Related papers: Causal-Tune: Mining Causal Factors from Vision Fou…

Knowing the features of a complex system that are highly relevant to a particular target variable is of fundamental interest in many areas of science. Existing approaches are often limited to linear settings, sometimes lack guarantees, and…

Vision Language Models (VLMs) are becoming increasingly integral to multimedia understanding; however, they often struggle with domain-specific video classification tasks, particularly in cases with limited data. This stems from a critical…

Generative models for graphs have been actively studied for decades, and they have a wide range of applications. Recently, learning-based graph generation that reproduces real-world graphs has been attracting the attention of many…

Linear structural causal models (SCMs) -- in which each observed variable is generated by a subset of the other observed variables as well as a subset of the exogenous sources -- are pervasive in causal inference and casual discovery.…

Causal discovery in time-series is a fundamental problem in the machine learning community, enabling causal reasoning and decision-making in complex scenarios. Recently, researchers successfully discover causality by combining neural…

We present Causal Generative Neural Networks (CGNNs) to learn functional causal models from observational data. CGNNs leverage conditional independencies and distributional asymmetries to discover bivariate and multivariate causal…

Open-Vocabulary semantic segmentation (OVSS) and domain generalization in semantic segmentation (DGSS) highlight a subtle complementarity that motivates Open-Vocabulary Domain-Generalized Semantic Segmentation (OV-DGSS). OV-DGSS aims to…

Recent advances in text-to-video diffusion models have enabled high-quality video synthesis, but controllable generation remains challenging, particularly under limited data and compute. Existing fine-tuning methods for conditional…

Deep learning models for semantic segmentation often experience performance degradation when deployed to unseen target domains unidentified during the training phase. This is mainly due to variations in image texture (\ie style) from…

We present Diff3F as a simple, robust, and class-agnostic feature descriptor that can be computed for untextured input shapes (meshes or point clouds). Our method distills diffusion features from image foundational models onto input shapes.…

Despite the success of deep learning in dermoscopy image analysis, its inherent black-box nature hinders clinical trust, motivating the use of prototypical networks for case-based visual transparency. However, inevitable selection bias in…

To gain deeper insights into a complex sensor system through the lens of causality, we present common and individual causal mechanism estimation (CICME), a novel three-step approach to inferring causal mechanisms from heterogeneous data…

Model quantization, which aims to compress deep neural networks and accelerate inference speed, has greatly facilitated the development of cumbersome models on mobile and edge devices. There is a common assumption in quantization methods…

Vision and Language (VL) models offer an effective method for aligning representation spaces of images and text, leading to numerous applications such as cross-modal retrieval, visual question answering, captioning, and more. However, the…

As a recent noticeable topic, domain generalization (DG) aims to first learn a generic model on multiple source domains and then directly generalize to an arbitrary unseen target domain without any additional adaption. In previous DG…

Source-Free Cross-Domain Few-Shot Learning (SF-CDFSL) focuses on fine-tuning with limited training data from target domains (e.g., medical or satellite images), where Vision-Language Models (VLMs) such as CLIP and SigLIP have shown…

Pre-trained vision-language models (VLMs) have shown impressive performance on various downstream tasks by utilizing knowledge learned from large data. In general, the performance of VLMs on target tasks can be further improved by prompt…

Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real…

Fine-tuning pre-trained neural network models has become a widely adopted approach across various domains. However, it can lead to the distortion of pre-trained feature extractors that already possess strong generalization capabilities.…

Existing Unsupervised Domain Adaptation (UDA) literature adopts the covariate shift and conditional shift assumptions, which essentially encourage models to learn common features across domains. However, due to the lack of supervision in…