Related papers: VISION DIFFMASK: Faithful Interpretation of Vision…
This work investigates a simple yet powerful dense prediction task adapter for Vision Transformer (ViT). Unlike recently advanced variants that incorporate vision-specific inductive biases into their architectures, the plain ViT suffers…
Understanding the mechanisms underlying deep neural networks remains a fundamental challenge in machine learning and computer vision. One promising, yet only preliminarily explored approach, is feature inversion, which attempts to…
Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…
This paper introduces a novel watermarking method for diffusion models. It is based on guiding the diffusion process using the gradient computed from any off-the-shelf watermark decoder. The gradient computation encompasses different image…
The goal of imitation learning is to mimic expert behavior without access to an explicit reward signal. Expert demonstrations provided by humans, however, often show significant variability due to latent factors that are typically not…
Visual counterfactual explanations aim to reveal the minimal semantic modifications that can alter a model's prediction, providing causal and interpretable insights into deep neural networks. However, existing diffusion-based counterfactual…
As deep learning models increasingly find applications in critical domains such as medical imaging, the need for transparent and trustworthy decision-making becomes paramount. Many explainability methods provide insights into how these…
Interpreting the inner workings of deep learning models is crucial for establishing trust and ensuring model safety. Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution…
In recent years, Transformer-based architectures have become the dominant method for Computer Vision applications. While Transformers are explainable and scale well with dataset size, they lack the inductive biases of Convolutional Neural…
Video watermarking embeds a message into a cover video in an imperceptible manner, which can be retrieved even if the video undergoes certain modifications or distortions. Traditional watermarking methods are often manually designed for…
We propose the first unsupervised and learning-based method to identify interpretable directions in h-space of pre-trained diffusion models. Our method is derived from an existing technique that operates on the GAN latent space.…
Deformable objects often appear in unstructured configurations. Tracing deformable objects helps bringing them into extended states and facilitating the downstream manipulation tasks. Due to the requirements for object-specific modeling or…
We propose an efficient approach to train large diffusion models with masked transformers. While masked transformers have been extensively explored for representation learning, their application to generative learning is less explored in…
We present a novel method for exemplar-based image translation, called matching interleaved diffusion models (MIDMs). Most existing methods for this task were formulated as GAN-based matching-then-generation framework. However, in this…
While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lagged behind their architectural evolution. Unlike traditional…
Deformable objects manipulation can benefit from representations that seamlessly integrate vision and touch while handling occlusions. In this work, we present a novel approach for, and real-world demonstration of, multimodal visuo-tactile…
Why should we trust the detections of deep neural networks for manipulated faces? Understanding the reasons is important for users in improving the fairness, reliability, privacy and trust of the detection models. In this work, we propose…
A common method to study deep learning systems is to use simplified model representations--for example, using singular value decomposition to visualize the model's hidden states in a lower dimensional space. This approach assumes that the…
Diffusion models have gained tremendous success in text-to-image generation, yet still lag behind with visual understanding tasks, an area dominated by autoregressive vision-language models. We propose a large-scale and fully end-to-end…
Many real-world applications today like video surveillance and urban governance need to address the recognition of masked faces, where content replacement by diverse masks often brings in incomplete appearance and ambiguous representation,…