Related papers: Modeling the Background for Incremental Learning i…
Semantic segmentation models are limited in their ability to scale to large numbers of object classes. In this paper, we introduce the new task of zero-shot semantic segmentation: learning pixel-wise classifiers for never-seen object…
Adversarial training is promising for improving robustness of deep neural networks towards adversarial perturbations, especially on the classification task. The effect of this type of training on semantic segmentation, contrarily, just…
Continual learning seeks to maintain stable adaptation under non-stationary environments, yet this problem becomes particularly challenging in object detection, where most existing methods implicitly assume relatively balanced visual…
This paper proposes a new active learning method for semantic segmentation. The core of our method lies in a new annotation query design. It samples informative local image regions (e.g., superpixels), and for each of such regions, asks an…
We propose a novel locally adaptive learning estimator for enhancing the inter- and intra- discriminative capabilities of Deep Neural Networks, which can be used as improved loss layer for semantic image segmentation tasks. Most loss layers…
Efficient categorization of historical documents is crucial for fields such as genealogy, legal research, and historical scholarship, where manual classification is impractical for large collections due to its labor-intensive and…
Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to…
Deep learning models generally display catastrophic forgetting when learning new data continuously. Many incremental learning approaches address this problem by reusing data from previous tasks while learning new tasks. However, the direct…
Semantic segmentation requires dense pixel-level annotations, which are costly and time-consuming to acquire. To address this, we present SeSAM, a framework that uses a foundational segmentation model, i.e. Segment Anything Model (SAM),…
While nowadays deep neural networks achieve impressive performances on semantic segmentation tasks, they are usually trained by optimizing pixel-wise losses such as cross-entropy. As a result, the predictions outputted by such networks…
Incremental semantic segmentation(ISS) is an emerging task where old model is updated by incrementally adding new classes. At present, methods based on convolutional neural networks are dominant in ISS. However, studies have shown that such…
Taming diffusion models for generative segmentation has attracted increasing attention. While existing approaches primarily focus on architectural tweaks or training heuristics, there remains a limited understanding of the intrinsic…
State-of-the-art methods for semantic segmentation are based on deep neural networks trained on large-scale labeled datasets. Acquiring such datasets would incur large annotation costs, especially for dense pixel-level prediction tasks like…
Vanilla pixel-level classifiers for semantic segmentation are based on a certain paradigm, involving the inner product of fixed prototypes obtained from the training set and pixel features in the test image. This approach, however,…
Learning versatile, fine-grained representations from irregular event streams is pivotal yet nontrivial, primarily due to the heavy annotation that hinders scalability in dataset size, semantic richness, and application scope. To mitigate…
Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate…
Scene labeling is a challenging classification problem where each input image requires a pixel-level prediction map. Recently, deep-learning-based methods have shown their effectiveness on solving this problem. However, we argue that the…
Pre-trained representation is one of the key elements in the success of modern deep learning. However, existing works on continual learning methods have mostly focused on learning models incrementally from scratch. In this paper, we explore…
Weakly supervised semantic segmentation is a challenging task as it only takes image-level information as supervision for training but produces pixel-level predictions for testing. To address such a challenging task, most recent…
Real-time semantic segmentation models offer an excellent balance between accuracy and inference speed. However, deploying these models in dynamic real world environments often requires the ability to learn novel classes incrementally…