Related papers: ProxyNCA++: Revisiting and Revitalizing Proxy Neig…

We propose Deep Companion Learning (DCL), a novel training method for Deep Neural Networks (DNNs) that enhances generalization by penalizing inconsistent model predictions compared to its historical performance. To achieve this, we train a…

Denoising Probabilistic Models (DPMs) represent an emerging domain of generative models that excel in generating diverse and high-quality images. However, most current training methods for DPMs often neglect the correlation between…

Fine-tuning large language models (LLMs) to align with human preferences has driven the success of systems such as Gemini and ChatGPT. However, approaches like Reinforcement Learning from Human Feedback (RLHF) remain computationally…

In this work, we study distance metric learning (DML) for high dimensional data. A typical approach for DML with high dimensional data is to perform the dimensionality reduction first before learning the distance metric. The main…

We present a mechanism to steer the sampling diversity of denoising diffusion and flow matching models, allowing users to sample from a sharper or broader distribution than the training distribution. We build on the observation that these…

Moving object detection (MOD) in remote sensing is significantly challenged by low resolution, extremely small object sizes, and complex noise interference. Current deep learning-based MOD methods rely on probability density estimation,…

Approximate nearest neighbor search (ANNS) plays an indispensable role in a wide variety of applications, including recommendation systems, information retrieval, and semantic search. Among the cutting-edge ANNS algorithms, graph-based…

Seeing clearly with high resolution is a foundation of Large Multimodal Models (LMMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where…

Uniform sampling of training data has been commonly used in traditional stochastic optimization algorithms such as Proximal Stochastic Gradient Descent (prox-SGD) and Proximal Stochastic Dual Coordinate Ascent (prox-SDCA). Although uniform…

Nearest neighbor (NN) sampling provides more semantic variations than pre-defined transformations for self-supervised learning (SSL) based image recognition problems. However, its performance is restricted by the quality of the support set,…

While recent years have witnessed remarkable progress in the feature representation of visual tracking, the problem of feature misalignment between the classification and regression tasks is largely overlooked. The approaches of feature…

Data selection methods, such as active learning and core-set selection, are useful tools for machine learning on large datasets. However, they can be prohibitively expensive to apply in deep learning because they depend on feature…

Distance metric learning (DML) is a critical factor for image analysis and pattern recognition. To learn a robust distance metric for a target task, we need abundant side information (i.e., the similarity/dissimilarity pairwise constraints…

Due to its efficiency and stability, Robust Principal Component Analysis (RPCA) has been emerging as a promising tool for moving object detection. Unfortunately, existing RPCA based methods assume static or quasi-static background, and…

Anomaly detection in medical images refers to the identification of abnormal images with only normal images in the training set. Most existing methods solve this problem with a self-reconstruction framework, which tends to learn an identity…

Night-time pedestrian detection remains challenging because labelled night-time data are limited and large illumination differences make daytime-only trained detectors unreliable. Latent diffusion models (LDMs) provide a powerful basis for…

Reconstructions of past climates are based on the calibration of available proxy data. This calibration is usually achieved by means of linear regression models. In the recent paleo-climate literature there is an ongoing discussion on the…

In this study, we propose an enhanced image restoration model, SUPIR, based on the integration of two low-rank adaptive (LoRA) modules with the Stable Diffusion XL (SDXL) framework. Our method leverages the advantages of LoRA to fine-tune…

Text-video retrieval aims to find the most relevant cross-modal samples for a given query. Recent methods focus on modeling the whole spatial-temporal relations. However, since video clips contain more diverse content than captions, the…

There is a family of label modification approaches including self and non-self label correction (LC), and output regularisation. They are widely used for training robust deep neural networks (DNNs), but have not been mathematically and…