Related papers: Visual Concept Reasoning Networks

Recently, dense connections have attracted substantial attention in computer vision because they facilitate gradient flow and implicit deep supervision during training. Particularly, DenseNet, which connects each layer to every other layer…

Referring image segmentation is a challenging task that involves generating pixel-wise segmentation masks based on natural language descriptions. The complexity of this task increases with the intricacy of the sentences provided. Existing…

Despite the success of convolution- and attention-based models in vision tasks, their rigid receptive fields and complex architectures limit their ability to model irregular spatial patterns and hinder interpretability, therefore posing…

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…

Visual Commonsense Reasoning (VCR) is a cognitive task, challenging models to answer visual questions requiring human commonsense, and to provide rationales explaining why the answers are correct. With emergence of Large Language Models…

As computer vision continues to advance and finds widespread applications across various domains, the need for interpretability in deep learning models becomes paramount. Existing methods often resort to post-hoc techniques or prototypes to…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Effective retinal vessel segmentation requires a sophisticated integration of global contextual awareness and local vessel continuity. To address this challenge, we propose the Graph Capsule Convolution Network (GCC-UNet), which merges…

Many interpretable AI approaches have been proposed to provide plausible explanations for a model's decision-making. However, configuring an explainable model that effectively communicates among computational modules has received less…

Scene recognition is currently one of the top-challenging research fields in computer vision. This may be due to the ambiguity between classes: images of several scene classes may share similar objects, which causes confusion among them.…

Semantic segmentation necessitates approaches that learn high-level characteristics while dealing with enormous amounts of data. Convolutional neural networks (CNNs) can learn unique and adaptive features to achieve this aim. However, due…

Visual concept discovery has long been deemed important to improve interpretability of neural networks, because a bank of semantically meaningful concepts would provide us with a starting point for building machine learning models that…

We propose a novel visual tracking algorithm based on the representations from a discriminatively trained Convolutional Neural Network (CNN). Our algorithm pretrains a CNN using a large set of videos with tracking ground-truths to obtain a…

Visual image reconstruction, the decoding of perceptual content from brain activity into images, has advanced significantly with the integration of deep neural networks (DNNs) and generative models. This review traces the field's evolution…

We present a novel technique for interpreting the neurons in CLIP-ResNet by decomposing their contributions to the output into individual computation paths. More specifically, we analyze all pairwise combinations of neurons and the…

Residual learning has recently surfaced as an effective means of constructing very deep neural networks for object recognition. However, current incarnations of residual networks do not allow for the modeling and integration of complex…

Convolutional Neural Networks (CNNs) have revolutionized the understanding of visual content. This is mainly due to their ability to break down an image into smaller pieces, extract multi-scale localized features and compose them to…

Understanding what deep network models capture in their learned representations is a fundamental challenge in computer vision. We present a new methodology to understanding such vision models, the Visual Concept Connectome (VCC), which…

Semantic segmentation has made significant strides in pixel-level image understanding, yet it remains limited in capturing contextual and semantic relationships between objects. Current models, such as CNN and Transformer-based…

Advances in multi-modal embeddings, and in particular CLIP, have recently driven several breakthroughs in Computer Vision (CV). CLIP has shown impressive performance on a variety of tasks, yet, its inherently opaque architecture may hinder…