Related papers: Critic Guided Segmentation of Rewarding Objects in…

Recently, adversarial imitation learning has shown a scalable reward acquisition method for inverse reinforcement learning (IRL) problems. However, estimated reward signals often become uncertain and fail to train a reliable statistical…

For visual object recognition tasks, the illumination variations can cause distinct changes in object appearance and thus confuse the deep neural network based recognition models. Especially for some rare illumination conditions, collecting…

Social media is daily creating massive multimedia content with paired image and text, presenting the pressing need to automate the vision and language understanding for various multimodal classification tasks. Compared to the commonly…

We propose a self-supervised approach for learning representations and robotic behaviors entirely from unlabeled videos recorded from multiple viewpoints, and study how this representation can be used in two robotic imitation settings:…

We propose a dual system for unsupervised object segmentation in video, which brings together two modules with complementary properties: a space-time graph that discovers objects in videos and a deep network that learns powerful object…

The use of attention models for automated image captioning has enabled many systems to produce accurate and meaningful descriptions for images. Over the years, many novel approaches have been proposed to enhance the attention process using…

Self-rewarding have emerged recently as a powerful tool in the field of Natural Language Processing (NLP), allowing language models to generate high-quality relevant responses by providing their own rewards during training. This innovative…

In this paper, we are interested in understanding self-supervised pretraining through studying the capability that self-supervised representation pretraining methods learn part-aware representations. The study is mainly motivated by that…

Self-supervised learning methods are attractive candidates for automatic object picking. However, the trial samples lack the complete ground truth because the observable parts of the agent are limited. That is, the information contained in…

We present two practical improvement techniques for unsupervised segmentation learning. These techniques address limitations in the resolution and accuracy of predicted segmentation maps of recent state-of-the-art methods. Firstly, we…

In recent years, Deep Neural Networks (DNN) have emerged as a practical method for image recognition. The raw data, which contain sensitive information, are generally exploited within the training process. However, when the training process…

Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and…

Defining reward functions for skill learning has been a long-standing challenge in robotics. Recently, vision-language models (VLMs) have shown promise in defining reward signals for teaching robots manipulation skills. However, existing…

In this work, we address the task of few-shot part segmentation, which aims to segment the different parts of an unseen object using very few labeled examples. It is found that leveraging the textual space of a powerful pre-trained…

Image-point class incremental learning helps the 3D-points-vision robots continually learn category knowledge from 2D images, improving their perceptual capability in dynamic environments. However, some incremental learning methods address…

3D point cloud segmentation is an important function that helps robots understand the layout of their surrounding environment and perform tasks such as grasping objects, avoiding obstacles, and finding landmarks. Current segmentation…

Humans describe images in terms of nouns and adjectives while algorithms operate on images represented as sets of pixels. Bridging this gap between how humans would like to access images versus their typical representation is the goal of…

Reinforcement learning (RL), particularly in sparse reward settings, often requires prohibitively large numbers of interactions with the environment, thereby limiting its applicability to complex problems. To address this, several prior…

Masked Image Modeling (MIM) is a powerful self-supervised strategy for visual pre-training without the use of labels. MIM applies random crops to input images, processes them with an encoder, and then recovers the masked inputs with a…

Deep neural network-based semantic segmentation generally requires large-scale cost extensive annotations for training to obtain better performance. To avoid pixel-wise segmentation annotations which are needed for most methods, recently…