Related papers: Leveraging Pretrained Image Classifiers for Langua…

Image segmentation is a fundamental task in computer vision, aimed at partitioning an image into semantically meaningful regions. Referring image segmentation extends this task by using natural language expressions to localize specific…

Deep neural network models have achieved remarkable progress in 3D scene understanding while trained in the closed-set setting and with full labels. However, the major bottleneck is that these models do not have the capacity to recognize…

This paper proposes a convolutional neural network that can fuse high-level prior for semantic image segmentation. Motivated by humans' vision recognition system, our key design is a three-layer generative structure consisting of high-level…

This paper presents a novel 3D semantic segmentation method for large-scale point cloud data that does not require annotated 3D training data or paired RGB images. The proposed approach projects 3D point clouds onto 2D images using virtual…

Existing machine learning models demonstrate excellent performance in image object recognition after training on a large-scale dataset under full supervision. However, these models only learn to map an image to a predefined class index,…

Current methods for LIDAR semantic segmentation are not robust enough for real-world applications, e.g., autonomous driving, since it is closed-set and static. The closed-set assumption makes the network only able to output labels of…

Recovering clear structures from severely blurry inputs is a challenging problem due to the large movements between the camera and the scene. Although some works apply segmentation maps on human face images for deblurring, they cannot…

Significant progress has been made on visual captioning, largely relying on pre-trained features and later fixed object detectors that serve as rich inputs to auto-regressive models. A key limitation of such methods, however, is that the…

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…

As a critical clue of video super-resolution (VSR), inter-frame alignment significantly impacts overall performance. However, accurate pixel-level alignment is a challenging task due to the intricate motion interweaving in the video. In…

Generalization is a central problem in machine learning, especially when data is limited. Using prior information to enforce constraints is the principled way of encouraging generalization. In this work, we propose to leverage the prior…

Zero-shot instance segmentation aims to detect and precisely segment objects of unseen categories without any training samples. Since the model is trained on seen categories, there is a strong bias that the model tends to classify all the…

Data augmentation is an essential technique in improving the generalization of deep neural networks. The majority of existing image-domain augmentations either rely on geometric and structural transformations, or apply different kinds of…

Referring Audio-Visual Segmentation (Ref-AVS) seeks to localize and segment target objects in video frames based on visual, auditory, and textual referring cues. The task is challenging because the relevance of different modalities varies…

We study lifelong visual perception in an embodied setup, where we develop new models and compare various agents that navigate in buildings and occasionally request annotations which, in turn, are used to refine their visual perception…

Training a deep network to perform semantic segmentation requires large amounts of labeled data. To alleviate the manual effort of annotating real images, researchers have investigated the use of synthetic data, which can be labeled…

Large Vision Language Models (LVLMs) have demonstrated impressive zero-shot capabilities in various vision-language dialogue scenarios. However, the absence of fine-grained visual object detection hinders the model from understanding the…

Visual semantic segmentation aims at separating a visual sample into diverse blocks with specific semantic attributes and identifying the category for each block, and it plays a crucial role in environmental perception. Conventional…

Producing densely annotated data is a difficult and tedious task for medical imaging applications. To address this problem, we propose a novel approach to generate supervision for semi-supervised semantic segmentation. We argue that…

The ability to localize and segment objects from unseen classes would open the door to new applications, such as autonomous object learning in active vision. Nonetheless, improving the performance on unseen classes requires additional…