Related papers: CoinSeg: Contrast Inter- and Intra- Class Represen…

This work addresses the task of open world semantic segmentation using RGBD sensing to discover new semantic classes over time. Although there are many types of objects in the real-word, current semantic segmentation methods make a closed…

Graph contrastive learning defines a contrastive task to pull similar instances close and push dissimilar instances away. It learns discriminative node embeddings without supervised labels, which has aroused increasing attention in the past…

This paper considers the problem of utilizing a large-scale text-to-image diffusion model to tackle the challenging Inexact Segmentation (IS) task. Unlike traditional approaches that rely heavily on discriminative-model-based paradigms or…

Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have…

Recently contrastive learning has shown significant progress in learning visual representations from unlabeled data. The core idea is training the backbone to be invariant to different augmentations of an instance. While most methods only…

Uncertainty modeling in speaker representation aims to learn the variability present in speech utterances. While the conventional cosine-scoring is computationally efficient and prevalent in speaker recognition, it lacks the capability to…

Automatic delineation of organ-at-risk (OAR) and gross-tumor-volume (GTV) is of great significance for radiotherapy planning. However, it is a challenging task to learn powerful representations for accurate delineation under limited pixel…

Convolutional sparse coding (CSC) can learn representative shift-invariant patterns from multiple kinds of data. However, existing CSC methods can only model noises from Gaussian distribution, which is restrictive and unrealistic. In this…

Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference…

Medical tasks are prone to inter-rater variability due to multiple factors such as image quality, professional experience and training, or guideline clarity. Training deep learning networks with annotations from multiple raters is a common…

We design an open-vocabulary image segmentation model to organize an image into meaningful regions indicated by arbitrary texts. Recent works (CLIP and ALIGN), despite attaining impressive open-vocabulary classification accuracy with…

Deep learning research over the past years has shown that by increasing the scope or difficulty of the learning problem over time, increasingly complex learning problems can be addressed. We study incremental learning in the context of…

Vision-language models like CLIP have achieved remarkable progress in cross-modal representation learning, yet suffer from systematic misclassifications among visually and semantically similar categories. We observe that such confusion…

Robustness of deep neural networks to input noise remains a critical challenge, as naive noise injection often degrades accuracy on clean (uncorrupted) data. We propose a novel training framework that addresses this trade-off through two…

The dominant paradigm for learning video-text representations -- noise contrastive learning -- increases the similarity of the representations of pairs of samples that are known to be related, such as text and video from the same sample,…

Semantic segmentation in open-vocabulary scenarios presents significant challenges due to the wide range and granularity of semantic categories. Existing weakly-supervised methods often rely on category-specific supervision and ill-suited…

Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as…

In real-world clinical settings, data distributions evolve over time, with a continuous influx of new, limited disease cases. Therefore, class incremental learning is of great significance, i.e., deep learning models are required to learn…

Partially-supervised instance segmentation is a task which requests segmenting objects from novel unseen categories via learning on limited seen categories with annotated masks thus eliminating demands of heavy annotation burden. The key to…

Most of previous deepfake detection researches bent their efforts to describe and discriminate artifacts in human perceptible ways, which leave a bias in the learned networks of ignoring some critical invariance features intra-class and…