Related papers: Seeing the Whole Picture: Distribution-Guided Data…

As camera and LiDAR sensors capture complementary information used in autonomous driving, great efforts have been made to develop semantic segmentation algorithms through multi-modality data fusion. However, fusion-based approaches require…

Dataset distillation (DD) has emerged as a widely adopted technique for crafting a synthetic dataset that captures the essential information of a training dataset, facilitating the training of accurate neural models. Its applications span…

Unsupervised semantic segmentation requires assigning a label to every pixel without any human annotations. Despite recent advances in self-supervised representation learning for individual images, unsupervised semantic segmentation with…

Dataset distillation aims to distill the knowledge of a large-scale real dataset into small yet informative synthetic data such that a model trained on it performs as well as a model trained on the full dataset. Despite recent progress,…

Open-vocabulary semantic segmentation (OVSS) aims to segment arbitrary category regions in images using open-vocabulary prompts, necessitating that existing methods possess pixel-level vision-language alignment capability. Typically, this…

Dataset distillation (DD) condenses large datasets into compact yet informative substitutes, preserving performance comparable to the original dataset while reducing storage, transmission costs, and computational consumption. However,…

Most of recent attention-guided feature masking distillation methods perform knowledge transfer via global teacher attention maps without delving into fine-grained clues. Instead, performing distillation at finer granularity is conducive to…

Semantic segmentation benchmarks in the realm of autonomous driving are dominated by large pre-trained transformers, yet their widespread adoption is impeded by substantial computational costs and prolonged training durations. To lift this…

Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…

Few-shot learning is a promising way for reducing the label cost in new categories adaptation with the guidance of a small, well labeled support set. But for few-shot semantic segmentation, the pixel-level annotations of support images are…

Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…

Dataset distillation (DD) has emerged as a powerful paradigm for dataset compression, enabling the synthesis of compact surrogate datasets that approximate the training utility of large-scale ones. While significant progress has been…

Dataset distillation aims to find a synthetic training set such that training on the synthetic data achieves similar performance to training on real data, with orders of magnitude less computational requirements. Existing methods can be…

Existing techniques often attempt to make knowledge transfer from a powerful machine translation (MT) to speech translation (ST) model with some elaborate techniques, which often requires transcription as extra input during training.…

Recently, there have been significant improvements in the accuracy of CNN models for semantic segmentation. However, these models are often heavy and suffer from low inference speed, which limits their practical application. To address this…

Zero-shot Semantic Segmentation (ZSS) aims to segment both seen and unseen classes using supervision from only seen classes. Beyond adaptation-based methods, distillation-based approaches transfer vision-language alignment of…

Dataset distillation has emerged as a strategy to compress real-world datasets for efficient training. However, it struggles with large-scale and high-resolution datasets, limiting its practicality. This paper introduces a novel…

In this paper, we introduce a novel knowledge distillation approach for the semantic segmentation task. Unlike previous methods that rely on power-trained teachers or other modalities to provide additional knowledge, our approach does not…

Semantic segmentation is the pixel-wise labelling of an image. Since the problem is defined at the pixel level, determining image class labels only is not acceptable, but localising them at the original image pixel resolution is necessary.…

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the…