Related papers: E-TCAV: Formalizing Penultimate Proxies for Effici…

In high stakes applications such as healthcare and finance analytics, the interpretability of predictive models is required and necessary for domain practitioners to trust the predictions. Traditional machine learning models, e.g., logistic…

Visual prompt tuning offers significant advantages for adapting pre-trained visual foundation models to specific tasks. However, current research provides limited insight into the interpretability of this approach, which is essential for…

Image-Text matching (ITM) is a common task for evaluating the quality of Vision and Language (VL) models. However, existing ITM benchmarks have a significant limitation. They have many missing correspondences, originating from the data…

One of the more challenging real-world problems in computational intelligence is to learn from non-stationary streaming data, also known as concept drift. Perhaps even a more challenging version of this scenario is when -- following a small…

While most existing neural image compression (NIC) and neural video compression (NVC) methodologies have achieved remarkable success, their optimization is primarily focused on human visual perception. However, with the rapid development of…

Interpretability is highly desired for deep neural network-based classifiers, especially when addressing high-stake decisions in medical imaging. Commonly used post-hoc interpretability methods have the limitation that they can produce…

VAEs, or variational autoencoders, are autoencoders that explicitly learn the distribution of the input image space rather than assuming no prior information about the distribution. This allows it to classify similar samples close to each…

Variational autoencoders (VAEs) combine latent variables with amortized variational inference, whose optimization usually converges into a trivial local optimum termed posterior collapse, especially in text modeling. By tracking the…

In recent years, deep learning has shown potential and efficiency in a wide area including computer vision, image and signal processing. Yet, translational challenges remain for user applications due to a lack of interpretability of…

Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the…

Temporal Reasoning is one important functionality for vision intelligence. In computer vision research community, temporal reasoning is usually studied in the form of video classification, for which many state-of-the-art Neural Network…

In many modern image-classification applications, understanding the cause of model's prediction can be as critical as the prediction's accuracy itself. Various feature-based local explanations generation methods have been designed to give…

Uncovering emergent concepts across transformer layers remains a significant challenge because the residual stream linearly mixes and duplicates information, obscuring how features evolve within large language models. Current research…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruction quality under high compression ratios. However, this…

Transfer Learning enables Convolutional Neural Networks (CNN) to acquire knowledge from a source domain and transfer it to a target domain, where collecting large-scale annotated examples is time-consuming and expensive. Conventionally,…

Visual Emotion Comprehension (VEC) aims to infer sentiment polarities or emotion categories from affective cues embedded in images. In recent years, Multimodal Large Language Models (MLLMs) have established a popular paradigm in VEC,…

Self-adaptive systems frequently use tactics to perform adaptations. Tactic examples include the implementation of additional security measures when an intrusion is detected, or activating a cooling mechanism when temperature thresholds are…

In this paper we introduce a new problem within the growing literature of interpretability for convolution neural networks (CNNs). While previous work has focused on the question of how to visually interpret CNNs, we ask what it is that we…

The need for interpretable models has fostered the development of self-explainable classifiers. Prior approaches are either based on multi-stage optimization schemes, impacting the predictive performance of the model, or produce…