Related papers: Strike a Balance in Continual Panoptic Segmentatio…

Dataset distillation is an effective technique for reducing the cost and complexity of model training while maintaining performance by compressing large datasets into smaller, more efficient versions. In this paper, we present a novel…

Panoptic and instance segmentation networks are often trained with specialized object detection modules, complex loss functions, and ad-hoc post-processing steps to manage the permutation-invariance of the instance masks. This work builds…

StyleGAN family is one of the most popular Generative Adversarial Networks (GANs) for unconditional generation. Despite its impressive performance, its high demand on storage and computation impedes their deployment on resource-constrained…

Practical autonomous driving systems face two crucial challenges: memory constraints and domain gap issues. In this paper, we present a novel approach to learn domain adaptive knowledge in models with limited memory, thus bestowing the…

Deep learning-based techniques have proven effective in polyp segmentation tasks when provided with sufficient pixel-wise labeled data. However, the high cost of manual annotation has created a bottleneck for model generalization. To…

Class imbalance is a fundamental problem in computer vision applications such as semantic segmentation. Specifically, uneven class distributions in a training dataset often result in unsatisfactory performance on under-represented classes.…

Deep models trained on long-tailed datasets exhibit unsatisfactory performance on tail classes. Existing methods usually modify the classification loss to increase the learning focus on tail classes, which unexpectedly sacrifice the…

Accurately identifying student misconceptions is crucial for personalized education but faces three challenges: (1) data scarcity with long-tail distribution, where authentic student reasoning is difficult to synthesize; (2) fuzzy…

This paper presents a new mechanism to facilitate the training of mask transformers for efficient panoptic segmentation, democratizing its deployment. We observe that due to its high complexity, the training objective of panoptic…

Transfer learning promises to reduce the high sample complexity of deep reinforcement learning (RL), yet existing methods struggle with domain shift between source and target environments. Policy distillation provides powerful tactical…

Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continual learning as avoiding interference with past updates,…

Continual learning (CL) methods designed for natural image classification often fail to reach basic quality standards for medical image segmentation. Atlas-based segmentation, a well-established approach in medical imaging, incorporates…

Vision-language retrieval aims to search for similar instances in one modality based on queries from another modality. The primary objective is to learn cross-modal matching representations in a latent common space. Actually, the assumption…

Generative models offer a promising paradigm for the final stage reranking in multi-stage recommender systems, with the ability to capture inter-item dependencies within reranked lists. However, their practical deployment still faces two…

Substantial efforts have been devoted to alleviating the impact of the long-tailed class distribution in federated learning. In this work, we observe an interesting phenomenon that certain weak classes consistently exist even for…

Distribution matching distillation (DMD) facilitates few-step image generation by aligning a distilled student with a reference multi-step teacher. In practice, however, optimizing DMD can reduce sample diversity in few-step synthesis, and…

Class-incremental fault diagnosis requires a model to adapt to new fault classes while retaining previous knowledge. However, limited research exists for imbalanced and long-tailed data. Extracting discriminative features from few-shot…

Learning based on multimodal data has attracted increasing interest recently. While a variety of sensory modalities can be collected for training, not all of them are always available in development scenarios, which raises the challenge to…

Previous Knowledge Distillation based efficient image retrieval methods employs a lightweight network as the student model for fast inference. However, the lightweight student model lacks adequate representation capacity for effective…

Knowledge distillation becomes a de facto standard to improve the performance of small neural networks. Most of the previous works propose to regress the representational features from the teacher to the student in a one-to-one spatial…