Related papers: SPG: Sparse-Projected Guides with Sparse Autoencod…

Autonomous navigation in unknown environments is challenging and demands the consideration of both geometric and semantic information in order to parse the navigability of the environment. In this work, we propose a novel space modeling…

Anomaly detection is a fundamental yet challenging problem in machine learning due to the lack of label information. In this work, we propose a novel and powerful framework, dubbed as SLA$^2$P, for unsupervised anomaly detection. After…

Sparse autoencoders (SAEs) are increasingly used for safety-relevant applications including alignment detection and model steering. These use cases require SAE latents to be as atomic as possible. Each latent should represent a single…

Domain generalization for semantic segmentation aims to mitigate the degradation in model performance caused by domain shifts. However, in many real-world scenarios, we are unable to access the model parameters and architectural details due…

Deep neural networks are powerful tools for biomedical image segmentation. These models are often trained with heavy supervision, relying on pairs of images and corresponding voxel-level labels. However, obtaining segmentations of…

Sparsely spread code division multiple access (SCDMA) is a promising non-orthogonal multiple access technique for future wireless communications. In this paper, we propose a novel trainable multiuser detector called sparse trainable…

Scene graph generation (SGG) is to detect object pairs with their relations in an image. Existing SGG approaches often use multi-stage pipelines to decompose this task into object detection, relation graph construction, and dense or…

Vision foundation models (FMs) achieve state-of-the-art performance in medical imaging. However, they encode information in abstract latent representations that clinicians cannot interrogate or verify. The goal of this study is to…

The human brain exhibits a strong ability to spontaneously associate different visual attributes of the same or similar visual scene, such as associating sketches and graffiti with real-world visual objects, usually without supervising…

Machine learning, particularly deep learning, is transforming industrial quality inspection. Yet, training robust machine learning models typically requires large volumes of high-quality labeled data, which are expensive, time-consuming,…

Sparse Autoencoders (SAEs) are an interpretability technique aimed at decomposing neural network activations into interpretable units. However, a major bottleneck for SAE development has been the lack of high-quality performance metrics,…

Scene graph generation (SGG) is a fundamental task aimed at detecting visual relations between objects in an image. The prevailing SGG methods require all object classes to be given in the training set. Such a closed setting limits the…

Weakly supervised video anomaly detection (WSVAD) is a challenging task. Generating fine-grained pseudo-labels based on weak-label and then self-training a classifier is currently a promising solution. However, since the existing methods…

Reliable control of myoelectric prostheses is often hindered by high inter-subject variability and the clinical impracticality of high-density sensor arrays. This study proposes a deep learning framework for accurate gesture recognition…

Existing zero-shot learning (ZSL) models typically learn a projection function from a feature space to a semantic embedding space (e.g.~attribute space). However, such a projection function is only concerned with predicting the training…

Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos. Existing methods universally depend on large-scale annotations or task-specific training procedures,…

Zero-shot anomaly detection (ZSAD) enables anomaly detection without normal samples from target categories, addressing scenarios where task-specific training data is unavailable. However, existing ZSAD methods either neglect adaptation of…

Depth estimation is a critical technology in autonomous driving, and multi-camera systems are often used to achieve a 360$^\circ$ perception. These 360$^\circ$ camera sets often have limited or low-quality overlap regions, making multi-view…

Large-scale visual-language pre-trained models (VLPM) have proven their excellent performance in downstream object detection for natural scenes. However, zero-shot nuclei detection on H\&E images via VLPMs remains underexplored. The large…

Semantic segmentation is a crucial task in computer vision that involves segmenting images into semantically meaningful regions at the pixel level. However, existing approaches often rely on expensive human annotations as supervision for…