实验室1篇论文被ECCV-24接收。ECCV会议是计算机视觉领域最重要的国际会议之一，每两年举办一届。ECCV-24将于2024年9月29日-10月4日在意大利/米兰举行。

题目：Learning to Distinguish Samples for Generalized Category Discovery

作者：Fengxiang Yang, Nan Pu, Wenjing Li, Zhiming Luo, Shaozi Li, Nicu Sebe, Zhun Zhong

摘要：Generalized Category Discovery (GCD) utilizes labelled data from seen categories to cluster unlabelled samples from both seen and unseen categories. Previous methods have demonstrated that assigning pseudo-labels for representation learning is effective. However, these methods commonly predict pseudo-labels based on pairwise similarities, while the overall relationship among each instance's k-nearest neighbors (kNNs) is largely overlooked, leading to inaccurate pseudo-labeling. To address this issue, we introduce a Neighbor Graph Convolutional Network (NGCN) that learns to predict pairwise similarities between instances using only labelled data. NGCN explicitly leverages the relationships among each instance's kNNs and is generalizable to samples of both seen and unseen classes. This helps produce more accurate positive samples by injecting the predicted similarities into subsequent clustering. Furthermore, we design a Cross-View Consistency Strategy (CVCS) to exclude samples with noisy pseudo-labels generated by clustering. This is achieved by comparing clusters from two different clustering algorithms. The filtered unlabelled data with pseudo-labels and the labelled data are then used to optimize the model through cluster- and instance-level contrastive objectives. The collaboration between NGCN and CVCS ensures the learning of a robust model, resulting in significant improvements in both seen and unseen class accuracies. Extensive experiments demonstrate that our method achieves state-of-the-art performance on both generic and fine-grained GCD benchmarks.