Related papers: ConceptScope: Characterizing Dataset Bias via Dise…

In image classification, a significant problem arises from bias in the datasets. When it contains only specific types of images, the classifier begins to rely on shortcuts - simplistic and erroneous rules for decision-making. This leads to…

Object counting is a foundational vision task with over a decade of dedicated research, yet state-of-the-art models still fail systematically in the mixed-object setting that dominates real-world applications such as industrial inspection…

Depth perception is fundamental for robots to understand the surrounding environment. As the view of cognitive neuroscience, visual depth perception methods are divided into three categories, namely binocular, active, and pictorial. The…

Co-salient object detection (Co-SOD) aims to identify common salient objects across a group of related images. While recent methods have made notable progress, they typically rely on low-level visual patterns and lack semantic priors,…

Smart focal-plane and in-chip image processing has emerged as a crucial technology for vision-enabled embedded systems with energy efficiency and privacy. However, the lack of special datasets providing examples of the data that these…

Benchmark datasets in computer vision often contain off-topic images, near duplicates, and label errors, leading to inaccurate estimates of model performance. In this paper, we revisit the task of data cleaning and formalize it as either a…

This paper introduces a visual sentiment concept classification method based on deep convolutional neural networks (CNNs). The visual sentiment concepts are adjective noun pairs (ANPs) automatically discovered from the tags of web photos,…

Multiple benchmarks have been developed to assess the alignment between deep neural networks (DNNs) and human vision. In almost all cases these benchmarks are observational in the sense they are composed of behavioural and brain responses…

Labeled datasets reflect the biases of their annotation pipelines, which sometimes introduce label bias: group-conditional label errors that cause systematic performance disparities across demographic subgroups. Label bias in image…

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still…

We consider the problem of retrieving objects from image data and learning to classify them into meaningful semantic categories with minimal supervision. To that end, we propose a fully differentiable unsupervised deep clustering approach…

This paper proposes an automatic spatially-aware concept discovery approach using weakly labeled image-text data from shopping websites. We first fine-tune GoogleNet by jointly modeling clothing images and their corresponding descriptions…

Pre-trained models operating directly on raw bytes have achieved promising performance in encrypted network traffic classification (NTC), but often suffer from shortcut learning-relying on spurious correlations that fail to generalize to…

Recent advances in machine learning leverage massive datasets of unlabeled images from the web to learn general-purpose image representations for tasks from image classification to face recognition. But do unsupervised computer vision…

Interpreting the inner workings of deep learning models is crucial for establishing trust and ensuring model safety. Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution…

We introduce ConceptVision, a method that aims for high accuracy in categorizing large number of scenes, while keeping the model relatively simpler and efficient for scalability. The proposed method combines the advantages of both low-level…

Attribute-based recognition models, due to their impressive performance and their ability to generalize well on novel categories, have been widely adopted for many computer vision applications. However, usually both the attribute vocabulary…

Interpretable-by-design models are gaining traction in computer vision because they provide faithful explanations for their predictions. In image classification, these models typically recover human-interpretable concepts from an image and…

Interpreting the decisions of deep image classifiers remains challenging, particularly in black-box settings where model internals are inaccessible. We introduce OCCAM, a framework for open-set causal concept explanation and ontology…

Biased attributes, spuriously correlated with target labels in a dataset, can problematically lead to neural networks that learn improper shortcuts for classifications and limit their capabilities for out-of-distribution (OOD)…