Related papers: Observing Context Improves Disparity Estimation wh…

Despite the great success of face recognition techniques, recognizing persons under unconstrained settings remains challenging. Issues like profile views, unfavorable lighting, and occlusions can cause substantial difficulties. Previous…

Media bias detection requires comprehensive integration of information derived from multiple news sources. Sentence-level political bias detection in news is no exception, and has proven to be a challenging task that requires an…

We address the problem of reward hacking, where maximising a proxy reward does not necessarily increase the true reward. This is a key concern for Large Language Models (LLMs), as they are often fine-tuned on human preferences that may not…

Fair inference in supervised learning is an important and active area of research, yielding a range of useful methods to assess and account for fairness criteria when predicting ground truth targets. As shown in recent work, however, when…

6D object pose estimation has been a research topic in the field of computer vision and robotics. Many modern world applications like robot grasping, manipulation, autonomous navigation etc, require the correct pose of objects present in a…

Inferring racial discrimination in police use of force -- the average causal effect of civilian race on use of force -- requires two assumptions about policing prior to potential use of force: that officers do not discriminate in whom they…

How do we determine whether two or more clothing items are compatible or visually appealing? Part of the answer lies in understanding of visual aesthetics, and is biased by personal preferences shaped by social attitudes, time, and place.…

Modern language models are trained on large amounts of data. These data inevitably include controversial and stereotypical content, which contains all sorts of biases related to gender, origin, age, etc. As a result, the models express…

Deep learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, e.g., hiring, banking, and criminal justice.…

Contextual information plays an important role in many computer vision tasks, such as object detection, video action detection, image classification, etc. Recognizing a single object or action out of context could be sometimes very…

The entropy of the codes usually serves as the rate loss in the recent learned lossy image compression methods. Precise estimation of the probabilistic distribution of the codes plays a vital role in the performance. However, existing deep…

Home entertainment systems feature in a variety of usage scenarios with one or more simultaneous users, for whom the complexity of choosing media to consume has increased rapidly over the last decade. Users' decision processes are complex…

Many epidemiological and clinical studies aim at analyzing a time-to-event endpoint. A common complication is right censoring. In some cases, it arises because subjects are still surviving after the study terminates or move out of the study…

The large majority of inferences drawn in empirical political research follow from model-based associations (e.g. regression). Here, we articulate the benefits of predictive modeling as a complement to this approach. Predictive models aim…

Assessing response quality to instructions in language models is vital but challenging due to the complexity of human language across different contexts. This complexity often results in ambiguous or inconsistent interpretations, making…

Proximal causal inference is a recently proposed framework for evaluating causal effects in the presence of unmeasured confounding. For point identification of causal effects, it leverages a pair of so-called treatment and outcome…

We propose a regression-based approach to removing implicit biases in representations. On tasks where the protected attribute is observed, the method is statistically more efficient than known approaches. Further, we show that this approach…

We propose an adversarial contextual model for detecting moving objects in images. A deep neural network is trained to predict the optical flow in a region using information from everywhere else but that region (context), while another…

Context of data points, which is usually defined as the other data points in a data set, has been found to play important roles in data representation and classification. In this paper, we study the problem of using context of a data point…

Causal approaches to fairness have seen substantial recent interest, both from the machine learning community and from wider parties interested in ethical prediction algorithms. In no small part, this has been due to the fact that causal…