Related papers: CEIR: Concept-based Explainable Image Representati…

Effectively explaining decisions of black-box machine learning models is critical to responsible deployment of AI systems that rely on them. Recognizing their importance, the field of explainable AI (XAI) provides several techniques to…

Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of…

Goal-oriented semantic communication (SC) aims to revolutionize communication systems by transmitting only task-essential information. However, current approaches face challenges such as joint training at transceivers, leading to redundant…

Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible. A natural image could be assigned with fine-grained labels that describe major components, coarse-grained labels…

Deep learning models have achieved state-of-the-art performance in many computer vision tasks. However, in real-world scenarios, novel classes that were unseen during training often emerge, requiring models to acquire new knowledge…

Composed image retrieval attempts to retrieve an image of interest from gallery images through a composed query of a reference image and its corresponding modified text. It has recently attracted attention due to the collaboration of…

CLIP has shown impressive results in aligning images and texts at scale. However, its ability to capture detailed visual features remains limited because CLIP matches images and texts at a global level. To address this issue, we propose…

Modern deep neural networks have now reached human-level performance across a variety of tasks. However, unlike humans they lack the ability to explain their decisions by showing where and telling what concepts guided them. In this work, we…

In many computer vision applications, images are acquired with arbitrary or random rotations and translations, and in such setups, it is desirable to obtain semantic representations disentangled from the image orientation. Examples of such…

Interpreting individual neurons in deep neural networks is a crucial step towards understanding their complex decision-making processes and ensuring AI safety. Despite recent progress in neuron labeling, existing methods often limit the…

While deep learning, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), has significantly advanced classification performance, its typical reliance on extensive annotated datasets presents a major obstacle in…

EXplainable AI (XAI) is an essential topic to improve human understanding of deep neural networks (DNNs) given their black-box internals. For computer vision tasks, mainstream pixel-based XAI methods explain DNN decisions by identifying…

This paper evaluates whether training a decision tree based on concepts extracted from a concept-based explainer can increase interpretability for Convolutional Neural Networks (CNNs) models and boost the fidelity and performance of the…

Retrieval is being redefined by agentic AI, demanding multimodal reasoning beyond conventional similarity-based paradigms. Composed Image Retrieval (CIR) exemplifies this shift as each query combines a reference image with textual…

This paper introduces the Contextual Evaluation Model (CEM), a novel method for knowledge representation and manipulation. The CEM differs from existing models in that it integrates facts, patterns and sequences into a single contextual…

Context-Aware Emotion Recognition (CAER) is a crucial and challenging task that aims to perceive the emotional states of the target person with contextual information. Recent approaches invariably focus on designing sophisticated…

Concept-Based Models (CBMs) are a class of deep learning models that provide interpretability by explaining predictions through high-level concepts. These models first predict concepts and then use them to perform a downstream task.…

Automatically describing an image with a sentence is a long-standing challenge in computer vision and natural language processing. Due to recent progress in object detection, attribute classification, action recognition, etc., there is…

Speech emotion recognition (SER) is a key technology to enable more natural human-machine communication. However, SER has long suffered from a lack of public large-scale labeled datasets. To circumvent this problem, we investigate how…

We introduce the Evidential Transformer, an uncertainty-driven transformer model for improved and robust image retrieval. In this paper, we make several contributions to content-based image retrieval (CBIR). We incorporate probabilistic…