85 citations · 150 across the 13 of their papers we have counts for
9 papers · 1 filter
TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment
Sweta Mahajan, Sukrut Rao, Jiahao Xie +2
Vision-language models such as CLIP are highly useful for diverse tasks due to their shared image-text embedding space. Despite this, the image and text embeddings are often poorly…
CFM: Language-aligned Concept Foundation Model for Vision
Kai Wittenmayer, Sukrut Rao, Amin Parchami-Araghi +2
Language-aligned vision foundation models perform strongly across diverse downstream tasks. Yet, their learned representations remain opaque, making interpreting their decision-mak…
B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
Shreyash Arya, Sukrut Rao, Moritz Böhle +1
B-cos Networks have been shown to be effective for obtaining highly human interpretable explanations of model decisions by architecturally enforcing stronger alignment between inpu…
Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
Sukrut Rao, Sweta Mahajan, Moritz Böhle +1
Concept Bottleneck Models (CBMs) have recently been proposed to address the 'black-box' problem of deep neural networks, by first mapping images to a human-understandable concept s…
Good Teachers Explain: Explanation-Enhanced Knowledge Distillation
Amin Parchami-Araghi, Moritz Böhle, Sukrut Rao +1
Knowledge Distillation (KD) has proven effective for compressing large teacher models into smaller student models. While it is well known that student models can achieve similar ac…
Studying How to Efficiently and Effectively Guide Models with Explanations
Sukrut Rao, Moritz Böhle, Amin Parchami-Araghi +1
Despite being highly performant, deep neural networks might base their decisions on features that spuriously correlate with the provided labels, thus hurting generalization. To mit…
Better Understanding Differences in Attribution Methods via Systematic Evaluations
Sukrut Rao, Moritz Böhle, Bernt Schiele
Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been…
Towards Better Understanding Attribution Methods
Sukrut Rao, Moritz Böhle, Bernt Schiele
Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been…
Adversarial Training against Location-Optimized Adversarial Patches
Sukrut Rao, David Stutz, Bernt Schiele
Deep neural networks have been shown to be susceptible to adversarial examples -- small, imperceptible changes constructed to cause mis-classification in otherwise highly accurate…