Related papers: Revealing Hidden Context Bias in Segmentation and …

The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to choose between computational tractability and…

We present a self-supervised learning (SSL) method suitable for semi-global tasks such as object detection and semantic segmentation. We enforce local consistency between self-learned features, representing corresponding image locations of…

This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i.e., without using…

Dense visual prediction tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have…

Transformer with its underlying attention mechanism and the ability to capture long-range dependencies makes it become a natural choice for unordered point cloud data. However, separated local regions from the general sampling architecture…

Concept Bottleneck Models (CBMs) try to make the decision-making process transparent by exploring an intermediate concept space between the input image and the output prediction. Existing CBMs just learn coarse-grained relations between the…

With a strong alignment between the training and test distributions, object relation as a context prior facilitates object detection. Yet, it turns into a harmful but inevitable training set bias upon test distributions that shift…

Learned image reconstruction techniques using deep neural networks have recently gained popularity, and have delivered promising empirical results. However, most approaches focus on one single recovery for each observation, and thus neglect…

Robotic systems often require precise scene analysis capabilities, especially in unstructured, cluttered situations, as occurring in human-made environments. While current deep-learning based methods yield good estimates of object poses,…

Referring image segmentation aims to segment a referent via a natural linguistic expression.Due to the distinct data properties between text and image, it is challenging for a network to well align text and pixel-level features. Existing…

Pre-trained Language Models (PLMs) are trained on large amounts of unlabeled data, yet they exhibit remarkable reasoning skills. However, the trustworthiness challenges posed by these black-box models have become increasingly evident in…

The prior self-supervised learning researches mainly select image-level instance discrimination as pretext task. It achieves a fantastic classification performance that is comparable to supervised learning methods. However, with degraded…

In many machine learning applications, from medical diagnostics to autonomous driving, the availability of prior knowledge can be used to improve the predictive performance of learning algorithms and incorporate `physical,' `domain…

Data augmentation remains a widely utilized technique in deep learning, particularly in tasks such as image classification, semantic segmentation, and object detection. Among them, Copy-Paste is a simple yet effective method and gain great…

Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. Such generality for transfer learning, however, sacrifices specificity if we are interested in a certain downstream…

An important step towards explaining deep image classifiers lies in the identification of image regions that contribute to individual class scores in the model's output. However, doing this accurately is a difficult task due to the…

Detecting partially occluded objects is a difficult task. Our experimental results show that deep learning approaches, such as Faster R-CNN, are not robust at object detection under occlusion. Compositional convolutional neural networks…

Performing data augmentation for learning deep neural networks is known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…

This paper describes a fast and accurate semantic image segmentation approach that encodes not only the discriminative features from deep neural networks, but also the high-order context compatibility among adjacent objects as well as low…

Layer-wise Relevance Propagation (LRP) and saliency maps have been recently used to explain the predictions of Deep Learning models, specifically in the domain of text classification. Given different attribution-based explanations to…