相关论文: VISLIX: An XAI Framework for Validating Vision Mod…

Data visualizations are powerful tools for communicating patterns in quantitative data. Yet understanding any data visualization is no small feat -- succeeding requires jointly making sense of visual, numerical, and linguistic inputs…

Explaining deep learning models is essential for clinical integration of medical image analysis systems. A good explanation highlights if a model depends on spurious features that undermines generalization and harms a subset of patients or,…

Visual reasoning is a core component of human intelligence and a critical capability for advanced multimodal models. Yet current reasoning evaluations of multimodal large language models (MLLMs) often rely on text descriptions and allow…

Task-oriented object detection aims to find objects suitable for accomplishing specific tasks. As a challenging task, it requires simultaneous visual data processing and reasoning under ambiguous semantics. Recent solutions are mainly…

Due to the increasing usage of machine learning (ML) techniques in security- and safety-critical domains, such as autonomous systems and medical diagnosis, ensuring correct behavior of ML systems, especially for different corner cases, is…

Interpretation and diagnosis of machine learning models have gained renewed interest in recent years with breakthroughs in new approaches. We present Manifold, a framework that utilizes visual analysis techniques to support interpretation,…

Novel view synthesis from images, for example, with 3D Gaussian splatting, has made great progress. Rendering fidelity and speed are now ready even for demanding virtual reality applications. However, the problem of assisting humans in…

Progress on object detection is enabled by datasets that focus the research community's attention on open challenges. This process led us from simple images to complex scenes and from bounding boxes to segmentation masks. In this work, we…

Efficient and accurate multi-organ segmentation from abdominal CT volumes is a fundamental challenge in medical image analysis. Existing 3D segmentation approaches are computationally and memory intensive, often processing entire volumes…

In recent years 3D object detection from LiDAR point clouds has made great progress thanks to the development of deep learning technologies. Although voxel or point based methods are popular in 3D object detection, they usually involve…

Effective cross-modal retrieval is essential for applications like information retrieval and recommendation systems, particularly in specialized domains such as manufacturing, where product information often consists of visual samples…

We introduce multi-slice reasoning, a new notion for single-view 3D reconstruction which challenges the current and prevailing belief that multi-view synthesis is the most natural conduit between single-view and 3D. Our key observation is…

Recent multi-modal contrastive learning models have demonstrated the ability to learn an embedding space suitable for building strong vision classifiers, by leveraging the rich information in large-scale image-caption datasets. Our work…

The increased interest in deep learning applications, and their hard-to-detect biases result in the need to validate and explain complex models. However, current explanation methods are limited as far as both the explanation of the…

Explaining Deep Learning models is becoming increasingly important in the face of daily emerging multimodal models, particularly in safety-critical domains like medical imaging. However, the lack of detailed investigations into the…

Large Language Models (LLMs) often exhibit systematic errors on specific subsets of data, known as error slices. For instance, a slice can correspond to a certain demographic, where a model does poorly in identifying toxic comments…

For a vision-language model (VLM) to understand the physical world, such as cause and effect, a first step is to capture the temporal dynamics of the visual world, for example how the physical states of objects evolve over time (e.g. a…

The recent breakthroughs in computer vision have benefited from the availability of large representative datasets (e.g. ImageNet and COCO) for training. Yet, robotic vision poses unique challenges for applying visual algorithms developed…

The proliferation of deepfake faces poses huge potential negative impacts on our daily lives. Despite substantial advancements in deepfake detection over these years, the generalizability of existing methods against forgeries from unseen…

Deep neural networks have consistently shown great performance in several real-world use cases like autonomous vehicles, satellite imaging, etc., effectively leveraging large corpora of labeled training data. However, learning unbiased…