Related papers: Improving Self-supervised Learning with Automated …

Unsupervised Domain Adaptation (UDA) addresses the problem of performance degradation due to domain shift between training and testing sets, which is common in computer vision applications. Most existing UDA approaches are based on…

Outlier exposure (OE) is powerful in out-of-distribution (OOD) detection, enhancing detection capability via model fine-tuning with surrogate OOD data. However, surrogate data typically deviate from test OOD data. Thus, the performance of…

Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image regions and support object-level explanations. While these methods perform well in…

Current adversarial adaptation methods attempt to align the cross-domain features, whereas two challenges remain unsolved: 1) the conditional distribution mismatch and 2) the bias of the decision boundary towards the source domain. To solve…

Discriminative learning effectively predicts true object class for image classification. However, it often results in false positives for outliers, posing critical concerns in applications like autonomous driving and video surveillance…

A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning…

As a subset of unsupervised representation learning, self-supervised representation learning adopts self-defined signals as supervision and uses the learned representation for downstream tasks, such as object detection and image captioning.…

Class imbalanced datasets are common in real-world applications that range from credit card fraud detection to rare disease diagnostics. Several popular classification algorithms assume that classes are approximately balanced, and hence…

We introduce Generalized Test-Time Augmentation (GTTA), a highly effective method for improving the performance of a trained model, which unlike other existing Test-Time Augmentation approaches from the literature is general enough to be…

Semi-supervised learning (semi-SL) is a promising alternative to supervised learning for medical image analysis when obtaining good quality supervision for medical imaging is difficult. However, semi-SL assumes that the underlying…

Nowadays, in many different fields, massive data are available and for several reasons, it might be convenient to analyze just a subset of the data. The application of the D-optimality criterion can be helpful to optimally select a…

Modern neural networks are known to give overconfident prediction for out-of-distribution inputs when deployed in the open world. It is common practice to leverage a surrogate outlier dataset to regularize the model during training, and…

Deep models often fail to generalize well in test domains when the data distribution differs from that in the training domain. Among numerous approaches to address this Out-of-Distribution (OOD) generalization problem, there has been a…

The problem of estimating subjective visual properties from image and video has attracted increasing interest. A subjective visual property is useful either on its own (e.g. image and video interestingness) or as an intermediate…

Contrastive learning is commonly applied to self-supervised learning, and has been shown to outperform traditional approaches such as the triplet loss and N-pair loss. However, the requirement of large batch sizes and memory banks has made…

Self-supervised learning on large-scale Vision Transformers (ViTs) as pre-training methods has achieved promising downstream performance. Yet, how much these pre-training paradigms promote lightweight ViTs' performance is considerably less…

Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given. Current UDA approaches learn domain-invariant features by aligning source and…

Class imbalance naturally exists when train and test models in different domains. Unsupervised domain adaptation (UDA) augments model performance with only accessible annotations from the source domain and unlabeled data from the target…

LiDAR-based semantic scene understanding is an important module in the modern autonomous driving perception stack. However, identifying outlier points in a LiDAR point cloud is challenging as LiDAR point clouds lack semantically-rich…

Universal Domain Adaptation (UniDA) aims to transfer knowledge from a source domain to a target domain without any constraints on label sets. Since both domains may hold private classes, identifying target common samples for domain…