Related papers: PURE: Turning Polysemantic Neurons Into Pure Featu…
Model interpretability is a requirement in many applications in which crucial decisions are made by users relying on a model's outputs. The recent movement for "algorithmic fairness" also stipulates explainability, and therefore…
Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features…
The objective of this work is to segment high-resolution images without overloading GPU memory usage or losing the fine details in the output segmentation map. The memory constraint means that we must either downsample the big image or…
Depth is a vital piece of information for autonomous vehicles to perceive obstacles. Due to the relatively low price and small size of monocular cameras, depth estimation from a single RGB image has attracted great interest in the research…
This paper investigates a fundamental problem of scene understanding: how to parse a scene image into a structured configuration (i.e., a semantic object hierarchy with object interaction relations). We propose a deep architecture…
In machine learning approach to image denoising a network is trained to recover a clean image from a noisy one. In this paper a novel structure is proposed based on training multiple specialized networks as opposed to existing structures…
The proliferation of deep neural networks in various domains has seen an increased need for interpretability of these models. Preliminary work done along this line and papers that surveyed such, are focused on high-level representation…
Sparse neural networks are often hypothesized to be more interpretable than dense models, motivated by findings that weight sparsity can produce compact circuits in language models. However, it remains unclear whether structural sparsity…
Although interpretable prototype networks have improved the transparency of deep learning image classification, the need for multiple prototypes in collaborative decision-making increases cognitive complexity and hinders user understanding.…
Despite deep learning (DL) has achieved remarkable progress in various domains, the DL models are still prone to making mistakes. This issue necessitates effective debugging tools for DL practitioners to interpret the decision-making…
Pervasive polysemanticity in large language models (LLMs) undermines discrete neuron-concept attribution, posing a significant challenge for model interpretation and control. We systematically analyze both encoder and decoder based LLMs…
When we experience a visual stimulus as beautiful, how much of that experience derives from perceptual computations we cannot describe versus conceptual knowledge we can readily translate into natural language? Disentangling perception from…
Convolutional neural networks (CNN) play a major role in image processing tasks like image classification, object detection, semantic segmentation. Very often CNN networks have from several to hundred stacked layers with several megabytes…
Image segmentation is a historic and significant computer vision task. With the help of deep learning techniques, image semantic segmentation has made great progresses. Over recent years, based on guidance of attention mechanism compared…
In this paper, we present NeuralReshaper, a novel method for semantic reshaping of human bodies in single images using deep generative networks. To achieve globally coherent reshaping effects, our approach follows a fit-then-reshape…
With the impressive capability to capture visual content, deep convolutional neural networks (CNN) have demon- strated promising performance in various vision-based ap- plications, such as classification, recognition, and objec- t…
Circuit discovery aims to identify minimal subnetworks that are responsible for specific behaviors in large language models (LLMs). Existing approaches primarily rely on iterative edge pruning, which is computationally expensive and limited…
This paper addresses semantic image segmentation by incorporating rich information into Markov Random Field (MRF), including high-order relations and mixture of label contexts. Unlike previous works that optimized MRFs using iterative…
Recently, deep feedforward neural networks have achieved considerable success in modeling biological sensory processing, in terms of reproducing the input-output map of sensory neurons. However, such models raise profound questions about…
We present a deformable prototypical part network (Deformable ProtoPNet), an interpretable image classifier that integrates the power of deep learning and the interpretability of case-based reasoning. This model classifies input images by…