Related papers: Debunking Grad-ECLIP: A Comprehensive Study on Its…

Despite the state-of-the-art performance of deep convolutional neural networks, they are susceptible to bias and malfunction in unseen situations. Moreover, the complex computation behind their reasoning is not human-understandable to…

Current image quality assessment methods are heavily biased towards global distortions (e.g., noise, blur), neglecting local perceptual artifacts such as ghosting, lens flare, and moire effects. Although significant progress has been made…

The success of Transformer language models is widely credited to their dot-product attention mechanism, which interweaves a set of key design principles: mixing information across positions (enabling multi-token interactions),…

Several explanation methods such as Integrated Gradients (IG) can be characterised as path-based methods, as they rely on a straight line between the data and an uninformative baseline. However, when applied to language models, these…

Prompt learning has propelled vision-language models like CLIP to excel in diverse tasks, making them ideal for federated learning due to computational efficiency. However, conventional approaches that rely solely on final-layer features…

Transformer-based models have recently shown success in representation learning on graph-structured data beyond natural language processing and computer vision. However, the success is limited to small-scale graphs due to the drawbacks of…

Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time. With the advancement of vision-language pre-trained models such as CLIP, they…

Conventional object detectors rely on cross-entropy classification, which can be vulnerable to class imbalance and label noise. We propose CLIP-Joint-Detect, a simple and detector-agnostic framework that integrates CLIP-style contrastive…

Many recent deep learning-based solutions have widely adopted the attention-based mechanism in various tasks of the NLP discipline. However, the inherent characteristics of deep learning models and the flexibility of the attention mechanism…

We propose a technique for producing "visual explanations" for decisions from a large class of CNN-based models, making them more transparent. Our approach - Gradient-weighted Class Activation Mapping (Grad-CAM), uses the gradients of any…

The task of graph-level anomaly detection (GLAD) is to identify anomalous graphs that deviate significantly from the majority of graphs in a dataset. While deep GLAD methods have shown promising performance, their black-box nature limits…

Graph learning is a prevalent field that operates on ubiquitous graph data. Effective graph learning methods can extract valuable information from graphs. However, these methods are non-robust and affected by missing attributes in graphs,…

Node representation learning in a network is an important machine learning technique for encoding relational information in a continuous vector space while preserving the inherent properties and structures of the network. Recently,…

Object categories are typically organized into a multi-granularity taxonomic hierarchy. When classifying categories at different hierarchy levels, traditional uni-modal approaches focus primarily on image features, revealing limitations in…

Despite the success of Vision-Language Models (VLMs) like CLIP in aligning vision and language, their proficiency in detailed, fine-grained visual comprehension remains a key challenge. We present CLIP-IN, a novel framework that bolsters…

Gaze estimation methods often experience significant performance degradation when evaluated across different domains, due to the domain gap between the testing and training data. Existing methods try to address this issue using various…

Convolutional neural networks have become state-of-the-art in a wide range of image recognition tasks. The interpretation of their predictions, however, is an active area of research. Whereas various interpretation methods have been…

Diabetic retinopathy (DR) is a complication of diabetes and usually takes decades to reach sight-threatening levels. Accurate and robust detection of DR severity is critical for the timely management and treatment of diabetes. However, most…

Vision Transformer(ViT) is one of the most widely used models in the computer vision field with its great performance on various tasks. In order to fully utilize the ViT-based architecture in various applications, proper visualization…

Contrastive Language-Image Pretraining (CLIP) model has exhibited remarkable efficacy in establishing cross-modal connections between texts and images, yielding impressive performance across a broad spectrum of downstream applications…