SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection

Misinformation is a prevalent societal issue due to its potential high risks. Out-of-context (OOC) misinformation, where authentic images are repurposed with false text, is one of the easiest and most effective ways to mislead audiences. Current methods focus on assessing image-text consistency but lack convincing explanations for their judgments, which is essential for debunking misinformation. While Multimodal Large Language Models (MLLMs) have rich knowledge and innate capability for visual reasoning and explanation generation, they still lack sophistication in understanding and discovering the subtle crossmodal differences. In this paper, we introduce SNIFFER, a novel multimodal large language model specifically engineered for OOC misinformation detection and explanation. SNIFFER employs two-stage instruction tuning on InstructBLIP. The first stage refines the model's concept alignment of generic objects with news-domain entities and the second stage leverages language-only GPT-4 generated OOC-specific instruction data to fine-tune the model's discriminatory powers. Enhanced by external tools and retrieval, SNIFFER not only detects inconsistencies between text and image but also utilizes external knowledge for contextual verification. Our experiments show that SNIFFER surpasses the original MLLM by over 40% and outperforms state-of-the-art methods in detection accuracy. SNIFFER also provides accurate and persuasive explanations as validated by quantitative and human evaluations.

Leveraging Old Knowledge to Continually Learn New Classes in Medical Images

Class-incremental continual learning is a core step towards developing artificial intelligence systems that can continuously adapt to changes in the environment by learning new concepts without forgetting those previously learned. This is especially needed in the medical domain where continually learning from new incoming data is required to classify an expanded set of diseases. In this work, we focus on how old knowledge can be leveraged to learn new classes without catastrophic forgetting. We propose a framework that comprises of two main components: (1) a dynamic architecture with expanding representations to preserve previously learned features and accommodate new features; and (2) a training procedure alternating between two objectives to balance the learning of new features while maintaining the model's performance on old classes. Experiment results on multiple medical datasets show that our solution is able to achieve superior performance over state-of-the-art baselines in terms of class accuracy and forgetting.

Distributional Shifts in Automated Diabetic Retinopathy Screening

Deep learning-based models are developed to automatically detect if a retina image is `referable' in diabetic retinopathy (DR) screening. However, their classification accuracy degrades as the input images distributionally shift from their training distribution. Further, even if the input is not a retina image, a standard DR classifier produces a high confident prediction that the image is `referable'. Our paper presents a Dirichlet Prior Network-based framework to address this issue. It utilizes an out-of-distribution (OOD) detector model and a DR classification model to improve generalizability by identifying OOD images. Experiments on real-world datasets indicate that the proposed framework can eliminate the unknown non-retina images and identify the distributionally shifted retina images for human intervention.

Towards Fully Interpretable Deep Neural Networks: Are We There Yet?

Despite the remarkable performance, Deep Neural Networks (DNNs) behave as black-boxes hindering user trust in Artificial Intelligence (AI) systems. Research on opening black-box DNN can be broadly categorized into post-hoc methods and inherently interpretable DNNs. While many surveys have been conducted on post-hoc interpretation methods, little effort is devoted to inherently interpretable DNNs. This paper provides a review of existing methods to develop DNNs with intrinsic interpretability, with a focus on Convolutional Neural Networks (CNNs). The aim is to understand the current progress towards fully interpretable DNNs that can cater to different interpretation requirements. Finally, we identify gaps in current work and suggest potential research directions.

Adversarially Robust Classifier with Covariate Shift Adaptation

Existing adversarially trained models typically perform inference on test examples independently from each other. This mode of testing is unable to handle covariate shift in the test samples. Due to this, the performance of these models often degrades significantly. In this paper, we show that simple adaptive batch normalization (BN) technique that involves re-estimating the batch-normalization parameters during inference, can significantly improve the robustness of these models for any random perturbations, including the Gaussian noise. This simple finding enables us to transform adversarially trained models into randomized smoothing classifiers to produce certified robustness to $\ell_2$ noise. We show that we can achieve $\ell_2$ certified robustness even for adversarially trained models using $\ell_{\infty}$-bounded adversarial examples. We further demonstrate that adaptive BN technique significantly improves robustness against common corruptions, while often enhancing performance against adversarial attacks. This enables us to achieve both adversarial and corruption robustness for the same classifier.

