Related papers: NMS-Loss: Learning with Non-Maximum Suppression fo…

We propose two novel loss functions, Multiplicative Loss and Confidence-Adaptive Multiplicative Loss, for semantic segmentation in medical and cellular images. Although Cross Entropy and Dice Loss are widely used, their additive combination…

Accurate human motion prediction is crucial for safe human-robot collaboration but remains challenging due to the complexity of modeling intricate and variable human movements. This paper presents Parallel Multi-scale Incremental Prediction…

Dense crowd counting is a challenging task that demands millions of head annotations for training models. Though existing self-supervised approaches could learn good representations, they require some labeled data to map these features to…

Estimating crowd count in densely crowded scenes is an extremely challenging task due to non-uniform scale variations. In this paper, we propose a novel end-to-end cascaded network of CNNs to jointly learn crowd count classification and…

Deep learning-based object detection and instance segmentation have achieved unprecedented progress. In this paper, we propose Complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding box regression and…

Sparse Mobile CrowdSensing (MCS) is a novel MCS paradigm where data inference is incorporated into the MCS process for reducing sensing costs while its quality is guaranteed. Since the sensed data from different cells (sub-areas) of the…

Real-time vision-based system of fault detection (RVBS-FD) for freight trains is an essential part of ensuring railway transportation safety. Most existing vision-based methods still have high computational costs based on convolutional…

A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad of solutions for deep metric learning. In this paper, we provide a general weighting framework for understanding recent…

We present multi-point optimization: an optimization technique that allows to train several models simultaneously without the need to keep the parameters of each one individually. The proposed method is used for a thorough empirical…

The recent rapid advances in machine learning technologies largely depend on the vast richness of data available today, in terms of both the quantity and the rich content contained within. For example, biometric data such as images and…

In the object detection task, CNN (Convolutional neural networks) models always need a large amount of annotated examples in the training process. To reduce the dependency of expensive annotations, few-shot object detection has become an…

The popular softmax loss and its recent extensions have achieved great success in the deep learning-based image classification. However, the data for training image classifiers usually has different quality. Ignoring such problem, the…

Translating machine learning algorithms into clinical applications requires addressing challenges related to interpretability, such as accounting for the effect of confounding variables (or metadata). Confounding variables affect the…

We consider a variant of matrix completion where entries are revealed in a biased manner. We wish to understand the extent to which such bias can be exploited in improving predictions. Towards that, we propose a natural model where the…

The crowd counting task aims at estimating the number of people located in an image or a frame from videos. Existing methods widely adopt density maps as the training targets to optimize the point-to-point loss. While in testing phase, we…

In this paper we propose a novel metric learning framework called Nullspace Kernel Maximum Margin Metric Learning (NK3ML) which efficiently addresses the small sample size (SSS) problem inherent in person re-identification and offers a…

Mixtures of linear dynamical systems (MoLDS) provide a path to model time-series data that exhibit diverse temporal dynamics across trajectories. However, its application remains challenging in complex and noisy settings, limiting its…

The Mean-Teacher (MT) scheme is widely adopted in semi-supervised object detection (SSOD). In MT, the sparse pseudo labels, offered by the final predictions of the teacher (e.g., after Non Maximum Suppression (NMS) post-processing), are…

Existing language models (LMs) predict tokens with a softmax over a finite vocabulary, which can make it difficult to predict rare tokens or phrases. We introduce NPM, the first nonparametric masked language model that replaces this softmax…

We investigate the optimization target of Contrast-Consistent Search (CCS), which aims to recover the internal representations of truth of a large language model. We present a new loss function that we call the Midpoint-Displacement (MD)…