Related papers: LIP: Local Importance-based Pooling

Deep convolutional neural networks have recently proven extremely competitive in challenging image recognition tasks. This paper proposes the epitomic convolution as a new building block for deep neural networks. An epitomic convolution…

A significant issue in training deep neural networks to solve supervised learning tasks is the need for large numbers of labelled datapoints. The goal of semi-supervised learning is to leverage ubiquitous unlabelled data, together with…

Although the recent progress in the deep neural network has led to the development of learnable local feature descriptors, there is no explicit answer for estimation of the necessary size of a neural network. Specifically, the local feature…

Convolutional neural networks are becoming standard tools for solving object recognition and visual tasks. However, most of the design and implementation of these complex models are based on trail-and-error. In this report, the main focus…

Large language models are known to contain representational redundancy across network depth, making depth pruning an effective approach for improving inference efficiency. Existing one-shot pruning methods rely on local layer importance or…

Several recent approaches showed how the representations learned by Convolutional Neural Networks can be repurposed for novel tasks. Most commonly it has been shown that the activation features of the last fully connected layers (fc7 or…

In this paper, we demonstrate that CLIP can also be adapted to downstream tasks where its vision-language alignment is suboptimally learned during pre-training on web-crawled data, all without requiring fine-tuning. We explore the case of…

Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only. Unlike previous methods which are composed of multiple offline stages, we propose Sequential Label Propagation and…

Recent successes in self-supervised learning (SSL) model spatial co-occurrences of visual features either by masking portions of an image or by aggressively cropping it. Here, we propose a new way to model spatial co-occurrences by aligning…

Recent advances in multimodal learning has resulted in powerful vision-language models, whose representations are generalizable across a variety of downstream tasks. Recently, their generalization ability has been further extended by…

Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations. Yet such models are not…

Resampling is a key component of sample-based recursive state estimation in particle filters. Recent work explores differentiable particle filters for end-to-end learning. However, resampling remains a challenge in these works, as it is…

Driven by Convolutional Neural Networks, object detection and semantic segmentation have gained significant improvements. However, existing methods on the basis of a full top-down module have limited robustness in handling those two tasks…

Graph convolutional networks (GCNs) have recently received wide attentions, due to their successful applications in different graph tasks and different domains. Training GCNs for a large graph, however, is still a challenge. Original…

Contrastive Language-Image Pretraining (CLIP) achieves strong generalization in vision-language tasks by aligning images and texts in a shared embedding space. However, recent findings show that CLIP-like models still underutilize…

Semi-supervised learning (SSL), which aims at leveraging a few labeled images and a large number of unlabeled images for network training, is beneficial for relieving the burden of data annotation in medical image segmentation. According to…

Convolutional networks require extensive image annotation, which can be costly and time-consuming. Feature Learning from Image Markers (FLIM) tackles this challenge by estimating encoder filters (i.e., kernel weights) from user-drawn…

Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small. To ensure good generalizability of deep…

Multi-label recognition with partial labels (MLR-PL), in which only some labels are known while others are unknown for each image, is a practical task in computer vision, since collecting large-scale and complete multi-label datasets is…

Object classification is one of the many holy grails in computer vision and as such has resulted in a very large number of algorithms being proposed already. Specifically in recent years there has been considerable progress in this area…