Focusing on pedestrians like human for clothes changing person re-identification.

Current approaches focus mainly on the design of networks to learn key identity features from local body components for clothes-changing person re-identification (CC-ReID). In this paper, we propose a humanoid focus-inspired image augmentation (HFIA) method, which is intuitive image processing rather than a sophisticated network architecture designed to enhance local nuances of pedestrian images. Based on pedestrian silhouettes, we roughly divide a pedestrian image into five body components, that is, head-shoulder, upper left torso, upper right torso, lower left torso, and lower right torso.

Aligning Text-to-Image Diffusion Models with Constrained Reinforcement Learning.

Reward finetuning has emerged as a powerful technique for aligning diffusion models with specific downstream objectives or user preferences. However, current approaches suffer from a persistent challenge of reward overoptimization, where models exploit imperfect reward feedback at the expense of overall performance. In this work, we identify three key contributors to overoptimization: (1) a granularity mismatch between the multi-step diffusion process and sparse rewards; (2) a loss of plasticity that limits the model's ability to adapt and generalize; and (3) an overly narrow focus on a single reward objective that neglects complementary performance criteria.

On neural architecture search and hyperparameter optimization: A max-flow based approach.

Automated Machine Learning (AutoML) involves the automatic production of models for specific tasks on given datasets, which can be divided into two aspects: Neural Architecture Search (NAS) for model construction and Hyperparameter Optimization (HPO) for model training. One of the most important components in an AutoML strategy is the search algorithm, which aims to recommend effective configurations according to historical observations. In this work, we propose a novel max-flow based search algorithm for AutoML by representing NAS and HPO as a Max-Flow problem on a graph and thus derive a couple of novel AutoML strategies, dubbed MF-NAS and MF-HPO, which handle the search space and the search strategy graphically.

Learning to Explore Sample Relationships.

Despite the great success achieved, deep learning technologies usually suffer from data scarcity issues in real-world applications, where existing methods mainly explore sample relationships in a vanilla way from the perspectives of either the input or the loss function. In this paper, we propose a batch transformer module, BatchFormerV1, to equip deep neural networks themselves with the abilities to explore sample relationships in a learnable way. Basically, the proposed method enables data collaboration, e.

Graph explicit pooling for graph-level representation learning.

Graph pooling has been increasingly recognized as crucial for Graph Neural Networks (GNNs) to facilitate hierarchical graph representation learning. Existing graph pooling methods commonly consist of two stages: selecting top-ranked nodes and discarding the remaining to construct coarsened graph representations. However, this paper highlights two key issues with these methods: (1) The process of selecting nodes to discard frequently employs additional Graph Convolutional Networks or Multilayer Perceptrons, lacking a thorough evaluation of each node's impact on the final graph representation and subsequent prediction tasks.

Finding core labels for maximizing generalization of graph neural networks.

Graph neural networks (GNNs) have become a popular approach for semi-supervised graph representation learning. GNNs research has generally focused on improving methodological details, whereas less attention has been paid to exploring the importance of labeling the data. However, for semi-supervised learning, the quality of training data is vital.

Exploring sparsity in graph transformers.

Graph Transformers (GTs) have achieved impressive results on various graph-related tasks. However, the huge computational cost of GTs hinders their deployment and application, especially in resource-constrained environments. Therefore, in this paper, we explore the feasibility of sparsifying GTs, a significant yet under-explored topic.

IoUformer: Pseudo-IoU prediction with transformer for visual tracking.

Siamese tracking has witnessed tremendous progress in tracking paradigm. However, its default box estimation pipeline still faces a crucial inconsistency issue, namely, the bounding box decided by its classification score is not always best overlapped with the ground truth, thus harming performance. To this end, we explore a novel simple tracking paradigm based on the intersection over union (IoU) value prediction.

Graph structure reforming framework enhanced by commute time distance for graph classification.

As a graph data mining task, graph classification has high academic value and wide practical application. Among them, the graph neural network-based method is one of the mainstream methods. Most graph neural networks (GNNs) follow the message passing paradigm and can be called Message Passing Neural Networks (MPNNs), achieving good results in structural data-related tasks.

On exploring node-feature and graph-structure diversities for node drop graph pooling.

Graph Neural Networks (GNNs) have been successfully applied to graph-level tasks in various fields such as biology, social networks, computer vision, and natural language processing. For the graph-level representations learning of GNNs, graph pooling plays an essential role. Among many pooling techniques, node drop pooling has garnered significant attention and is considered as a leading approach.

Boosting Graph Contrastive Learning via Adaptive Sampling.

Contrastive learning (CL) is a prominent technique for self-supervised representation learning, which aims to contrast semantically similar (i.e., positive) and dissimilar (i.

Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks.

Graph neural networks (GNNs) tend to suffer from high computation costs due to the exponentially increasing scale of graph data and a large number of model parameters, which restricts their utility in practical applications. To this end, some recent works focus on sparsifying GNNs (including graph structures and model parameters) with the lottery ticket hypothesis (LTH) to reduce inference costs while maintaining performance levels. However, the LTH-based methods suffer from two major drawbacks: 1) they require exhaustive and iterative training of dense models, resulting in an extremely large training computation cost, and 2) they only trim graph structures and model parameters but ignore the node feature dimension, where vast redundancy exists.

Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration.

Point cloud registration is a fundamental problem in 3D computer vision. Previous learning-based methods for LiDAR point cloud registration can be categorized into two schemes: dense-to-dense matching methods and sparse-to-sparse matching methods. However, for large-scale outdoor LiDAR point clouds, solving dense point correspondences is time-consuming, whereas sparse keypoint matching easily suffers from keypoint detection error.

BiN-Flow: Bidirectional Normalizing Flow for Robust Image Dehazing.

Image dehazing aims to remove haze in images to improve their image quality. However, most image dehazing methods heavily depend on strict prior knowledge and paired training strategy, which would hinder generalization and performance when dealing with unseen scenes. In this paper, to address the above problem, we propose Bidirectional Normalizing Flow (BiN-Flow), which exploits no prior knowledge and constructs a neural network through weakly-paired training with better generalization for image dehazing.

Not All Instances Contribute Equally: Instance-Adaptive Class Representation Learning for Few-Shot Visual Recognition.

Few-shot visual recognition refers to recognize novel visual concepts from a few labeled instances. Many few-shot visual recognition methods adopt the metric-based meta-learning paradigm by comparing the query representation with class representations to predict the category of query instance. However, the current metric-based methods generally treat all instances equally and consequently often obtain biased class representation, considering not all instances are equally significant when summarizing the instance-level representations for the class-level representation.