Related papers: Pairwise Matching of Intermediate Representations …
Recent studies show that deep vision-only and language-only models--trained on disjoint modalities--nonetheless project their inputs into a partially aligned representational space. Yet we still lack a clear picture of where in each network…
This paper explores the intricate relationship between interpretability and robustness in deep learning models. Despite their remarkable performance across various tasks, deep learning models often exhibit critical vulnerabilities,…
Vision-language models like CLIP show impressive ability to align images and text, but their training on short, concise captions makes them struggle with lengthy, detailed descriptions. Recent advances mitigate this challenge by leveraging…
Evaluating the alignment between textual prompts and generated images is critical for ensuring the reliability and usability of text-to-image (T2I) models. However, most existing evaluation methods rely on coarse-grained metrics or static…
This paper addresses the problem of matching pedestrians across multiple camera views, known as person re-identification. Variations in lighting conditions, environment and pose changes across camera views make re-identification a…
Extracting effective and discriminative features is very important for addressing the challenging person re-identification (re-ID) task. Prevailing deep convolutional neural networks (CNNs) usually use high-level features for identifying…
Many high-performance models suffer from a lack of interpretability. There has been an increasing influx of work on explainable artificial intelligence (XAI) in order to disentangle what is meant and expected by XAI. Nevertheless, there is…
We present a simple yet highly generalizable method for explaining interacting parts within a neural network's reasoning process. First, we design an algorithm based on cross derivatives for computing statistical interaction effects between…
Visual document retrieval aims to retrieve a set of document pages relevant to a query from visually rich collections. Existing methods often employ Vision-Language Models (VLMs) to encode queries and visual pages into a shared embedding…
Explainable Artificial Intelligence (XAI) has gained importance in interpreting model predictions. Among leading techniques for XAI, Local Interpretable Model-agnostic Explanations (LIME) is most frequently utilized as it notably helps…
Sparse keypoint matching is crucial for 3D vision tasks, yet current keypoint detectors often produce spatially inaccurate matches. Existing refinement methods mitigate this issue through alignment of matched keypoint locations, but they…
As artificial intelligence systems become increasingly integrated into daily life, the field of explainability has gained significant attention. This trend is particularly driven by the complexity of modern AI models and their…
Modern data augmentation using a mixture-based technique can regularize the models from overfitting to the training data in various computer vision applications, but a proper data augmentation technique tailored for the part-based…
Semantic part localization can facilitate fine-grained categorization by explicitly isolating subtle appearance differences associated with specific object parts. Methods for pose-normalized representations have been proposed, but generally…
The rapid advancement of AI-generation models has enabled the creation of hyperrealistic imagery, posing ethical risks through widespread misinformation. Current deepfake detection methods, categorized as face specific detectors or general…
Providing a human-understandable explanation of classifiers' decisions has become imperative to generate trust in their use for day-to-day tasks. Although many works have addressed this problem by generating visual explanation maps, they…
Human understandable explanation of deep learning models is essential for various critical and sensitive applications. Unlike image or tabular data where the importance of each input feature (for the classifier's decision) can be directly…
The person re-identification task requires to robustly estimate visual similarities between person images. However, existing person re-identification models mostly estimate the similarities of different image pairs of probe and gallery…
Person re-identification (\textit{re-id}) refers to matching pedestrians across disjoint yet non-overlapping camera views. The most effective way to match these pedestrians undertaking significant visual variations is to seek reliably…
We examine several aspects of explicability of a classification system built from neural networks. The first aspect is the pairwise explicability, which is the ability to provide the most accurate prediction when the range of possibilities…