相关论文: Overcoming Statistical Shortcuts for Open-ended Vi…

Convolutional Neural Networks (CNNs) have recently emerged as the dominant model in computer vision. If provided with enough training data, they predict almost any visual quantity. In a discrete setting, such as classification, CNNs are not…

Recent advancements in discrete image generation showed that scaling the VQ codebook size significantly improves reconstruction fidelity. However, training generative models with a large VQ codebook remains challenging, typically requiring…

Algorithmic image-based diagnosis and prognosis of neurodegenerative diseases on longitudinal data has drawn great interest from computer vision researchers. The current state-of-the-art models for many image classification tasks are based…

Vision-Language Models (VLMs) excel at multimodal reasoning, yet it remains unclear whether their answers are grounded in visual evidence or driven by learned language and world priors. Counting provides a precise testbed: when visual…

Clustering algorithms have significantly improved along with Deep Neural Networks which provide effective representation of data. Existing methods are built upon deep autoencoder and self-training process that leverages the distribution of…

Training convolutional networks for semantic segmentation with strong (per-pixel) and weak (per-bounding-box) supervision requires a large amount of weakly labeled data. We propose two methods for selecting the most relevant data with weak…

Convolutional Neural Networks (CNNs) have shown to be powerful medical image segmentation models. In this study, we address some of the main unresolved issues regarding these models. Specifically, training of these models on small medical…

Out-of-Distribution (OOD) generalization has become a primary metric for evaluating image analysis systems. Since deep learning models tend to capture domain-specific context, they often develop shortcut dependencies on these non-causal…

The existing continual learning methods are mainly focused on fully-supervised scenarios and are still not able to take advantage of unlabeled data available in the environment. Some recent works tried to investigate semi-supervised…

Due to the costliness of labelled data in real-world applications, semi-supervised object detectors, underpinned by pseudo labelling, are appealing. However, handling confusing samples is nontrivial: discarding valuable confusing samples…

Leveraging the characteristics of convolutional layers, neural networks are extremely effective for pattern recognition tasks. However in some cases, their decisions are based on unintended information leading to high performance on…

General change detection (GCD) and semantic change detection (SCD) are common methods for identifying changes and distinguishing object categories involved in those changes, respectively. However, the binary changes provided by GCD is often…

This paper reports a new solution of leveraging temporal classification to support weakly supervised object detection (WSOD). Specifically, we introduce raster scan-order techniques to serialize 2D images into 1D sequence data, and then…

Evaluating the predictive performance of species distribution models (SDMs) under realistic deployment scenarios requires careful handling of spatial and temporal dependencies in the data. Cross-validation (CV) is the standard approach for…

Visual Question Answering (VQA) models are prone to learn the shortcut solution formed by dataset biases rather than the intended solution. To evaluate the VQA models' reasoning ability beyond shortcut learning, the VQA-CP v2 dataset…

We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. Here, regularized autoencoders provide a popular approach by learning the identity mapping on the…

Accurately controlling object count in text-to-image generation remains a key challenge. Supervised methods often fail, as training data rarely covers all count variations. Methods that manipulate the denoising process to add or remove…

Counting the number of items in a visual scene remains a fundamental yet challenging task in computer vision. Traditional approaches to solving this problem rely on domain-specific counting architectures, which are trained using datasets…

Multi-view crowd counting can effectively mitigate occlusion issues that commonly arise in single-image crowd counting. Existing deep-learning multi-view crowd counting methods project different camera view images onto a common space to…

Various convolutional neural networks (CNNs) were developed recently that achieved accuracy comparable with that of human beings in computer vision tasks such as image recognition, object detection and tracking, etc. Most of these networks,…