Learning Semantically Meaningful Features for Interpretable Classifications

Learning semantically meaningful features is important for Deep Neural Networks to win end-user trust. Attempts to generate post-hoc explanations fall short in gaining user confidence as they do not improve the interpretability of feature representations learned by the models. In this work, we propose Semantic Convolutional Neural Network (SemCNN) that has an additional Concept layer to learn the associations between visual features and word phrases. SemCNN employs an objective function that optimizes for both the prediction accuracy as well as the semantic meaningfulness of the learned feature representations. Further, SemCNN makes its decisions as a weighted sum of the contributions of these features leading to fully interpretable decisions. Experiment results on multiple benchmark datasets demonstrate that SemCNN can learn features with clear semantic meaning and their corresponding contributions to the model decision without compromising prediction accuracy. Furthermore, these learned concepts are transferrable and can be applied to new classes of objects that have similar concepts.

Towards Maximizing the Representation Gap between In-Domain \& Out-of-Distribution Examples

Among existing uncertainty estimation approaches, Dirichlet Prior Network (DPN) distinctly models different predictive uncertainty types. However, for in-domain examples with high data uncertainties among multiple classes, even a DPN model often produces indistinguishable representations from the out-of-distribution (OOD) examples, compromising their OOD detection performance. We address this shortcoming by proposing a novel loss function for DPN to maximize the \textit{representation gap} between in-domain and OOD examples. Experimental results demonstrate that our proposed approach consistently improves OOD detection performance.

Approximate Manifold Defense Against Multiple Adversarial Perturbations

Existing defenses against adversarial attacks are typically tailored to a specific perturbation type. Using adversarial training to defend against multiple types of perturbation requires expensive adversarial examples from different perturbation types at each training step. In contrast, manifold-based defense incorporates a generative network to project an input sample onto the clean data manifold. This approach eliminates the need to generate expensive adversarial examples while achieving robustness against multiple perturbation types. However, the success of this approach relies on whether the generative network can capture the complete clean data manifold, which remains an open problem for complex input domain. In this work, we devise an approximate manifold defense mechanism, called RBF-CNN, for image classification. Instead of capturing the complete data manifold, we use an RBF layer to learn the density of small image patches. RBF-CNN also utilizes a reconstruction layer that mitigates any minor adversarial perturbations. Further, incorporating our proposed reconstruction process for training improves the adversarial robustness of our RBF-CNN models. Experiment results on MNIST and CIFAR-10 datasets indicate that RBF-CNN offers robustness for multiple perturbations without the need for expensive adversarial training.

Normal Similarity Network for Generative Modelling

Gaussian distributions are commonly used as a key building block in many generative models. However, their applicability has not been well explored in deep networks. In this paper, we propose a novel deep generative model named as Normal Similarity Network (NSN) where the layers are constructed with Gaussian-style filters. NSN is trained with a layer-wise non-parametric density estimation algorithm that iteratively down-samples the training images and captures the density of the down-sampled training images in the final layer. Additionally, we propose NSN-Gen for generating new samples from noise vectors by iteratively reconstructing feature maps in the hidden layers of NSN. Our experiments suggest encouraging results of the proposed model for a wide range of computer vision applications including image generation, styling and reconstruction from occluded images.

Quantifying Aspect Bias in Ordinal Ratings using a Bayesian Approach

User opinions expressed in the form of ratings can influence an individual's view of an item. However, the true quality of an item is often obfuscated by user biases, and it is not obvious from the observed ratings the importance different users place on different aspects of an item. We propose a probabilistic modeling of the observed aspect ratings to infer (i) each user's aspect bias and (ii) latent intrinsic quality of an item. We model multi-aspect ratings as ordered discrete data and encode the dependency between different aspects by using a latent Gaussian structure. We handle the Gaussian-Categorical non-conjugacy using a stick-breaking formulation coupled with P\'{o}lya-Gamma auxiliary variable augmentation for a simple, fully Bayesian inference. On two real world datasets, we demonstrate the predictive ability of our model and its effectiveness in learning explainable user biases to provide insights towards a more reliable product quality estimation.