Related papers: Posthoc Interpretation via Quantization
Vectorized quantum block encoding provides a way to embed classical data into Hilbert space, offering a pathway for quantum models, such as Quantum Transformers (QT), that replace classical self-attention with quantum circuit simulations to…
Humans use abstract concepts for understanding instead of hard features. Recent interpretability research has focused on human-centered concept explanations of neural networks. Concept Activation Vectors (CAVs) estimate a model's…
Part-prototype networks have recently become methods of interest as an interpretable alternative to many of the current black-box image classifiers. However, the interpretability of these methods from the perspective of human users has not…
With the popularity of deep neural networks (DNNs), model interpretability is becoming a critical concern. Many approaches have been developed to tackle the problem through post-hoc analysis, such as explaining how predictions are made or…
Transparency and explainability in image classification are essential for establishing trust in machine learning models and detecting biases and errors. State-of-the-art explainability methods generate saliency maps to show where a specific…
We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a…
Vector quantization (VQ) is a technique to deterministically learn features with discrete codebook representations. It is commonly performed with a variational autoencoding model, VQ-VAE, which can be further extended to hierarchical…
Part-prototype models are explainable-by-design image classifiers, and a promising alternative to black box AI. This paper explores the applicability and potential of interpretable machine learning, in particular PIP-Net, for automated…
Deep classifiers tend to associate a few discriminative input variables with their objective function, which in turn, may hurt their generalization capabilities. To address this, one can design systematic experiments and/or inspect the…
Continual learning requires to overcome catastrophic forgetting when training a single model on a sequence of tasks. Recent top-performing approaches are prompt-based methods that utilize a set of learnable parameters (i.e., prompts) to…
The growing use of large language models has raised environmental and economic concerns about their intensity of resource usage during inference. Serving these models to each user requires substantial energy and water for cooling. Model…
Image captioning models are becoming increasingly successful at describing the content of images in restricted domains. However, if these models are to function in the wild - for example, as assistants for people with impaired vision - a…
Photonic quantum processors naturally produce intrinsically stochastic measurement outcomes, offering a hardware-native source of structured randomness that can be exploited during machine-learning training. Here we introduce Photonic…
Vector Quantization (VQ) has become the cornerstone of tokenization for many multimodal Large Language Models and diffusion synthesis. However, existing VQ paradigms suffer from a fundamental conflict: they enforce discretization before the…
Deep neural networks have demonstrated remarkable performance across numerous learning tasks but often suffer from miscalibration, resulting in unreliable probability outputs. This has inspired many recent works on mitigating…
Quantization plays an important role in the energy-efficient deployment of deep neural networks on resource-limited devices. Post-training quantization is highly desirable since it does not require retraining or access to the full training…
We propose a novel framework for uncertainty quantification via information bottleneck (IB-UQ) for scientific machine learning tasks, including deep neural network (DNN) regression and neural operator learning (DeepONet). Specifically, we…
Classification techniques can be used to analyze system behaviors, network protocols, and cryptographic primitives based on identifiable traits. While useful for defense, such classification can also be leveraged by attackers to infer…
The most common methods in explainable artificial intelligence are post-hoc techniques which identify the most relevant features used by pretrained opaque models. Some of the most advanced post hoc methods can generate explanations that…
Abstract Modern image generation (IG) models have been shown to capture rich semantics valuable for image understanding (IU) tasks. However, the potential of IU models to improve IG performance remains uncharted. We address this issue using…