Robert Pless

NeurIPS Conference 2025 Conference Paper

QuARI: Query Adaptive Retrieval Improvement

• Eric Xing
• Abby Stylianou
• Robert Pless
• Nathan Jacobs

Massive-scale pretraining has made vision-language models increasingly popular for image-to-image and text-to-image retrieval across a broad collection of domains. However, these models do not perform well when used for challenging retrieval tasks, such as instance retrieval in very large-scale image collections. Recent work has shown that linear transformations of VLM features trained for instance retrieval can improve performance by emphasizing subspaces that relate to the domain of interest. In this paper, we explore a more extreme version of this specialization by learning to map a given query to a query-specific feature space transformation. Because this transformation is linear, it can be applied with minimal computational cost to millions of image embeddings, making it effective for large-scale retrieval or re-ranking. Results show that this method consistently outperforms state-of-the-art alternatives, including those that require many orders of magnitude more computation at query time.

NeurIPS Conference 2023 Conference Paper

SG×P : A Sorghum Genotype × Phenotype Prediction Dataset and Benchmark

• Zeyu Zhang
• Robert Pless
• Nadia Shakoor
• Austin Carnahan
• Abby Stylianou

Large scale field-phenotyping approaches have the potential to solve important questions about the relationship of plant genotype to plant phenotype. Computational approaches to measuring the phenotype (the observable plant features) are required to address the problem at a large scale, but machine learning approaches to extract phenotypes from sensor data have been hampered by limited access to (a) sufficiently large, organized multi-sensor datasets, (b) field trials that have a large scale and significant number of genotypes, (c) full genetic sequencing of those phenotypes, and (d) datasets sufficiently organized so that algorithm centered researchers can directly address the real biological problems. To address this, we present SGxP, a novel benchmark dataset from a large-scale field trial consisting of the complete genotype of over 300 sorghum varieties, and time sequences of imagery from several field plots growing each variety, taken with RGB and laser 3D scanner imaging. To lower the barrier to entry and facilitate further developments, we provide a set of well organized, multi-sensor imagery and corresponding genomic data. We implement baseline deep learning based phenotyping approaches to create baseline results for individual sensors and multi-sensor fusion for detecting genetic mutations with known impacts. We also provide and support an open-ended challenge by identifying thousands of genetic mutations whose phenotypic impacts are currently unknown. A web interface for machine learning researchers and practitioners to share approaches, visualizations and hypotheses supports engagement with plant biologists to further the understanding of the sorghum genotype x phenotype relationship. The full dataset, leaderboard (including baseline results) and discussion forums can be found at http: //sorghumsnpbenchmark. com.

AAAI Conference 2019 Conference Paper

Hotels-50K: A Global Hotel Recognition Dataset

• Abby Stylianou
• Hong Xuan
• Maya Shende
• Jonathan Brandt
• Richard Souvenir
• Robert Pless

Recognizing a hotel from an image of a hotel room is important for human trafficking investigations. Images directly link victims to places and can help verify where victims have been trafficked, and where their traffickers might move them or others in the future. Recognizing the hotel from images is challenging because of low image quality, uncommon camera perspectives, large occlusions (often the victim), and the similarity of objects (e. g. , furniture, art, bedding) across different hotel rooms. To support efforts towards this hotel recognition task, we have curated a dataset of over 1 million annotated hotel room images from 50, 000 hotels. These images include professionally captured photographs from travel websites and crowd-sourced images from a mobile application, which are more similar to the types of images analyzed in real-world investigations. We present a baseline approach based on a standard network architecture and a collection of data-augmentation approaches tuned to this problem domain.

IROS Conference 2007 Conference Paper

Faster and more accurate face detection on mobile robots using geometric constraints

• Michael Dixon
• Frederick Heckel
• Robert Pless
• William D. Smart

We develop a framework to allow generic object detection algorithms to exploit geometric information commonly available to robot vision systems. Robot systems take pictures with calibrated cameras from known positions and may simultaneously capture depth measurements in the scene. This allows known constraints on the 3D size and position of objects to be translated into constraints on potential locations and scales of objects in the image, eliminating potentially expensive image operations for geometrically infeasible object locations. We show this integration to be very natural in the context of face detection and find that the computational effort of the standard Viola Jones face detector (as implemented in OpenCV) can be reduced by 85 percent with three times fewer false positives.

IROS Conference 2004 Conference Paper

Extrinsic calibration of a camera and laser range finder (improves camera calibration)

• Qilong Zhang
• Robert Pless

We describe theoretical and experimental results for the extrinsic calibration of sensor platform consisting of a camera and a 2D laser range finder. The calibration is based on observing a planar checkerboard pattern and solving for constraints between the "views" of a planar checkerboard calibration pattern from a camera and laser range finder. We give a direct solution that minimizes an algebraic error from this constraint, and subsequent nonlinear refinement minimizes a re-projection error. To our knowledge, this is the first published calibration tool for this problem. Additionally we show how this constraint can reduce the variance in estimating intrinsic camera parameters.

TCS Journal 2000 Journal Article

Fault tolerant K-center problems

• Samir Khuller
• Robert Pless
• Yoram J. Sussmann

The basic K-center problem is a fundamental facility location problem, where we are asked to locate K facilities in a graph, and to assign vertices to facilities, so as to minimize the maximum distance from a vertex to the facility to which it is assigned. This problem is known to be NP-hard, and several optimal approximation algorithms that achieve an approximation factor of 2 have been developed for it. We focus our attention on a generalization of this problem, where each vertex is required to have a set of α (α⩽K) centers close to it. In particular, we study two different versions of this problem. In the first version, each vertex is required to have at least α centers close to it. In the second version, each vertex that does not have a center placed on it is required to have at least α centers close to it. For both these versions we are able to provide polynomial time approximation algorithms that achieve constant approximation factors for any α. For the first version we give an algorithm that achieves an approximation factor of 3 for any α, and achieves an approximation factor of 2 for α<4. For the second version, we provide algorithms with approximation factors of 2 for any α. The best possible approximation factor for even the basic K-center problem is 2, assuming P≠NP. In addition, we give a polynomial time approximation algorithm for a generalization of the K-supplier problem where a subset of at most K supplier nodes must be selected as centers so that every demand node has at least α centers close to it. For this version our approximation factor is 3. The best possible approximation factor for even the basic K-supplier problem is 3, assuming P≠NP.

SODA Conference 2000 Conference Paper

On local search and placement of meters in networks

• Samir Khuller
• Randeep Bhatia
• Robert Pless

SODA Conference 1999 Conference Paper

The Full Degree Spanning Tree Problem

• Randeep Bhatia
• Samir Khuller
• Robert Pless
• Yoram J. Sussmann