep learning movement is the argument that deep networks are somehow prone to overfitting and are thus unable to generalize well when datasets are small. The claim is not baseless and likely stems from the observation that PAC bounds on generalization error are usually so large for deep networks that they are vacuous (i.e., logically meaningless). Contrary to this, recent advances using the PAC-Bayesian framework have instead shown non-vacuous bounds on generalization error for large (stochastic) networks and standard datasets (e.g., MNIST and CIFAR-10). We apply these techniques to a much smaller medical imagining dataset (the ISIC 2018 challenge set). Further, we consider generalization of deep networks on segmentation tasks which has not commonly been done using the PAC-Bayesian framework. Importantly, we observe that the resultant bounds are also non-vacuous despite the sharp reduction in sample size. In total, our results demonstrate the applicability of PAC-Bayesian bounds for deep stochastic networks in the medical imaging domain.

There has recently been a concerted effort to derive mechanisms in vision and machine learning systems to offer uncertainty estimates of the predictions they make. Clearly, there are enormous benefits to a system that is not only accurate but also has a sense for when it is not sure. Existing proposals center around Bayesian interpretations of modern deep architectures -- these are effective but can often be computationally demanding. We show how classical ideas in the literature on exponential families on probabilistic networks provide an excellent starting point to derive uncertainty estimates in Gated Recurrent Units (GRU). Our proposal directly quantifies uncertainty deterministically, without the need for costly sampling-based estimation. We demonstrate how our model can be used to quantitatively and qualitatively measure uncertainty in unsupervised image sequence prediction. To our knowledge, this is the first result describing sampling-free uncertainty estimation for powerful sequential models such as GRUs.