Cross-domain image retrieval aims at retrieving images across different domains to excavate cross-domain classificatory or correspondence relationships. This paper studies a less-touched problem of cross-domain image retrieval, i.e., unsupervised cross-domain image retrieval, considering the following practical assumptions: (i) no correspondence relationship, and (ii) no category annotations. It is challenging to align and bridge distinct domains without cross-domain correspondence. To tackle the challenge, we present a novel Correspondence-free Domain Alignment (CoDA) method to effectively eliminate the cross-domain gap through In-domain Self-matching Supervision (ISS) and Cross-domain Classifier Alignment (CCA). To be specific, ISS is presented to encapsulate discriminative information into the latent common space by elaborating a novel self-matching supervision mechanism. To alleviate the cross-domain discrepancy, CCA is proposed to align distinct domain-specific classifiers. Thanks to the ISS and CCA, our method could encode the discrimination into the domain-invariant embedding space for unsupervised cross-domain image retrieval. To verify the effectiveness of the proposed method, extensive experiments are conducted on four benchmark datasets compared with six state-of-the-art methods.

In the task of multi-label classification, it is a key challenge to determine the correlation between labels. One solution to this is the Target Embedding Autoencoder (TEA), but most TEA-based frameworks have numerous parameters, large models, and high complexity, which makes it difficult to deal with the problem of large-scale learning. To address this issue, we provide a Target Embedding Autoencoder framework based on Knowledge Distillation (KD-TEA) that compresses a Teacher model with large parameters into a small Student model through knowledge distillation. Specifically, KD-TEA transfers the dark knowledge learned from the Teacher model to the Student model. The dark knowledge can provide effective regularization to alleviate the over-fitting problem in the training process, thereby enhancing the generalization ability of the Student model, and better completing the multi-label task. In order to make the Student model learn the knowledge of the Teacher model directly, we improve the distillation loss: KD-TEA uses MSE loss instead of KL divergence loss to improve the performance of the model in multi-label tasks. Experiments on multiple datasets show that our KD-TEA framework is superior to the most advanced multi-label classification methods in both performance and efficiency.

Deep neural network has achieved promising results for automatic glaucoma detection on fundus images. Nevertheless, the intrinsic discrepancy across glaucoma datasets is challenging for the data-driven neural network approaches. This discrepancy leads to the domain gap that affects model performance and declines model generalization capability. Existing domain adaptation-based transfer learning methods mostly fine-tune pretrained models on target domains to reduce the domain gap. However, this feature learning-based adaptation method is implicit, and it is not an optimal solution for transfer learning on the diverse glaucoma datasets. In this paper, we propose a mixup domain adaptation (mixDA) method that bridges domain adaptation with domain mixup to improve model performance across divergent glaucoma datasets. Specifically, the domain adaptation reduces the domain gap of glaucoma datasets in transfer learning with an explicit adaptation manner. Meanwhile, the domain mixup further minimizes the risk of outliers after domain adaptation and improves the model generalization capability. Extensive experiments show the superiority of our mixDA on several public glaucoma datasets. Moreover, our method outperforms state-of-the-art methods by a large margin on four glaucoma datasets: REFUGE, LAG, ORIGA, and RIM-ONE.

Despite significant advances in continual semantic segmentation ( CSS ), they still rely on the pixel-level annotation to train models, which is time-consuming and labor-intensive. Continual learning from image-level labels is an emerging scheme in continual semantic segmentation to reduce the annotation cost. However, the incomplete and coarse pseudo-labels are insufficient to train a model to maintain a balance between stability and plasticity. To solve these issues, we propose a novel end-to-end framework based on Transformer, called L2A, for Weakly Supervised Continual Semantic Segmentation ( WSCSS ). In particular, to generate reliable annotations from the image-level supervision, we introduce a semantic affinity from multi-head self-attention (SA-MHSA) module to capture the semantic relationships among adjacent image coordinates. Subsequently, this acquired semantic affinity is employed to refine the initial pseudo labels of new classes trained with the image-level annotations. Furthermore, to minimize catastrophic forgetting, we propose a semantic drift compensation (SDC) strategy to optimize the pseudo-label generation process, which can effectively improve the alignment of object boundaries across both new and old categories. Comprehensive experiments conducted on the PASCAL VOC 2012 and COCO datasets demonstrate the superiority of our framework in existing WSCSS scenarios and a newly proposed challenge protocol, as well as remains competitive compared to the pixel-level supervised CSS methods.