Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Convolutional Neural Networks: Semantic Segmentation

Description

This lecture covers the use of Convolutional Neural Networks (CNNs) for semantic segmentation, focusing on the transition from patch classification to pixel classification. The instructor explains the limitations of early models and introduces new models designed specifically for pixel classification. Different approaches to semantic segmentation, such as encoder-decoder models and hypercolumns, are discussed. The lecture also delves into the concept of learned decoding using techniques like U-Net and transposed convolutions. The importance of skip connections in maintaining high-resolution information during decoding is highlighted. The session concludes with a summary emphasizing the significance of CNNs in research and industry, encouraging further exploration through reading clubs and additional courses.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

Official source

Ontological neighbourhood

Information engineering

Machine learning: Artificial neural networks

Related concepts (32)

Convolutional neural network

Convolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.

Image segmentation

In and computer vision, image segmentation is the process of partitioning a into multiple image segments, also known as image regions or image objects (sets of pixels). The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. More precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain characteristics.

Residual neural network

A Residual Neural Network (a.k.a. Residual Network, ResNet) is a deep learning model in which the weight layers learn residual functions with reference to the layer inputs. A Residual Network is a network with skip connections that perform identity mappings, merged with the layer outputs by addition. It behaves like a Highway Network whose gates are opened through strongly positive bias weights. This enables deep learning models with tens or hundreds of layers to train easily and approach better accuracy when going deeper.

Object co-segmentation

In computer vision, object co-segmentation is a special case of , which is defined as jointly segmenting semantically similar objects in multiple images or video frames. It is often challenging to extract segmentation masks of a target/object from a noisy collection of images or video frames, which involves object discovery coupled with . A noisy collection implies that the object/target is present sporadically in a set of images or the object/target disappears intermittently throughout the video of interest.

Transformer (machine learning model)

A transformer is a deep learning architecture that relies on the parallel multi-head attention mechanism. The modern transformer was proposed in the 2017 paper titled 'Attention Is All You Need' by Ashish Vaswani et al., Google Brain team. It is notable for requiring less training time than previous recurrent neural architectures, such as long short-term memory (LSTM), and its later variation has been prevalently adopted for training large language models on large (language) datasets, such as the Wikipedia corpus and Common Crawl, by virtue of the parallelized processing of input sequence.

Related lectures (35)

Deep Learning: Convolutional Neural Networks

Covers Convolutional Neural Networks, standard architectures, training techniques, and adversarial examples in deep learning.

Sequence to Sequence Models: Overview and Applications

Covers sequence to sequence models, their architecture, applications, and the role of attention mechanisms in improving performance.

Deep Learning: Convolutional Neural Networks

Introduces Convolutional Neural Networks, explaining their architecture, training process, and applications in semantic segmentation tasks.

Convolutional Neural Networks

Covers Convolutional Neural Networks, including layers, training strategies, standard architectures, tasks like semantic segmentation, and deep learning tricks.

Neural Networks: Two Layers Neural Network