47 accepted papers
Spatio-temporal reasoning is a remarkable capability of Vision Language Models (VLMs), but the underlying mechanisms of such abilities remain largely opaque. We postulate that visual/geometrical and textual representations of spatial structure must be combined at some point in VLM computations. We s…
Contrastive Language-Image Pre-Training (CLIP) is a popular method for learning multimodal latent spaces with well-organized semantics. Despite its wide range of applications, CLIP's latent space is known to fail at handling complex visual-textual interactions. Recent works attempt to address its sh…
Orientation-rich images, such as fingerprints and textures, often exhibit coherent angular directional patterns that are challenging to model using standard generative approaches based on isotropic Euclidean diffusion. Motivated by the role of phase synchronization in biological systems, we propose…
How can we troubleshoot a deep visual model, i.e., understand why it makes certain mistakes and further take action to correct its behavior? We design a Model Diagnosis and Correction system (MDC), an automated framework that analyzes the pattern of errors, proposes candidate causes of attributes, c…
We propose a method for discovering and visualizing the differences between two learned representations, enabling more direct and interpretable model comparisons. We validate our method, which we call Representational Differences Explanations (RDX), by using it to compare models with known conceptua…
How do two deep neural networks differ in how they arrive at a decision? Measuring the similarity of deep networks has been a long-standing open question. Most existing methods provide a single number to measure the similarity of two networks at a given layer, but give no insight into what makes th…
"Model performance evaluation is a critical and expensive task in machine learning and computer vision. Without clear guidelines, practitioners often estimate model accuracy using a one-time completely random selection of the data. However, by employing tailored sampling and estimation strategies, o…
Diffusion models are generative models with impressive text-to-image synthesis capabilities and have spurred a new wave of creative methods for classical machine learning tasks. However the best way to harness the perceptual knowledge of these generative models for visual tasks is still an open ques…
Quantifying motion in 3D is important for studying the behavior of humans and other animals, but manual pose annotations are expensive and time-consuming to obtain. Self-supervised keypoint discovery is a promising strategy for estimating 3D poses without annotations. However, current keypoint disco…
We propose an experimental method for measuring bias in face recognition systems. Existing methods to measure bias depend on benchmark datasets that are collected in the wild and annotated for protected (e.g., race, gender) and non-protected (e.g., pose, lighting) attributes. Such observational data…
We introduce MABe22, a large-scale, multi-agent video and trajectory benchmark to assess the quality of learned behavior representations. This dataset is collected from a variety of biology experiments, and includes triplets of interacting mice (4.7 million frames video+pose tracking data, 10 millio…
Estimating the geographical range of a species from sparse observations is a challenging and important geospatial prediction problem. Given a set of locations where a species has been observed, the goal is to build a model to predict whether the species is present or absent at any location. This pro…
Humans can perceive multiple expressions, each one with varying intensity, in the picture of a face. We propose a methodology for collecting and modeling multidimensional modulated expression annotations from human annotators. Our data reveals that the perception of some expressions can be quite dif…
"Weakly supervised object localization (WSOL) aims to learn representations that encode object location using only image-level category labels. However, many objects can be labeled at different levels of granularity. Is it an animal, a bird, or a great horned owl? Which image-level labels should we…
"We present a method for finding paths in a deep generative model’s latent space that can maximally vary one set of image features while holding others constant. Crucially, unlike past traversal approaches, ours can manipulate arbitrary multidimensional features of an image such as facial identity a…
We propose a method for learning the posture and structure of agents from unlabelled behavioral videos. Starting from the observation that behaving agents are generally the main sources of movement in behavioral videos, our method, Behavioral Keypoint Discovery (B-KinD), uses an encoder-decoder arch…
"We present the Caltech Fish Counting Dataset (CFC), a large-scale dataset for detecting, tracking, and counting fish in sonar videos. We identify sonar videos as a rich source of data for advancing low signal-to-noise computer vision applications and tackling domain generalization in multiple-objec…
Text spotting end-to-end methods have recently gained attention in the literature due to the benefits of jointly optimizing the text detection and recognition components. Existing methods usually have a distinct separation between the detection and recognition branches, requiring exact annotations f…
"We introduce Semi-supervised Performance Evaluation for Face Recognition (SPE-FR). SPE-FR is a statistical method for evaluating the performance and algorithmic bias of face verification systems when identity labels are unavailable or incomplete. The method is based on parametric Bayesian modeling…
"Each year, thousands of people learn new visual categorization tasks - radiologists learn to recognize tumors, birdwatchers learn to distinguish similar species, and crowd workers learn how to annotate valuable data for applications like autonomous driving. As humans learn, their brain updates the…
Predicting all applicable labels for a given image is known as multi-label classification. Compared to the standard multi-class case (where each image has only one label), it is considerably more challenging to annotate training data for multi-label classification. When the number of potential label…
We propose a framework for sequence-to-sequence contrastive learning (SeqCLR) of visual representations, which we apply to text recognition. To account for the sequence-to-sequence structure, each feature map is divided into different instances over which the contrastive loss is computed. This opera…
Specialized domain knowledge is often necessary to accurately annotate training sets for in-depth analysis, but can be burdensome and time-consuming to acquire from domain experts. This issue arises prominently in automated behavior analysis, in which agent movements or actions of interest are detec…
