Related papers: IFShip: Interpretable Fine-grained Ship Classifica…

Language-vision models like CLIP have made significant strides in vision tasks, such as zero-shot image classification (ZSIC). However, generating specific and expressive visual descriptions remains challenging; descriptions produced by…

Conventional Time Series Classification (TSC) methods are often black boxes that obscure inherent interpretation of their decision-making processes. In this work, we leverage Multiple Instance Learning (MIL) to overcome this issue, and…

We introduce CoT-ICL Lab, a framework and methodology to generate synthetic tokenized datasets and systematically study chain-of-thought (CoT) in-context learning (ICL) in language models. CoT-ICL Lab allows fine grained control over the…

Referring Expression Comprehension (REC) is a crucial cross-modal task that objectively evaluates the capabilities of language understanding, image comprehension, and language-to-image grounding. Consequently, it serves as an ideal testing…

Unmanned Aerial Vehicle (UAV) Vision-and-Language Navigation (VLN) is vital for applications such as disaster response, logistics delivery, and urban inspection. However, existing methods often struggle with insufficient multimodal fusion,…

While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow and are dominated by a text-centric paradigm, limiting their applicability to complex visual…

Deep learning algorithms have recently gained significant attention due to their impressive performance. However, their high complexity and un-interpretable mode of operation hinders their confident deployment in real-world safety-critical…

This paper presents a novel concept learning framework for enhancing model interpretability and performance in visual classification tasks. Our approach appends an unsupervised explanation generator to the primary classifier network and…

Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintaining interpretability…

Explainable AI has emerged to be a key component for black-box machine learning approaches in domains with a high demand for reliability or transparency. Examples are medical assistant systems, and applications concerned with the General…

Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My…

We aim to provide a computationally cheap yet effective approach for fine-grained image classification (FGIC) in this letter. Unlike previous methods that rely on complex part localization modules, our approach learns fine-grained features…

Mechanistic interpretability seeks to understand the neural mechanisms that enable specific behaviors in Large Language Models (LLMs) by leveraging causality-based methods. While these approaches have identified neural circuits that copy…

Depicting novel classes with language descriptions by observing few-shot samples is inherent in human-learning systems. This lifelong learning capability helps to distinguish new knowledge from old ones through the increase of open-world…

Infrared ship detection (IRSD) has received increasing attention in recent years due to the robustness of infrared images to adverse weather. However, a large number of false alarms may occur in complex scenes. To address these challenges,…

State-of-the-art intent classification (IC) and slot filling (SF) methods often rely on data-intensive deep learning models, limiting their practicality for industry applications. Large language models on the other hand, particularly…

Grasping is one of the most fundamental challenging capabilities in robotic manipulation, especially in unstructured, cluttered, and semantically diverse environments. Recent researches have increasingly explored language-guided…

Robotic grasping is one of the most fundamental tasks in robotic manipulation, and grasp detection/generation has long been the subject of extensive research. Recently, language-driven grasp generation has emerged as a promising direction…

Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clouds or depth, either…

Recent research on model interpretability in natural language processing extensively uses feature scoring methods for identifying which parts of the input are the most important for a model to make a prediction (i.e. explanation or…