Related papers: Parallel Backpropagation for Shared-Feature Visual…

Weakly supervised image segmentation trained with image-level labels usually suffers from inaccurate coverage of object areas during the generation of the pseudo groundtruth. This is because the object activation maps are trained with the…

Understanding internal feature representations of deep neural networks (DNNs) is a fundamental step toward model interpretability. Inspired by neuroscience methods that probe biological neurons using visual stimuli, recent deep learning…

Recognition and reasoning are two pillars of visual understanding. However, these tasks have an imbalance in focus; whereas recent advances in neural networks have shown strong empirical performance in visual recognition, there has been…

A major prerequisite for the application of machine learning models in clinical decision making is trust and interpretability. Current explainability studies in the neuroimaging community have mostly focused on explaining individual…

Visual reasoning tasks such as visual question answering (VQA) require an interplay of visual perception with reasoning about the question semantics grounded in perception. However, recent advances in this area are still primarily driven by…

Supervised deep convolutional neural networks (DCNNs) are currently one of the best computational models that can explain how the primate ventral visual stream solves object recognition. However, embodied cognition has not been considered…

The deep generative adversarial networks (GAN) recently have been shown to be promising for different computer vision applications, like image edit- ing, synthesizing high resolution images, generating videos, etc. These networks and the…

Deep learning has excelled in image recognition tasks through neural networks inspired by the human brain. However, the necessity for large models to improve prediction accuracy introduces significant computational demands and extended…

The brain cortex, which processes visual, auditory and sensory data in the brain, is known to have many recurrent connections within its layers and from higher to lower layers. But, in the case of machine learning with neural networks, it…

Mechanistic interpretability aims to understand how models store representations by breaking down neural networks into interpretable units. However, the occurrence of polysemantic neurons, or neurons that respond to multiple unrelated…

Projecting visual features into word embedding space has become a significant fusion strategy adopted by Multimodal Large Language Models (MLLMs). However, its internal mechanisms have yet to be explored. Inspired by multilingual research,…

Multivariate Pattern (MVP) classification holds enormous potential for decoding visual stimuli in the human brain by employing task-based fMRI data sets. There is a wide range of challenges in the MVP techniques, i.e. decreasing noise and…

How can a machine learn to recognize visual attributes emerging out of online community without a definitive supervised dataset? This paper proposes an automatic approach to discover and analyze visual attributes from a noisy collection of…

Object co-segmentation is the task of segmenting the same objects from multiple images. In this paper, we propose the Attention Based Object Co-Segmentation for object co-segmentation that utilize a novel attention mechanism in the…

The majority of computer vision algorithms fail to find higher-order (abstract) patterns in an image so are not robust against adversarial attacks, unlike human lateralized vision. Deep learning considers each input pixel in a homogeneous…

Feed-forward convolutional neural networks (CNNs) are currently state-of-the-art for object classification tasks such as ImageNet. Further, they are quantitatively accurate models of temporally-averaged responses of neurons in the primate…

Despite the growing use of transformer models in computer vision, a mechanistic understanding of these networks is still needed. This work introduces a method to reverse-engineer Vision Transformers trained to solve image classification…

Fine-grained visual recognition is to classify objects with visually similar appearances into subcategories, which has made great progress with the development of deep CNNs. However, handling subtle differences between different…

Feature visualization has gained substantial popularity, particularly after the influential work by Olah et al. in 2017, which established it as a crucial tool for explainability. However, its widespread adoption has been limited due to a…

Human observers engage in selective information uptake when classifying visual patterns. The same is true of deep neural networks, which currently constitute the best performing artificial vision systems. Our goal is to examine the…