AIConfPaper
← Search

Rakshith Shetty

6 accepted papers

2021

Seeking Similarities Over Differences: Similarity-Based Domain Alignment for Adaptive Object Detection

Farzaneh Rezaeianaran, Rakshith Shetty, Rahaf Aljundi, Daniel Olmeda Reino, Shanshan Zhang, Bernt Schiele
ICCV 2021poster

In order to robustly deploy object detectors across a wide range of scenarios, they should be adaptable to shifts in the input distribution without the need to constantly annotate new data. This has motivated research in Unsupervised Domain Adaptation (UDA) algorithms for detection. UDA methods lear…

Cited by 111PDF ↗code ↗Scholar ↗
2020

Towards Automated Testing and Robustification by Semantic Adversarial Data Generation

Rakshith Shetty, Mario Fritz, Bernt Schiele
ECCV 2020poster

Widespread application of computer vision systems in real world tasks is currently hindered by their unexpected behavior on unseen examples. This occurs due to limitations of empirical testing on finite test sets and lack of systematic methods to identify the breaking points of a trained model. In t…

Cited by 5Source ↗PDF ↗Scholar ↗
2020

Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing

Vedika Agarwal, Rakshith Shetty, Mario Fritz
CVPR 2020poster

Despite significant success in Visual Question Answering (VQA), VQA models have been shown to be notoriously brittle to linguistic variations in the questions. Due to deficiencies in models and datasets, today's models often rely on correlations rather than predictions that are causal w.r.t. data. I…

Cited by 187PDF ↗code ↗Scholar ↗
2019

Not Using the Car to See the Sidewalk -- Quantifying and Controlling the Effects of Context in Classification and Segmentation

Rakshith Shetty, Bernt Schiele, Mario Fritz
CVPR 2019poster

Importance of visual context in scene understanding tasks is well recognized in the computer vision community. However, to what extent the computer vision models are dependent on the context to make their predictions is unclear. A model overly relying on context will fail when encountering objects…

Cited by 101PDF ↗Scholar ↗
2017

Paying Attention to Descriptions Generated by Image Captioning Models

Hamed R. Tavakoli, Rakshith Shetty, Ali Borji, Jorma Laaksonen
ICCV 2017poster

To bridge the gap between humans and machines in image understanding and describing, we need further insight into how people describe a perceived scene. In this paper, we study the agreement between bottom-up saliency-based visual attention and object referrals in scene description constructs. We in…

Cited by 99PDF ↗Scholar ↗
2017

Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training

Rakshith Shetty, Marcus Rohrbach, Lisa Anne Hendricks, Mario Fritz, Bernt Schiele
ICCV 2017poster

While strong progress has been made in image captioning recently, machine and human captions are still quite distinct. This is primarily due to the deficiencies in the generated word distribution, vocabulary size, and strong bias in the generators towards frequent captions. Furthermore, humans -- ri…

Cited by 311PDF ↗Scholar ↗