Related papers: Extracting Causal Visual Features for Limited labe…

We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by using only image-level labels -- the most crucial step in WSSS. We…

Current state of the art methods for generating semantic segmentation rely heavily on a large set of images that have each pixel labeled with a class of interest label or background. Coming up with such labels, especially in domains that…

Automated medical image segmentation is an important step in many medical procedures. Recently, deep learning networks have been widely used for various medical image segmentation tasks, with U-Net and generative adversarial nets (GANs)…

Classical machine learning techniques often struggle with overfitting and unreliable predictions when exposed to novel conditions. Introducing causality into the modelling process offers a promising way to mitigate these challenges by…

Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make…

The fully convolutional network (FCN) has achieved tremendous success in dense visual recognition tasks, such as scene segmentation. The last layer of FCN is typically a global classifier (1x1 convolution) to recognize each pixel to a…

In this paper we report results for recognizing colorectal NBI endoscopic images by using features extracted from convolutional neural network (CNN). In this comparative study, we extract features from different layers from different CNN…

Significant progress has been achieved on the improvement and downstream usages of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention is paid to the interpretation of CLIP. We propose a…

Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative…

Estimates of image gradients play a ubiquitous role in image segmentation and classification problems since gradients directly relate to the boundaries or the edges of a scene. This paper proposes an unified approach to gradient estimation…

Even though convolutional neural networks (CNNs) are driving progress in medical image segmentation, standard models still have some drawbacks. First, the use of multi-scale approaches, i.e., encoder-decoder architectures, leads to a…

Image fusion aims to combine complementary information from multiple source images to generate more comprehensive scene representations. Existing methods primarily rely on the stacking and design of network architectures to enhance the…

Lack of explainability in artificial intelligence, specifically deep neural networks, remains a bottleneck for implementing models in practice. Popular techniques such as Gradient-weighted Class Activation Mapping (Grad-CAM) provide a…

Graphical structures estimated by causal learning algorithms from time series data can provide misleading causal information if the causal timescale of the generating process fails to match the measurement timescale of the data. Existing…

Context, as referred to situational factors related to the object of interest, can help infer the object's states or properties in visual recognition. As such contextual features are too diverse (across instances) to be annotated, existing…

Humans have perfected the art of learning from multiple modalities through sensory organs. Despite their impressive predictive performance on a single modality, neural networks cannot reach human level accuracy with respect to multiple…

Convolutional neural networks have been shown to develop internal representations, which correspond closely to semantically meaningful objects and parts, although trained solely on class labels. Class Activation Mapping (CAM) is a recent…

We provide a rigorous definition of the visual cause of a behavior that is broadly applicable to the visually driven behavior in humans, animals, neurons, robots and other perceiving systems. Our framework generalizes standard accounts of…

We explore multi-scale convolutional neural nets (CNNs) for image classification. Contemporary approaches extract features from a single output layer. By extracting features from multiple layers, one can simultaneously reason about high,…

This document summarizes different visual explanations methods such as CAM, Grad-CAM, Localization using Multiple Instance Learning - Saliency-based methods, Saliency-driven Class-Impressions, Muting pixels in input image - Adversarial…