Related papers: Countering Inconsistent Labelling by Google's Visi…

There exists an apparent negative correlation between performance and interpretability of deep learning models. In an effort to reduce this negative correlation, we propose a Born Identity Network (BIN), which is a post-hoc approach for…

The importance of explainability in AI has become a pressing concern, for which several explainable AI (XAI) approaches have been recently proposed. However, most of the available XAI techniques are post-hoc methods, which however may be…

The robustness of machine learning models can be compromised by spurious correlations between non-causal features in the input data and target labels. A common way to test for such correlations is to train on data where the label is…

Scene text images have different shapes and are subjected to various distortions, e.g. perspective distortions. To handle these challenges, the state-of-the-art methods rely on a rectification network, which is connected to the text…

Open Source Software projects add labels to open issues to help contributors choose tasks. However, manually labeling issues is time-consuming and error-prone. Current automatic approaches for creating labels are mostly limited to…

Recent works find that AI algorithms learn biases from data. Therefore, it is urgent and vital to identify biases in AI algorithms. However, the previous bias identification pipeline overly relies on human experts to conjecture potential…

Today, most methods for image understanding tasks rely on feed-forward neural networks. While this approach has allowed for empirical accuracy, efficiency, and task adaptation via fine-tuning, it also comes with fundamental disadvantages.…

The performance of deep networks for semantic image segmentation largely depends on the availability of large-scale training images which are labelled at the pixel level. Typically, such pixel-level image labellings are obtained manually by…

Photorealistic image generation from simulated label maps are necessitated in several contexts, such as for medical training in virtual reality. With conventional deep learning methods, this task requires images that are paired with…

While deep learning has led to huge progress in complex image classification tasks like ImageNet, unexpected failure modes, e.g. via spurious features, call into question how reliably these classifiers work in the wild. Furthermore, for…

Adversarial attacks play an essential role in understanding deep neural network predictions and improving their robustness. Existing attack methods aim to deceive convolutional neural network (CNN)-based classifiers by manipulating RGB…

We present a method for compositing virtual objects into a photograph such that the object colors appear to have been processed by the photo's camera imaging pipeline. Compositing in such a camera-aware manner is essential for high realism,…

The inability of state-of-the-art semantic segmentation methods to detect anomaly instances hinders them from being deployed in safety-critical and complex applications, such as autonomous driving. Recent approaches have focused on either…

Inverse problems have many applications in science and engineering. In Computer vision, several image restoration tasks such as inpainting, deblurring, and super-resolution can be formally modeled as inverse problems. Recently, methods have…

Typical template-based object pose pipelines estimate the pose by retrieving the closest matching template and aligning it with the observed image. However, failure to retrieve the correct template often leads to inaccurate pose…

Robustness has become one of the most critical problems in machine learning (ML). The science of interpreting ML models to understand their behavior and improve their robustness is referred to as explainable artificial intelligence (XAI).…

Given the vast amounts of video available online, and recent breakthroughs in object detection with static images, object detection in video offers a promising new frontier. However, motion blur and compression artifacts cause substantial…

Under the flourishing development in performance, current image-text retrieval methods suffer from $N$-related time complexity, which hinders their application in practice. Targeting at efficiency improvement, this paper presents a simple…

We present an adversarial framework to craft perturbations that mislead classifiers by accounting for the image content and the semantics of the labels. The proposed framework combines a structure loss and a semantic adversarial loss in a…

Image captioning, which generates natural language descriptions of the visual information in an image, is a crucial task in vision-language research. Previous models have typically addressed this task by aligning the generative capabilities…