Related papers: QASA: Quality-Guided K-Adaptive Slot Attention for…

Zero-Shot Learning (ZSL) aims to recognise unseen object classes, which are not observed during the training phase. The existing body of works on ZSL mostly relies on pretrained visual features and lacks the explicit attribute localisation…

Diffusion Transformers (DiTs) set the state of the art in visual generation, yet their quadratic self-attention cost fundamentally limits scaling to long token sequences. Recent Top-K sparse attention approaches reduce the computation of…

Unsupervised extraction of objects from low-level visual data is an important goal for further progress in machine learning. Existing approaches for representing objects without labels use structured generative models with static images.…

Slot attention is a powerful method for object-centric modeling in images and videos. However, its set-equivariance limits its ability to handle videos with a dynamic number of objects because it cannot break ties. To overcome this…

Attention mechanisms are ubiquitous components in neural architectures applied to natural language processing. In addition to yielding gains in predictive accuracy, attention weights are often claimed to confer interpretability, purportedly…

We present a method to stop the evaluation of a decision making process when the result of the full evaluation is obvious. This trait is highly desirable for online margin-based machine learning algorithms where a classifier traditionally…

Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention. While sparse attention provides a promising acceleration solution, existing methods…

Recent methods for long-tailed instance segmentation still struggle on rare object classes with few training data. We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addresses the data…

It is a common paradigm in object detection frameworks to treat all samples equally and target at maximizing the performance on average. In this work, we revisit this paradigm through a careful study on how different samples contribute to…

Self-attention in Transformers relies on globally normalized softmax weights, causing all tokens to compete for influence at every layer. When composed across depth, this interaction pattern induces strong synchronization dynamics that…

The diversity of retinal imaging devices poses a significant challenge: domain shift, which leads to performance degradation when applying the deep learning models trained on one domain to new testing domains. In this paper, we propose a…

Arbitrary-oriented object detection is a relatively emerging but challenging task. Although remarkable progress has been made, there still remain many unsolved issues due to the large diversity of patterns in orientation, scale, aspect…

Few-Shot Learning (FSL) has attracted growing attention in computer vision due to its capability in model training without the need for excessive data. FSL is challenging because the training and testing categories (the base vs. novel sets)…

Attention mechanisms, which enable a neural network to accurately focus on all the relevant elements of the input, have become an essential component to improve the performance of deep neural networks. There are mainly two attention…

Object detection is essential in space applications targeting Space Domain Awareness and also applications involving relative navigation scenarios. Current deep learning models for Object Detection in space applications are often trained on…

Zero-shot object counting (ZSOC) aims to enumerate objects of arbitrary categories specified by text descriptions without requiring visual exemplars. However, existing methods often treat counting as a coarse retrieval task, suffering from…

This paper proposes a method for visually explaining the decision-making process of video recognition networks with a temporal extension of occlusion sensitivity analysis, called Adaptive Occlusion Sensitivity Analysis (AOSA). The key idea…

Recent domain adaptation methods have demonstrated impressive improvement on unsupervised domain adaptation problems. However, in the semi-supervised domain adaptation (SSDA) setting where the target domain has a few labeled instances…

Fine-tuning large language models is essential for task-specific adaptation, yet it remains computationally prohibitive. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a solution, but current approaches typically ignore the…

Incremental object detection is fundamentally challenged by catastrophic forgetting. A major factor contributing to this issue is background shift, where background categories in sequential tasks may overlap with either previously learned…