Skip to yearly menu bar Skip to main content


Session

Oral Session 4: Vision Applications and Optimization

Moderator: Julien Mairal

Abstract:
Chat is not available.

Fri 10 Dec. 0:00 - 0:15 PST

Oral
Passive attention in artificial neural networks predicts human visual selectivity

Thomas Langlois · Haicheng Zhao · Erin Grant · Ishita Dasgupta · Tom Griffiths · Nori Jacoby

Developments in machine learning interpretability techniques over the past decade have provided new tools to observe the image regions that are most informative for classification and localization in artificial neural networks (ANNs). Are the same regions similarly informative to human observers? Using data from 79 new experiments and 7,810 participants, we show that passive attention techniques reveal a significant overlap with human visual selectivity estimates derived from 6 distinct behavioral tasks including visual discrimination, spatial localization, recognizability, free-viewing, cued-object search, and saliency search fixations. We find that input visualizations derived from relatively simple ANN architectures probed using guided backpropagation methods are the best predictors of a shared component in the joint variability of the human measures. We validate these correlational results with causal manipulations using recognition experiments. We show that images masked with ANN attention maps were easier for humans to classify than control masks in a speeded recognition experiment. Similarly, we find that recognition performance in the same ANN models was likewise influenced by masking input images using human visual selectivity maps. This work contributes a new approach to evaluating the biological and psychological validity of leading ANNs as models of human vision: by examining their similarities and differences in terms of their visual selectivity to the information contained in images.

Fri 10 Dec. 0:15 - 0:20 PST

Q&A
Q&A

Fri 10 Dec. 0:20 - 0:35 PST

Oral
Shape As Points: A Differentiable Poisson Solver

Songyou Peng · Chiyu Jiang · Yiyi Liao · Michael Niemeyer · Marc Pollefeys · Andreas Geiger

In recent years, neural implicit representations gained popularity in 3D reconstruction due to their expressiveness and flexibility. However, the implicit nature of neural implicit representations results in slow inference times and requires careful initialization. In this paper, we revisit the classic yet ubiquitous point cloud representation and introduce a differentiable point-to-mesh layer using a differentiable formulation of Poisson Surface Reconstruction (PSR) which allows for a GPU-accelerated fast solution of the indicator function given an oriented point cloud. The differentiable PSR layer allows us to efficiently and differentiably bridge the explicit 3D point representation with the 3D mesh via the implicit indicator field, enabling end-to-end optimization of surface reconstruction metrics such as Chamfer distance. This duality between points and meshes hence allows us to represent shapes as oriented point clouds, which are explicit, lightweight and expressive. Compared to neural implicit representations, our Shape-As-Points (SAP) model is more interpretable, lightweight, and accelerates inference time by one order of magnitude. Compared to other explicit representations such as points, patches, and meshes, SAP produces topology-agnostic, watertight manifold surfaces. We demonstrate the effectiveness of SAP on the task of surface reconstruction from unoriented point clouds and learning-based reconstruction.

Fri 10 Dec. 0:35 - 0:40 PST

Q&A
Q&A

Fri 10 Dec. 0:40 - 0:55 PST

Oral
Optimal Rates for Random Order Online Optimization

Uri Sherman · Tomer Koren · Yishay Mansour

We study online convex optimization in the random order model, recently proposed by Garber et al. (2020), where the loss functions may be chosen by an adversary, but are then presented to the online algorithm in a uniformly random order. Focusing on the scenario where the cumulative loss function is (strongly) convex, yet individual loss functions are smooth but might be non-convex, we give algorithms that achieve the optimal bounds and significantly outperform the results of Garber et al. (2020), completely removing the dimension dependence and improve their scaling with respect to the strong convexity parameter. Our analysis relies on novel connections between algorithmic stability and generalization for sampling without-replacement analogous to those studied in the with-replacement i.i.d. setting, as well as on a refined average stability analysis of stochastic gradient descent.

Fri 10 Dec. 0:55 - 1:00 PST

Q&A
Q&A