Related papers: MOTS R-CNN: Cosine-margin-triplet loss for multi-o…

Person re-identification (ReID) is an important task in computer vision. Recently, deep learning with a metric learning loss has become a common framework for ReID. In this paper, we also propose a new metric learning loss with hard sample…

Metric learning seeks perceptual embeddings where visually similar instances are close and dissimilar instances are apart, but learned representations can be sub-optimal when the distribution of intra-class samples is diverse and distinct…

Recently, contrastive learning attracts increasing interests in neural text generation as a new solution to alleviate the exposure bias problem. It introduces a sequence-level training signal which is crucial to generation tasks that always…

Person re-identification (ReID) aims to match people across multiple non-overlapping video cameras deployed at different locations. To address this challenging problem, many metric learning approaches have been proposed, among which triplet…

Multi-target tracking (MTT) is a classical signal processing task, where the goal is to estimate the states of an unknown number of moving targets from noisy sensor measurements. In this paper, we revisit MTT from a deep learning…

Benefiting from its ability to efficiently learn how an object is changing, correlation filters have recently demonstrated excellent performance for rapidly tracking objects. Designing effective features and handling model drifts are two…

In this paper, we address the problem of 3D object instance recognition and pose estimation of localized objects in cluttered environments using convolutional neural networks. Inspired by the descriptor learning approach of Wohlhart et al.,…

Similarity metric is crucial for massive MIMO positioning utilizing channel state information~(CSI). In this letter, we propose a novel massive MIMO CSI similarity learning method via deep convolutional neural network~(DCNN) and contrastive…

Oriented object detection for multi-spectral imagery faces significant challenges due to differences both within and between modalities. Although existing methods have improved detection accuracy through complex network architectures, their…

Deep metric learning objectives (e.g., triplet loss) require storing and comparing high-dimensional embeddings, making the per-batch loss buffer scale as $O(S\cdot D)$, where $S$ is the number of samples in a batch and $D$ is the feature…

Training a modern deep neural network on massive labeled samples is the main paradigm in solving the scene classification problem for remote sensing, but learning from only a few data points remains a challenge. Existing methods for…

Face recognition has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs), the central task of which is how to improve the feature discrimination. To this end, several margin-based (\textit{e.g.},…

Metric learning aims to learn a distance metric such that semantically similar instances are pulled together while dissimilar instances are pushed away. Many existing methods consider maximizing or at least constraining a distance margin in…

Deep representation learning using triplet network for classification suffers from a lack of theoretical foundation and difficulty in tuning both the network and classifiers for performance. To address the problem, local-margin triplet loss…

The Information Contrastive (I-Con) framework revealed that over 23 representation learning methods implicitly minimize KL divergence between data and learned distributions that encode similarities between data points. However, a KL-based…

Deep-learning architectures for classification problems involve the cross-entropy loss sometimes assisted with auxiliary loss functions like center loss, contrastive loss and triplet loss. These auxiliary loss functions facilitate better…

Person recognition aims at recognizing the same identity across time and space with complicated scenes and similar appearance. In this paper, we propose a novel method to address this task by training a network to obtain robust and…

Region-based Convolutional Neural Networks (R-CNNs) have achieved great success in the field of object detection. The existing R-CNNs usually divide a Region-of-Interest (ROI) into grids, and then localize objects by utilizing the spatial…

This paper extends the popular task of multi-object tracking to multi-object tracking and segmentation (MOTS). Towards this goal, we create dense pixel-level annotations for two existing tracking datasets using a semi-automatic annotation…

This paper pays close attention to the cross-modality visible-infrared person re-identification (VI Re-ID) task, which aims to match pedestrian samples between visible and infrared modes. In order to reduce the modality-discrepancy between…