相关论文: Causal Attribution via Activation Patching

We investigate the robustness of vision transformers (ViTs) through the lens of their special patch-based architectural structure, i.e., they process an image as a sequence of image patches. We find that ViTs are surprisingly insensitive to…

Image captioning is a challenging computer vision task, which aims to generate a natural language description of an image. Most recent researches follow the encoder-decoder framework which depends heavily on the previous generated words for…

With the maturity of visual detection techniques, we are more ambitious in describing visual content with open-vocabulary, fine-grained and free-form language, i.e., the task of image captioning. In particular, we are interested in…

Understanding what sparse auto-encoder (SAE) features in vision transformers truly represent is usually done by inspecting the patches where a feature's activation is highest. However, self-attention mixes information across the entire…

Visual prompting techniques are widely used to efficiently fine-tune pretrained Vision Transformers (ViT) by learning a small set of shared prompts for all tokens. However, existing methods overlook the unique roles of different tokens in…

Importance estimators are explainability methods that quantify feature importance for deep neural networks (DNN). In vision transformers (ViT), the self-attention mechanism naturally leads to attention maps, which are sometimes interpreted…

Deep Learning has revolutionized machine learning, reaching unprecedented levels of accuracy, but at the cost of reduced interpretability. Especially in image processing systems, deep networks transform local pixel information into more…

Convolutional neural networks have been shown to develop internal representations, which correspond closely to semantically meaningful objects and parts, although trained solely on class labels. Class Activation Mapping (CAM) is a recent…

Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the premise that the causal variables themselves are observed. However, for AI agents such as robots trying to make…

Existing feature attribution methods like SHAP often suffer from global dependence, failing to capture true local model behavior. This paper introduces VARSHAP, a novel model-agnostic local feature attribution method which uses the…

Attribution modelling lies at the heart of marketing effectiveness, yet most existing approaches depend on user-level path data, which are increasingly inaccessible due to privacy regulations and platform restrictions. This paper introduces…

Prompt learning has recently attracted much attention for adapting pre-trained vision-language models (e.g., CLIP) to downstream recognition tasks. However, most of the existing CLIP-based prompt learning methods only show a limited ability…

Explaining deep learning models in a way that humans can easily understand is essential for responsible artificial intelligence applications. Attribution methods constitute an important area of explainable deep learning. The attribution…

Transformers have profoundly influenced AI research, but explaining their decisions remains challenging -- even for relatively simpler tasks such as classification -- which hinders trust and safe deployment in real-world applications.…

We present PAT, a transformer-based network that learns complex temporal co-occurrence action dependencies in a video by exploiting multi-scale temporal features. In existing methods, the self-attention mechanism in transformers loses the…

This paper introduces Attribution Projection Calculus (AP-Calculus), a novel mathematical framework for determining causal relationships in structured Bayesian networks. We investigate a specific network architecture with source nodes…

The expansion of explainable artificial intelligence as a field of research has generated numerous methods of visualizing and understanding the black box of a machine learning model. Attribution maps are generally used to highlight the…

In this work, we focus on a novel and practical task, i.e., Time-vAriant iMage inPainting (TAMP). The aim of TAMP is to restore a damaged target image by leveraging the complementary information from a reference image, where both images…

Vision transformers (ViTs) encoding an image as a sequence of patches bring new paradigms for semantic segmentation.We present an efficient framework of representation separation in local-patch level and global-region level for semantic…

Class-Incremental Learning (CIL) enables models to continuously integrate new knowledge while mitigating catastrophic forgetting. Driven by the remarkable generalization of CLIP, leveraging pre-trained vision-language models has become a…