Related papers: ReMaX: Relaxing for Better Training on Efficient P…

This paper presents a new regularization method to train a fully convolutional network for semantic tissue segmentation in histopathological images. This method relies on the benefit of unsupervised learning, in the form of image…

Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…

In this paper, we present a new data-efficient voxel-based self-supervised learning method for event cameras. Our pre-training overcomes the limitations of previous methods, which either sacrifice temporal information by converting event…

Scribble-supervised medical image segmentation tackles the limitation of sparse masks. Conventional approaches alternate between: labeling pseudo-masks and optimizing network parameters. However, such iterative two-stage paradigm is…

Decomposing complex tasks into a sequence of simpler subtasks can improve learning efficiency for an autonomous agent. Reinforcement learning (RL) can be used to optimize agent policies to complete subtasks, but requires well-defined…

Deep learning has thrived by training on large-scale datasets. However, in robotics applications sample efficiency is critical. We propose a novel adaptive masked proxies method that constructs the final segmentation layer weights from few…

We introduce a highly efficient method for panoptic segmentation of large 3D point clouds by redefining this task as a scalable graph clustering problem. This approach can be trained using only local auxiliary tasks, thereby eliminating the…

Although scaling up the number of trainable parameters in both pre-training and fine-tuning can effectively improve the performance of large language models, it also leads to increased computational overhead. When delving into the parameter…

We propose a self-supervised spatio-temporal matching method, coined Motion-Aware Mask Propagation (MAMP), for video object segmentation. MAMP leverages the frame reconstruction task for training without the need for annotations. During…

In this paper, we aim to tackle the challenging few-shot segmentation task from a new perspective. Typical methods follow the paradigm to firstly learn prototypical features from support images and then match query features in pixel-level…

Finetuning a pretrained backbone in the encoder part of an image transformer network has been the traditional approach for the semantic segmentation task. However, such an approach leaves out the semantic context that an image provides…

Panoptic Part Segmentation (PPS) aims to unify panoptic segmentation and part segmentation into one task. Previous work mainly utilizes separated approaches to handle thing, stuff, and part predictions individually without performing any…

Instance segmentation aims to detect and segment individual objects in a scene. Most existing methods rely on precise mask annotations of every category. However, it is difficult and costly to segment objects in novel categories because a…

Most weakly supervised semantic segmentation (WSSS) methods follow the pipeline that generates pseudo-masks initially and trains the segmentation model with the pseudo-masks in fully supervised manner after. However, we find some matters…

Optimizing Neural networks is a difficult task which is still not well understood. On the other hand, fixed representation methods such as kernels and random features have provable optimization guarantees but inferior performance due to…

Panoptic segmentation is an important computer vision task, where the current state-of-the-art solutions require specialized components to perform well. We propose a simple generalist framework based on a deep encoder - shallow decoder…

Semi-supervised semantic segmentation aims to utilize limited labeled images and abundant unlabeled images to achieve label-efficient learning, wherein the weak-to-strong consistency regularization framework, popularized by FixMatch, is…

Many deep learning based automated medical image segmentation systems, in reality, face difficulties in deployment due to the cost of massive data annotation and high latency in model iteration. We propose a dynamic interactive learning…

Dense prediction tasks, such as semantic segmentation, depth estimation, and surface normal prediction, can be easily formulated as per-pixel classification (discrete outputs) or regression (continuous outputs). This per-pixel prediction…

Unstructured pruning reduces the memory footprint in deep neural networks (DNNs). Recently, researchers proposed different types of structural pruning intending to reduce also the computation complexity. In this work, we first suggest a new…