Multi-agent behavior modeling aims to understand the interactions that occur between agents. We present a multi-agent dataset from behavioral neuroscience, the Caltech Mouse Social Interactions (CalMS21) Dataset. Our dataset consists of trajectory data of social interactions, recorded from videos of…
Trained on large datasets, deep learning (DL) can accurately classify videos into hundreds of diverse classes. However, video data is expensive to annotate. Zero-shot learning (ZSL) proposes one solution to this problem. ZSL trains a model once, and generalizes to new tasks whose classes are not pre…
Measuring algorithmic bias is crucial both to assess algorithmic fairness, and to guide the improvement of algorithms. Current bias measurement methods in computer vision are based on observational datasets, and conflate algorithmic bias with dataset bias. To address this problem we develop an exper…
We propose a novel loss function that dynamically re-scales the cross entropy based on prediction difficulty regarding a sample. Deep neural network architectures in image classification tasks struggle to disambiguate visually similar objects. Likewise, in human pose estimation symmetric body parts…
Appearance information alone is often not sufficient to accurately differentiate between fine-grained visual categories. Human experts make use of additional cues such as where, and when, a given image was taken in order to inform their final decision. This contextual information is readily availabl…
We introduce a method to generate vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function, we process images through a "probe network" and compute an embeddi…
How can we help a forgetful learner learn multiple concepts within a limited time frame? While there have been extensive studies in designing optimal schedules for teaching a single concept given a learner's memory model, existing approaches for teaching multiple concepts are typically based on heur…
Low dimensional embeddings that capture the main variations of interest in collections of data are important for many applications. One way to construct these embeddings is to acquire estimates of similarity from the crowd. Similarity is a multi-dimensional concept that varies from individual to ind…
We introduce a method for efficiently crowdsourcing multiclass annotations in challenging, real world image datasets. Our method is designed to minimize the number of human annotations that are necessary to achieve a desired level of confidence on class labels. It is based on combining models of wor…
Modern applications of machine teaching for humans often involve domain-specific, non- trivial target hypothesis classes. To facilitate understanding of the target hypothesis, it is crucial for the teaching algorithm to use examples which are interpretable to the human learner. In this paper, we pro…
It is desirable for detection and classification algorithms to generalize to unfamiliar environments, but suitable benchmarks for quantitatively studying this phenomenon are not yet available. We present a dataset designed to measure recognition generalization to novel environments. The images in ou…
We study the problem of computer-assisted teaching with explanations. Conventional approaches for machine teaching typically only provide feedback at the instance level e.g., the category or label of the instance. However, it is intuitive that clear explanations from a knowledgeable teacher can…
Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories. In contrast, the natural world is heavily imbalanced, as some species are more abundant and easier to photograph than others. To encourage further progress in challe…
In real-world applications of education, an effective teacher adaptively chooses the next example to teach based on the learner’s current state. However, most existing work in algorithmic machine teaching focuses on the batch setting, where adaptivity plays no role. In this paper, we study the case…
There is a need for simple yet accurate white-box learning systems that train quickly and with little data. To this end, we showcase REBEL, a multi-class boosting method, and present a novel family of weak learners called localized similarities. Our framework provably minimizes the training error of…
We propose a new method to analyze the impact of errors in algorithms for multi-instance pose estimation and a principled benchmark that can be used to compare them. We define and characterize three classes of errors - localization, scoring, and background - study how they are influenced by instance…
We propose and systematically evaluate three strategies for training dynamically-routed artificial neural networks: graphs of learned transformations through which different input signals may take different paths. Though some approaches have advantages over others, the resulting networks are often q…
We introduce a method to greatly reduce the amount of redundant annotations required when crowdsourcing annotations such as bounding boxes, parts, and class labels. For example, if two Mechanical Turkers happen to click on the same pixel location when annotating a part in a given image--an event tha…
We propose a framework for detecting action patterns from motion sequences and modeling the sensory-motor relationship of animals, using a generative recurrent neural network. The network has a discriminative part (classifying actions) and a generative part (predicting motion), whose recurrent cells…
Images are formed by counting how many photons traveling from a given set of directions hit an image sensor during a given time interval. When photons are few and far in between, the concept of `image' breaks down and it is best to consider directly the flow of photons. Computer vision in this regim…
Each corner of the inhabited world is imaged from multiple viewpoints with increasing frequency. Online map services like Google Maps or Here Maps provide direct access to huge amounts of densely sampled, georeferenced images from street view and aerial perspective. There is an opportunity to design…
We present a domain-general account of causation that applies to settings in which macro-level causal relations between two systems are of interest, but the relevant causal features are poorly understood and have to be aggregated from vast arrays of micro-measurements. Our approach generalizes that…
We introduce tools and methodologies to collect high quality, large scale fine-grained computer vision datasets using citizen scientists -- crowd annotators who are passionate and knowledgeable about specific domains such as birds or airplanes. We worked with citizen scientists and domain experts t…
A video dataset that is designed to study fine-grained categorisation of pedestrians is introduced. Pedestrians were recorded ``in-the-wild'' from a moving vehicle. Annotations include bounding boxes, tracks, 14 keypoints with occlusion information and the fine-grained categories of age (5 classes),…